I'm working with (un-paired/independent) environmental data collected over 2 consecutive months that I'd like to compare for each calendar year (CYR). I have many years and several months of data so running each test one by one is too tedious. I found a useful piece of code for running multiple Kruskal-Wallis tests, but given that the Wilcoxon only compares 2 groups at once and my groups (Month or Month2) change slightly per year (depending on when data were collected) this code won't work - that I know of. Thanks in advance!
# Kruskal-Wallis code (hoping for something like this using wilcoxon test instead):
by(dry_season, dry_season$CYR, function(z) kruskal.test(temp ~ Month2, data = z))
# With these settings (March and April are just examples from my data):
wilcox.test(March, April, mu=0, alt="two.sided", paired=F, conf.int=T, conf.level=0.8, exact = F, correct = F)
# Data:
> dput(dry_season)
structure(list(use_for_analysis = structure(c(3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 3L,
3L, 3L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 1L,
3L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 3L, 3L, 3L, 1L,
1L, 3L, 3L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 1L, 1L, 3L, 3L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 1L,
3L, 3L, 1L, 3L, 3L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 3L, 3L,
1L, 3L, 3L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
1L, 1L, 3L, 3L, 3L, 1L, 3L, 3L, 3L, 3L, 1L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 1L, 3L, 1L, 3L, 3L, 3L, 3L, 1L, 3L, 1L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 1L, 3L, 3L, 1L, 3L, 3L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
1L, 3L, 3L, 3L, 3L, 3L, 1L, 3L, 3L, 3L, 3L, 1L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
1L, 3L, 3L, 1L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 1L, 1L, 3L, 3L, 3L, 1L, 3L, 3L, 3L, 3L, 1L,
3L, 3L, 3L, 1L, 3L, 3L, 1L, 3L, 1L, 3L, 3L, 3L, 3L, 3L, 1L, 3L,
3L, 3L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L), levels = c("Pre_SAV", "Pre_storm", "Standard"
), class = "factor"), CYR = structure(c(9L, 9L, 9L, 9L, 12L,
12L, 9L, 9L, 9L, 9L, 12L, 7L, 6L, 12L, 6L, 6L, 12L, 12L, 2L,
9L, 9L, 9L, 2L, 9L, 7L, 5L, 6L, 6L, 7L, 9L, 6L, 12L, 12L, 12L,
12L, 2L, 9L, 2L, 9L, 9L, 9L, 12L, 5L, 7L, 2L, 9L, 12L, 6L, 5L,
6L, 6L, 7L, 6L, 5L, 12L, 12L, 2L, 9L, 12L, 7L, 9L, 9L, 7L, 2L,
5L, 5L, 12L, 2L, 2L, 9L, 12L, 2L, 5L, 7L, 6L, 9L, 6L, 7L, 12L,
5L, 7L, 6L, 6L, 6L, 12L, 9L, 12L, 6L, 2L, 2L, 5L, 9L, 2L, 9L,
5L, 12L, 6L, 9L, 12L, 2L, 12L, 7L, 2L, 5L, 7L, 2L, 6L, 9L, 7L,
6L, 6L, 5L, 6L, 2L, 9L, 6L, 2L, 9L, 12L, 2L, 6L, 7L, 9L, 12L,
7L, 12L, 9L, 12L, 5L, 5L, 12L, 6L, 2L, 2L, 7L, 7L, 6L, 2L, 9L,
7L, 5L, 6L, 2L, 6L, 5L, 6L, 12L, 12L, 9L, 5L, 9L, 2L, 7L, 2L,
5L, 7L, 9L, 6L, 2L, 7L, 2L, 5L, 12L, 6L, 7L, 7L, 6L, 7L, 2L,
6L, 6L, 5L, 5L, 12L, 12L, 6L, 7L, 9L, 5L, 9L, 12L, 2L, 9L, 6L,
2L, 7L, 12L, 2L, 7L, 6L, 9L, 6L, 7L, 5L, 5L, 5L, 2L, 7L, 6L,
5L, 7L, 7L, 2L, 9L, 7L, 12L, 12L, 2L, 12L, 6L, 9L, 12L, 6L, 5L,
6L, 9L, 5L, 9L, 2L, 5L, 7L, 7L, 9L, 7L, 7L, 5L, 7L, 5L, 2L, 6L,
12L, 2L, 2L, 6L, 12L, 7L, 5L, 5L, 9L, 9L, 12L, 5L, 7L, 6L, 5L,
5L, 6L, 5L, 7L, 2L, 2L, 7L, 12L, 12L, 2L, 12L, 5L, 5L, 6L, 2L,
5L, 7L, 7L, 2L, 5L, 6L, 2L, 5L, 2L, 7L, 7L, 12L, 5L, 5L, 2L,
5L, 12L, 5L, 7L, 5L, 7L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L), levels = c("2005", "2006", "2007",
"2008", "2014", "2015", "2016", "2017", "2018", "2019", "2021",
"2022"), class = "factor"), Season = c("DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY", "DRY",
"DRY"), Month = c(3, 2, 3, 2, 3, 2, 2, 3, 2, 3, 3, 4, 4, 3, 4,
3, 3, 2, 3, 2, 3, 2, 3, 3, 4, 3, 4, 4, 4, 3, 3, 3, 2, 3, 3, 2,
2, 3, 2, 3, 3, 3, 3, 4, 3, 3, 3, 4, 3, 4, 3, 4, 3, 3, 3, 2, 3,
2, 3, 3, 2, 3, 3, 2, 4, 3, 3, 2, 3, 2, 3, 2, 3, 4, 4, 3, 3, 4,
3, 3, 4, 3, 3, 4, 3, 2, 2, 3, 3, 2, 3, 3, 2, 3, 3, 3, 4, 2, 3,
3, 3, 4, 2, 3, 4, 3, 3, 2, 3, 3, 4, 4, 3, 3, 3, 3, 2, 2, 3, 2,
4, 4, 3, 3, 3, 2, 3, 3, 3, 3, 3, 3, 3, 2, 4, 3, 4, 3, 2, 4, 4,
3, 3, 3, 3, 3, 3, 2, 2, 3, 3, 2, 4, 2, 3, 3, 3, 3, 2, 3, 3, 3,
3, 4, 4, 3, 4, 3, 3, 3, 3, 3, 3, 3, 2, 3, 4, 3, 3, 3, 3, 3, 3,
4, 2, 4, 3, 2, 3, 4, 2, 3, 3, 4, 3, 3, 2, 4, 3, 3, 3, 3, 3, 3,
4, 3, 3, 3, 3, 3, 3, 2, 3, 4, 4, 3, 3, 2, 3, 3, 3, 3, 3, 4, 4,
3, 3, 4, 2, 3, 3, 2, 2, 3, 3, 3, 3, 3, 3, 2, 3, 3, 3, 3, 3, 4,
3, 3, 4, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 2, 4, 3, 4, 2, 3, 3, 2,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2),
Site = c(17, 46, 27, 37, 18, 40, 45, 16, 47, 26, 29, 23,
17, 1, 9, 47, 19, 41, 16, 44, 15, 36, 17, 25, 6, 47, 8, 16,
22, 8, 40, 30, 42, 2, 20, 31, 35, 18, 43, 14, 24, 11, 16,
21, 15, 7, 31, 15, 46, 6, 31, 13, 41, 39, 21, 43, 14, 42,
3, 41, 34, 23, 47, 47, 8, 45, 10, 30, 19, 40, 32, 39, 15,
20, 14, 6, 21, 5, 22, 38, 12, 39, 46, 7, 4, 33, 44, 30, 13,
29, 44, 13, 38, 22, 14, 9, 13, 41, 33, 20, 23, 4, 46, 17,
19, 8, 20, 39, 46, 45, 5, 7, 38, 12, 12, 29, 37, 32, 5, 28,
12, 3, 5, 24, 40, 45, 21, 8, 37, 43, 34, 19, 21, 45, 18,
45, 4, 7, 38, 11, 6, 28, 11, 37, 13, 44, 25, 46, 31, 36,
4, 27, 2, 36, 42, 27, 20, 18, 44, 39, 22, 18, 35, 3, 10,
34, 11, 44, 10, 27, 36, 12, 35, 6, 47, 43, 17, 3, 41, 11,
26, 6, 19, 10, 26, 1, 36, 35, 38, 2, 30, 26, 26, 5, 19, 34,
43, 9, 35, 40, 33, 43, 23, 10, 16, 7, 27, 5, 37, 25, 2, 39,
42, 4, 1, 18, 33, 29, 9, 20, 37, 42, 9, 15, 8, 11, 25, 3,
25, 24, 28, 34, 42, 34, 14, 32, 32, 21, 1, 28, 12, 10, 24,
23, 22, 2, 33, 31, 14, 33, 41, 31, 38, 15, 3, 13, 9, 23,
22, 24, 1, 36, 7, 40, 30, 32, 32, 24, 2, 30, 35, 16, 25,
29, 1, 28, 17, 26, 29, 27, 28, 4, 1, 2, 3, 4, 5, 6, 7, 8,
9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23,
24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38,
39, 40, 41, 42, 43, 44, 45, 46, 47), temp = c(24.7, 24.7,
24.3, 24.8, 23.5, 26.3, 24.2, 24.6, 24.1, 24.6, 22.5, 25.8,
23.2, 25.4, 23.7, 25.8, 23.9, 25.6, 18.66, 25.7, 24.8, 24.6,
21.36, 24, 24.7, 20.9, 24, 23.3, 25.7, 22.5, 24.8, 23.5,
25.3, 26.3, 23.9, 25.03, 24.9, 21.58, 25.6, 24.7, 24.5, 25.4,
22.4, 25.9, 19.24, 23.4, 23.4, 23.2, 20.5, 25.3, 26.3, 22.5,
25, 22.2, 24, 26, 19.32, 24.5, 25.8, 23.2, 25.7, 24.8, 26,
23.6, 21.7, 19.9, 25.4, 25.57, 21.95, 27.1, 23.9, 24.9, 21.9,
24.6, 23.8, 24.2, 26.1, 24.7, 24, 21.6, 22.9, 27.4, 26.3,
25.2, 25.6, 25.4, 25.3, 26.4, 19.48, 25.82, 21.4, 25, 25.15,
25.2, 22.3, 26.1, 24.1, 25.8, 24.1, 23.04, 23.6, 24.6, 24.18,
22.9, 26, 22.85, 26, 27.3, 26.9, 26.6, 25, 22.4, 28.4, 19.79,
25.3, 26.3, 25.72, 24.8, 26.6, 25.29, 24.1, 25.1, 25.1, 23.5,
23.1, 24.9, 25.7, 26.4, 21.5, 20.8, 24.3, 26.2, 23.82, 23.9,
26.1, 27, 25.8, 23.37, 28.5, 23.9, 23.2, 26.2, 20.55, 26.6,
22.5, 26.2, 23.6, 25.1, 25.4, 22.4, 24.8, 26.04, 25.3, 25.88,
21.8, 28.6, 25.5, 26.8, 24.51, 23.7, 24.02, 22.9, 24.4, 25.9,
23.3, 28.2, 25, 26.3, 21, 26.7, 28.6, 22.5, 22.3, 26.5, 26.5,
28, 25.9, 25.5, 21.5, 25.8, 23.6, 23.79, 26.1, 24.7, 27.16,
25.5, 24.3, 26.97, 23.7, 26.2, 25.8, 27.2, 29.9, 23.7, 23,
21.5, 24.93, 24.5, 28.6, 22.1, 28.3, 27.4, 24.17, 25.8, 26.1,
26.8, 24.1, 23.66, 24.3, 26.6, 24.5, 27.3, 28.1, 24.2, 26.6,
25.8, 22.4, 26.2, 22.13, 24.5, 24, 27.2, 26.9, 25.3, 24.8,
22.6, 29.5, 24.7, 28.06, 27.1, 24.3, 27.37, 25.89, 26, 27.5,
28.7, 22.3, 24.2, 26, 26.7, 26.8, 22, 29.2, 27.7, 24, 24.4,
27.9, 22.7, 27.2, 28.09, 26.83, 28.4, 25.3, 27, 25.52, 27.9,
23.4, 24.6, 27.4, 28.3, 24.9, 24.4, 26.1, 26.58, 23.6, 28.3,
28.94, 24.4, 26.3, 29.5, 24.6, 28.1, 25.9, 24.6, 26.48, 24.8,
28.5, 25.3, 29.9, 24.6, 29.3, 24.46, 20, 20, 19, 20, 20,
19, 23, 21, 22, 21, 21, 20, 19, 19, 19, 19, 20, 19, 20, 17,
18, 19, 19, 20, 20, 19, 18, 17.5, 19, 19, 19, 19, 18, 18,
19, 19, 19, 19, 20, 20, 19, 20, 20, 20, 20, 21, 21), sal = c(21.29,
33.36, 15.14, 21.77, 25.37, 22.98, 32.4, 22.6, 32.12, 15.49,
20.52, 11.92, 27.33, 28.37, 30.53, 34.62, 24.45, 22.04, 32.48,
33.58, 25.2, 20.77, 27.89, 11.36, 23.64, 28.55, 31.21, 27.49,
13.21, 29.39, 31.54, 21.53, 23.25, 27.55, 22.52, 23.99, 20.4,
25.94, 32.65, 26.36, 11.76, 25.08, 24.33, 13.2, 32.46, 29.36,
22.7, 27.51, 30.08, 31.35, 27.92, 20.49, 32.29, 19.09, 20.72,
25.37, 32.41, 29.26, 28.22, 20.01, 20.07, 11.69, 26.48, 25.8,
30.29, 30.64, 25.47, 25.88, 24.12, 32.13, 22.37, 29.3, 24.44,
12.71, 28.69, 29.94, 25.05, 25.01, 20.79, 13.21, 21.48, 31.62,
33.74, 31.89, 28.01, 20.16, 23.74, 27.41, 32.55, 26.18, 27.49,
27.94, 27.29, 12.98, 26.13, 25.97, 29.49, 25.37, 22.47, 24.47,
20.04, 25.29, 26.56, 23.94, 15.42, 31.41, 24.39, 28.7, 26.42,
33.79, 30.42, 29.19, 31.53, 31.66, 28.33, 25.14, 26.8, 17.55,
27.37, 26.61, 29.8, 25.43, 30.31, 20.04, 17.71, 21.32, 13.05,
26.14, 17.23, 28.6, 22.52, 23.33, 19.29, 26.6, 13.54, 28.12,
31.57, 29.08, 27.46, 22.86, 22.71, 24.7, 32.59, 29.62, 28.31,
33.71, 19.66, 21.39, 16.24, 17.31, 30.67, 24.28, 25.54, 26.56,
26.9, 15.19, 16.56, 22.54, 26.2, 8.76, 19.63, 21.29, 22.82,
31.26, 22.2, 17.99, 30.07, 26.71, 29.02, 25.31, 29.7, 28.69,
17.48, 27.75, 27.64, 33.26, 18.74, 30.66, 28.05, 28.95, 19.8,
33.7, 13.48, 30.12, 24.23, 25.18, 22.57, 25.72, 7.88, 30.94,
15.33, 25.33, 15.89, 26.62, 15.4, 18.21, 27.07, 22.95, 29.72,
27.77, 18.55, 28, 19, 29.13, 18.57, 28.48, 20.25, 34, 21.65,
23.11, 29.77, 20.19, 32.93, 29.61, 32.25, 15.67, 18.5, 15.12,
30.52, 12.57, 9.62, 28.82, 29.05, 16.39, 23.45, 29.5, 10.56,
29.33, 23.72, 23.66, 20.33, 25.49, 25.69, 27.77, 25.3, 17.2,
20.69, 12.68, 30.88, 14.86, 24.92, 29.62, 8.06, 22.97, 13.57,
27.39, 27.45, 21.81, 16.97, 24.86, 26.03, 17.07, 15.57, 25.08,
33.34, 25.08, 29.94, 14.42, 23.65, 24.78, 30.59, 10.25, 24.55,
26.69, 23.37, 26.26, 25.24, 16.62, 31.83, 17.7, 10.51, 24.08,
17.45, 22.16, 32.63, 21.56, 23.51, 21.5, 14.04, 21.57, 13.7,
32.12, 37, 40, 38, 37, 38, 37, 28, 35, 32, 35, 36, 39, 36,
37, 35, 38, 36, 37, 38, 36, 31, 30, 28, 28, 28, 35, 31, 32,
31, 34, 34, 34, 25, 30, 25, 35, 35, 35, 34, 34, 32, 33, 32,
34, 33, 34, 34), DO = c(5.2, 2.7, 5.3, 4, 4.98, 5.04, 4,
5.4, 5, 6.1, 4.29, 4.68, 4.2, 6.51, 3.17, 4.91, 5.02, 4.24,
5.99, 4.5, 4.9, 5, NA, 5.9, 3.56, 5.7, 3.22, 5.2, 5.25, 5.9,
2.4, 4.45, 5.61, 5.42, 6.03, 4.47, 5.6, 9.91, 5.2, 5.9, 6.7,
2.05, 3.74, 6.4, NA, 5.5, 4.77, 7.07, 6.57, 5.17, 2.16, 4.4,
3.85, 5.05, 5.68, 4.74, NA, 6.8, 5.66, 5.57, 5.5, 6.9, 5.05,
7.89, 4.29, 6.78, 3.02, 4.48, 5.73, 5.3, 5.16, 5.96, 5.23,
7.16, 3.92, 4.9, 4.94, 6.7, 5.73, 7.05, 4.46, 3.53, 5.45,
5.05, 7.64, 6.2, 6.19, 4.09, NA, 4.61, 6.69, 5.1, 5.76, 7.2,
4.85, 4.09, 4.69, 10.2, 4.55, 9.87, 5.94, 6.96, 7.25, 6.65,
5.8, NA, 5.64, 5.5, 7.26, 6.83, 3.35, 5.48, 4.15, NA, 5.4,
3.59, 6.69, 5.3, 5.45, 6.22, 4.4, 7.98, 6.1, 6.07, 8.14,
6.45, 7.6, 5.72, 6.94, 7.13, 4.6, 5.03, 6.32, 7.21, 6.88,
8.69, 10.57, NA, 6.6, 7.05, 5.63, 5.41, NA, 3.61, 5.48, 6.42,
5.97, 6.94, 6.1, 8.26, 7.5, 6.06, 8.04, 6.07, 7.49, 4.94,
8.1, 5.52, 8.33, 8.82, 9.2, 7.63, 5.73, 4.69, 5.14, 7.18,
4.6, 7.32, NA, 5.33, 5.9, 5.83, 7.49, 5.21, 6.17, 7.99, 10.5,
7.2, 7.62, 5.3, 6.01, NA, 8.4, 3.92, 8.61, 7.85, 5.16, 7.28,
8.68, 3.79, 7.2, 6.19, 7.29, 5.72, 9.48, 7.15, 8.29, 7.8,
7.33, 7.66, 12.55, 9.88, 10.38, 5.3, 11.45, 4.45, 5.54, NA,
5.41, 4.52, 5.5, 6.73, 9.1, 8.15, 7.59, 9.4, 9.98, 7.7, NA,
9.3, 8.94, 9.74, 7.8, 8.95, 9.32, 7.25, 7.12, 8.11, 6.76,
5.75, 5.34, 7, 9.45, 6.19, 5.56, 7.84, 7.03, 9.26, 7.7, 8.6,
4.59, 6.01, 6.47, 7.6, 8.97, 5.17, 6.42, 7.32, 12.07, 8.38,
8.58, 7.2, 5.88, 4.77, NA, 8.23, 8.19, 12.67, 8.45, 8.76,
6.38, 9.51, 11.91, 8.1, 7.77, 5.58, 10.13, 10.21, NA, 11.72,
9.22, 7.87, 14.43, 9.22, NA, 9.88, 7.36, 10.71, 7.92, 7.42,
8.09, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA), water_depth = c(70, 45, 64, 76, 68,
95, 75, 91, 65, 84, 80, 80, 55, 98, 51, 97, 85, 92, 62, 65,
98, 98, 58, 83, 68, NA, 60, 80, 92, 68, 95, 85, 143, 108,
112, 72, 101, 63, 80, 106, 103, 75, 51, 85, 49, 85, 101,
72, NA, 70, 90, 117, 95, 81, 103, 98, 58, 53, 107, 72, 106,
102, 85, 74, 63, NA, 73, 70, 62, 81, 113, 79, 68, 96, 79,
90, 86, 95, 118, 86, 128, 101, 42, 70, 143, 95, 68, 100,
52, 60, NA, 90, 52, 102, 69, 84, 90, 43, 110, 64, 109, 96,
62, 99, 80, 110, 105, 90, 52, 83, 70, 80, 91, 40, 110, 105,
59, 96, 97, 56, 85, 102, 105, 113, 87, 98, 91, 75, 86, NA,
118, 103, 63, 84, 63, 62, 52, 115, 55, 83, 88, 104, 33, 78,
74, 43, 94, 59, 80, 80, 100, 50, 120, 72, NA, 30, 103, 98,
74, 95, 62, 79, 119, 62, 89, 57, 35, 53, 55, 85, 76, 88,
79, 75, 95, 45, 75, 79, NA, 74, 95, 65, 76, 50, 50, 95, 104,
35, 100, 62, 76, 78, 83, 88, 72, 75, 60, 60, 49, NA, 76,
50, 64, 73, 64, 83, 73, 80, 92, 64, 90, 78, 55, 64, 60, 57,
75, 71, 60, 48, 90, 67, 53, 67, 49, 65, 61, 77, 52, 60, 88,
68, 68, 70, 85, 75, 79, 64, 71, 57, 86, 52, 63, 70, 66, 82,
63, 60, 60, 70, 39, 77, 88, 84, 52, 98, 39, 50, 75, 62, 80,
75, 38, 72, 45, 66, 67, 50, 62, 80, 80, 70, 48, 59, 47, 70,
68, 65, 81, 46, 85, 49, 31, 29, 46, 41, 67, 42, 82, 80, 70,
68, 78, 52, 38, 30, 90, 90, 80, 83, 87, 75, 69, 28, 91, 108,
109, 80, 59, 68, 90, 90, 85, 80, 90, 90, 85, 95, 80, 80,
91, 89, 42, 78, 85, 72, 87, 90, 87), sed_depth = c(51, 4,
52, 47, 2, 45, 36, 39, 25, 54, 17, 18, 10, 45, 25, 78, 7,
69, NA, 105, 60, 35, NA, 58, 27, NA, 0, 15, 33, 6, 60, 29,
39, 22, 14, NA, 40, NA, 80, 34, 50, 19, 93, 33, NA, 39, 32,
15, NA, 50, 40, 4, 80, 92, 25, 72, NA, 27, 8, 73, 40, 66,
45, NA, 0, NA, 22, NA, NA, 46, 9, NA, 34, 27, 50, 47, 34,
21, 23, 54, 7, 49, 7, 60, 7, 28, 72, 36, NA, NA, NA, 30,
NA, 15, 87, 10, 10, 73, 59, NA, 23, 5, NA, 24, 25, NA, 15,
55, 4, 81, 25, 41, 61, NA, 35, 25, NA, 7, 5, NA, 15, 63,
25, 34, 73, 63, 32, 0, 45, NA, 25, 27, NA, NA, 0, 3, 5, NA,
61, 52, 32, 70, NA, 48, 53, 100, 30, 4, 37, 61, 9, NA, 10,
NA, NA, 75, 18, 18, NA, 75, NA, 1, 24, 33, 40, 35, 30, 100,
NA, 65, 50, 34, 58, 17, 45, 90, 19, 61, NA, 61, 33, NA, 13,
35, NA, 94, 42, NA, 57, 50, 26, 75, 27, 13, 40, 57, NA, 24,
61, NA, 9, 68, NA, 29, 43, 10.17, 21, NA, 30, 30, 38, 22,
90, 3, 60, 2, 14, 21, NA, 78, 42, 55, 30, 48, 0, 67, 69,
73, NA, 50, 23, NA, NA, 35, 29, 13, 53, 30, 74, 33, 1, 58,
43, 35, 30, 44, 26, 52, 35, NA, NA, 56, 45, 42, NA, 10, 21,
30, 30, NA, 73, 45, 57, NA, 63, 29, NA, 45, NA, 35, 38, 20,
35, 42, NA, 65, 24, 50, 5, 63, 15, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA), Month2 = structure(c(3L,
2L, 3L, 2L, 3L, 2L, 2L, 3L, 2L, 3L, 3L, 4L, 4L, 3L, 4L, 3L,
3L, 2L, 3L, 2L, 3L, 2L, 3L, 3L, 4L, 3L, 4L, 4L, 4L, 3L, 3L,
3L, 2L, 3L, 3L, 2L, 2L, 3L, 2L, 3L, 3L, 3L, 3L, 4L, 3L, 3L,
3L, 4L, 3L, 4L, 3L, 4L, 3L, 3L, 3L, 2L, 3L, 2L, 3L, 3L, 2L,
3L, 3L, 2L, 4L, 3L, 3L, 2L, 3L, 2L, 3L, 2L, 3L, 4L, 4L, 3L,
3L, 4L, 3L, 3L, 4L, 3L, 3L, 4L, 3L, 2L, 2L, 3L, 3L, 2L, 3L,
3L, 2L, 3L, 3L, 3L, 4L, 2L, 3L, 3L, 3L, 4L, 2L, 3L, 4L, 3L,
3L, 2L, 3L, 3L, 4L, 4L, 3L, 3L, 3L, 3L, 2L, 2L, 3L, 2L, 4L,
4L, 3L, 3L, 3L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 2L, 4L, 3L,
4L, 3L, 2L, 4L, 4L, 3L, 3L, 3L, 3L, 3L, 3L, 2L, 2L, 3L, 3L,
2L, 4L, 2L, 3L, 3L, 3L, 3L, 2L, 3L, 3L, 3L, 3L, 4L, 4L, 3L,
4L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 2L, 3L, 4L, 3L, 3L, 3L, 3L,
3L, 3L, 4L, 2L, 4L, 3L, 2L, 3L, 4L, 2L, 3L, 3L, 4L, 3L, 3L,
2L, 4L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 3L, 3L, 3L, 3L, 3L, 3L,
2L, 3L, 4L, 4L, 3L, 3L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 3L,
3L, 4L, 2L, 3L, 3L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 2L, 3L,
3L, 3L, 3L, 3L, 4L, 3L, 3L, 4L, 2L, 2L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 2L, 4L, 3L, 4L, 2L, 3L, 3L, 2L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), levels = c("Jan",
"Feb", "Mar", "Apr"), class = "factor")), row.names = c(NA,
-329L), class = c("tbl_df", "tbl", "data.frame"))
This will run the analysis for the temp data and should give you what you need to get the other variables you want. First we need to get rid of the empty factor levels in CYR:
dry_season <- droplevels(dry_season)
Now split the data and get rid of the empty factor levels in Month2:
dry_season.splt <- split(dry_season, dry_season$CYR)
dry_season.splt <- lapply(dry_season.splt, droplevels)
Now run the analysis for temp
results.temp <- lapply(dry_season.splt, function(x) wilcox.test(temp~Month2, x, conf.int=TRUE, conf.level=0.8, exact=FALSE, correct=FALSE))
names(results.temp)
results.temp[["2005"]] # or results.temp[[1]]
#
# Wilcoxon rank sum test
#
# data: temp by Month2
# W = 87.5, p-value = 0.5245
# alternative hypothesis: true location shift is not equal to 0
# 80 percent confidence interval:
# -9.999840e-01 1.470944e-05
# sample estimates:
# difference in location
# -1.393135e-05
Just change temp to the other variables to get their results.
Related
I am trying to remove the outliers from various variables at the same time in my dataset but with the function used it seems that when it finds one outlier it turns the whole row into NA.
That´s a problem because I have to apply the same process to a larger dataset and I am worried that it considerably reduces my sample...
So I would like to just turn the case where the outlier is into NA without turning the whole row into NA. Is that eventually possible?
Thank you for your input
#function used for outliers
outliers <- function(x) {
Q1 <- quantile(x, probs=.25, na.rm = TRUE)
Q3 <- quantile(x, probs=.75, na.rm = TRUE)
iqr = Q3-Q1
upper_limit = Q3 + (iqr*1.5)
lower_limit = Q1 - (iqr*1.5)
x > upper_limit | x < lower_limit
}
remove_outliers <- function(dflinear, cols = names(dflinear)) {
for (col in cols) {
dflinear <- dflinear[!outliers(dflinear[[col]]),]
}
dflinear
}
dflinear_without_outliers<-remove_outliers(dflinear, c("insuline", "glucose", "hdl","ldl"))
#Reproducible sample below
dflinear<- structure(list(id = structure(c("SA01", "SA02", "SA03", "SA04",
"SA05", "SA06", "SA07", "SA08", "SA09", "SA10", "SA11", "SA12",
"SA13", "SA14", "SA15", "SA16", "SA17", "SA18", "SA19", "SA20",
"SA21", "SA22", "SA23", "SA24", "SA25", "SA26", "SA27", "SA28",
"SA29", "SA30", "SA31", "SA32", "SA33", "SA34", "SA35", "SA36",
"SA37", "SA38", "SA39", "SA40", "SA41", "SA42", "SA43", "SA44",
"SA45", "SA46", "SA47", "SA48", "SA49", "SA50", "SA51", "SA52",
"SA53", "SA54", "SA56", "SA57", "SA58", "SA59", "SA60", "SA61",
"SA62", "SA63", "SA64", "SA65", "SA66", "SA67", "SA68", "SA69",
"SA72", "SA73", "SA74", "SA75", "SA76", "SA77", "SA78", "SA79",
"SA80", "SA81", "SA82", "SA83", "SA84", "SA85", "SA86", "SA87",
"SA88", "SA89", "SA90", "SA92", "SA93", "SA94", "SA95", "SA96",
"SA97", "SA99", "SA100", "SA101", "SA102", "SA103", "SA104",
"SA105", "SA107", "SA108", "SA109", "SA110", "SA111", "SA112",
"SA113", "SA114", "SA115", "SA116", "SA118", "SC01", "SC02",
"SC03", "SC04", "SC05", "SC06", "SC07", "SC08", "SC09", "SC10",
"SC11", "SC12", "SC13", "SC14", "SC15", "SC16", "SC17", "SC18",
"SC19", "SC20", "SC21", "SC22", "SC23", "SC24", "SC25", "SC26",
"SC27", "SC28", "SC29", "SC30", "SC31", "SC32", "SC33", "SC34",
"SC35", "SC36", "SC37", "SC38", "M01", "M02", "M03", "M04", "M05",
"M06", "M07", "M08", "M09", "M10", "M11", "M12", "M13", "M14",
"M15", "M16", "M17", "M18", "M19", "M20", "M21", "M22", "M23",
"M24", "M25", "M26", "M27", "M28", "M29", "M30", "M31", "M32",
"M33", "M34", "M35", "M36", "M37", "M38", "M39", "M40", "M41",
"M42", "M43", "M44", "M45", "M46", "M47", "M48", "M49", "M50",
"M51", "M52", "M53", "SA01", "SA02", "SA03", "SA04", "SA05",
"SA06", "SA07", "SA08", "SA09", "SA10", "SA11", "SA12", "SA13",
"SA14", "SA15", "SA16", "SA17", "SA18", "SA19", "SA20", "SA21",
"SA22", "SA23", "SA24", "SA25", "SA26", "SA27", "SA28", "SA29",
"SA30", "SA31", "SA32", "SA33", "SA34", "SA35", "SA36", "SA37",
"SA38", "SA39", "SA40", "SA41", "SA42", "SA43", "SA44", "SA45",
"SA46", "SA47", "SA48", "SA49", "SA50", "SA51", "SA52", "SA53",
"SA54", "SA56", "SA57", "SA58", "SA59", "SA60", "SA61", "SA62",
"SA63", "SA64", "SA65", "SA66", "SA67", "SA68", "SA69", "SA72",
"SA73", "SA74", "SA75", "SA76", "SA77", "SA78", "SA79", "SA80",
"SA81", "SA82", "SA83", "SA84", "SA85", "SA86", "SA87", "SA88",
"SA89", "SA90", "SA92", "SA93", "SA94", "SA95", "SA96", "SA97",
"SA99", "SA100", "SA101", "SA102", "SA103", "SA104", "SA105",
"SA107", "SA108", "SA109", "SA110", "SA111", "SA112", "SA113",
"SA114", "SA115", "SA116", "SA118", "SC01", "SC02", "SC03", "SC04",
"SC05", "SC06", "SC07", "SC08", "SC09", "SC10", "SC11", "SC12",
"SC13", "SC14", "SC15", "SC16", "SC17", "SC18", "SC19", "SC20",
"SC21", "SC22", "SC23", "SC24", "SC25", "SC26", "SC27", "SC28",
"SC29", "SC30", "SC31", "SC32", "SC33", "SC34", "SC35", "SC36",
"SC37", "SC38", "M01", "M02", "M03", "M04", "M05", "M06", "M07",
"M08", "M09", "M10", "M11", "M12", "M13", "M14", "M15", "M16",
"M17", "M18", "M19", "M20", "M21", "M22", "M23", "M24", "M25",
"M26", "M27", "M28", "M29", "M30", "M31", "M32", "M33", "M34",
"M35", "M36", "M37", "M38", "M39", "M40", "M41", "M42", "M43",
"M44", "M45", "M46", "M47", "M48", "M49", "M50", "M51", "M52",
"M53"), label = "Code of PrevenGo", format.spss = "A5", display_width = 12L),
group = structure(c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L), .Label = c("Metab", "SA", "SC"), class = "factor"),
sex = structure(c(2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 2L,
2L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L,
1L, 2L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 2L,
1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L,
2L, 2L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 2L,
1L, 2L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L,
1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 1L,
2L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 1L,
2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 1L,
1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 2L,
2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 2L,
1L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L,
1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 1L,
1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L,
1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 1L,
1L, 2L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L,
1L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 1L,
1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L,
2L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 2L,
2L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L,
2L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L,
1L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 1L,
1L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L,
1L, 2L, 2L, 2L), .Label = c("F", "M"), class = "factor"),
time = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L), insuline = structure(c(9, 4.1, 3.3, 9.4, 22.9, 16.2,
8.7, 16.7, 21.2, 21, 12.8, 7.3, 38.4, 20.2, 19.6, 6.4, 18.9,
12.1, 8.2, 17, 15.6, 12.5, 19.1, 13.7, 8, 20.1, 19.8, 6.8,
15.4, 14.7, 11.9, 8.8, 7.9, 51.2, 10.8, 8.1, 28.6, 8.6, 27.9,
13.3, 9, 16.3, 13.3, 5.8, 27.3, 4.2, 8.2, 9.9, 20.1, 11.7,
8.7, 18.1, 10.9, 27.4, 14.6, 29.1, 10.2, 20.2, 9.7, 12.3,
18.2, 1.9, 11.6, 14.6, 7.9, 11.2, 13.8, 21.2, 23.8, 18, 23.5,
21.4, 11.4, 12, 6.6, 13.5, 10.4, 25.3, 56.8, 10.7, 21.5,
8.5, 30.2, 5.3, 7.5, 15.9, 11.6, 22.4, 25.2, 6.1, 15.1, 9.3,
24.3, 30.8, 8.9, 9.8, 34.1, 13.4, 23.1, 21.1, 4.8, 20.1,
38.5, 16.1, 34.1, 16.1, 17.7, 41.4, 20.4, 21.5, 36.3, 15.9,
8.8, 6.1, 29, 4, 23.1, 36.8, 16.4, 15.5, 28.8, 15.9, NA,
7.1, 6.1, 10, 9.1, 25.2, 19.1, 6.9, 14.7, 23.1, 19.3, 12.3,
7.3, 5.9, 8, 0.5, 9, 4, 10.4, 21.4, 14.6, 8.8, 24.5, 5.3,
9.8, 17.6, 10.2, 10.7, 23, 14.5, 4.6, 33.3, 23.3, 7.2, 3.7,
13.1, 6.7, 20, 7.5, 9.2, 4.5, 2.1, 7.7, 11.7, 7.6, 22.5,
8.8, 5.1, 14.8, 15.1, 18.8, 24.3, 14, 17.2, 16.2, 23.6, 17.4,
16.5, 12.1, 15.3, 11.4, 8.7, 22.6, 10.5, 7.4, 15.1, 13.1,
24.6, 19.3, 19.7, 14.1, 5.9, 19.7, 14.9, 5.9, 17.2, 16.9,
6.2, 11.2, 4.1, 10, 3.7, 3.6, 11.6, 16.9, NA, 8, 17.3, NA,
18.3, 4, 3.1, 26.4, 12.9, 17.9, 10.3, 22.5, NA, NA, 23.4,
15.1, NA, 11.9, 27, 6.2, NA, 21.5, 11.6, 15.8, 8.6, 15.2,
10.1, 20.6, 21.7, 45.3, 8.3, 19.5, 29.2, 21.5, 11.4, 9.5,
31.8, 35.3, 11.2, 15.4, NA, 8.5, 22.6, 14.3, NA, 11.8, 11.4,
4.2, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 35.8, NA, NA,
NA, NA, NA, 19.7, 42.8, 30.6, 12.2, 5.2, 4.9, 20.4, NA, 23.5,
NA, 13.6, 19.4, 6.9, 16.7, 7.2, 14.7, 59.2, 22, 41.4, 18.1,
10.5, 19.8, 17.4, NA, 25.9, NA, 8.3, 25.9, 5.7, 17.1, 25.2,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 10.3, 9.1, 14.8,
13.7, 6.2, 17.9, 13.9, 14.6, 70.4, 23.6, 13.8, 15.2, 9.9,
14, 27.6, 14.3, 23.7, 11, 12.1, 13.5, 21, NA, 7.2, 12.3,
4.4, 6.2, 3.9, 15, 9.6, NA, 9, 10.3, NA, 13.3, 6, 11.3, 17.6,
8.5, 10, NA, 11.8, 10.4, 26.2, NA, 10, 5.7, 16.3, 4.7, 20.3,
7.7, 14.6, 9.4, 6.3, 10, 11.1, 6.7, 42.5, NA, NA, NA, 7.7,
18.6, NA, 16.7, 25.4, 21.8, 26.8, 10.2, 13.8, 11.6, 19.1,
8.3, 3.8, 31.1, NA, 7.1, 11.1, 8.7, 19, 16, 31.8, 11.7, 3.4,
17.6, 12.3, 5.1, 17.5, 6.7, 3.8, 16.6, 6.1), format.spss = "F4.2", display_width = 11L),
glucose = structure(c(90, 95, 79, 85, 95, 97, 86, 74, 88,
95, 94, 88, 86, 94, 86, 95, 97, 88, 88, 88, 83, 103, 79,
67, 88, 79, 90, 79, 97, 94, 85, 83, 88, 97, 81, 95, 92, 94,
99, 79, 83, 92, 81, 92, 79, 94, 83, 79, 81, 92, 86, 95, 92,
95, 92, 85, 94, 81, 86, 85, 99, 92, 85, 72, 86, 81, 79, 86,
97, 88, 92, 97, 83, 103, 97, 95, 85, 77, 77, 83, 99, 90,
77, 77, 83, 92, 88, 83, 88, 86, 88, 97, 101, 99, 88, 101,
94, 86, 85, 83, 86, 88, 92, 94, 94, 90, 160, 94, 83, 95,
97, 88, 88, 95, 90, 92, 113, 104, 85, 101, 91.8, 99, 94,
85, 85, 83, 86, 88, 95, 79, 101, 92, 83, 90, 85, 95, 88,
79, 90, 79, 94, 99, 83, 85, 85, 77, 99, 81, 92, 86.4, 95.4,
82.8, 73.8, 81, 90, 82.8, 79.2, 90, 82.8, 91.8, 90, 84.6,
84.6, 84.6, 77.4, 77.4, 75.6, 88.2, 79.2, 92, 90, 113, 81,
81, 81, 84.6, 88.2, 73.8, 81, 81, 82.8, 79.2, 70.2, 91.8,
97.2, 82.8, 70.2, 91.8, 93.6, 86.4, 93.6, 73.8, 95.4, 81,
97.2, 77.4, 90, 82.8, 86.4, 88.2, 88.2, 73.8, 90, 92, 83,
86, 99, NA, 86, 81, NA, 99, 83, 86, 76, 90, 85, 90, 92, NA,
NA, 79, 79, NA, 86, 81, 88, NA, 90, 86, 92, 85, 92, 83, 92,
90, 92, 95, 94, 88, 90, 86, 88, 101, 95, 92, 81, NA, 92,
90, 81, NA, 90, 81, 88, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, 85, NA, NA, NA, NA, NA, 85, 88, 86, 88, 106, 101, 88,
NA, 79, NA, 85, 99, 92, 79, 88, 88, 95, 81, 86, 77, 81, 92,
97, NA, 86, NA, 88, 94, 81, 86, 85, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, 85, 88, 95, 83, 92, 112, 94, 95, 108,
97, 90, 88, 86, 97, 95, 88, 90, 88, 77, 94, 81, NA, 79, 83,
95, 88, 81, 92, 92, NA, 88, 86, NA, 85, 85, 97, 81, 88, 90,
NA, 77.4, 94, 83, NA, 95, 85, 92, 83, 95, 88, 94, 94, 88,
77, 90, 86, 92, NA, NA, NA, 95, 92, NA, 90, 103, 90, 85,
92, 83, 81, 94, 81, 79, 94, NA, 92, 99, 95, 84, 95, 72, 90,
79, 97.5, 85, 88, 79, 81, 72, 85, 88), format.spss = "F4.2", display_width = 11L),
hdl = structure(c(54, 55, 48, 38, 46, 50, 45, 38, 50, 43,
39, 32, 35, 34, 40, 48, 53, 33, 42, 34, 41, 48, 51, 38, 53,
38, 37, 44, 37, 33, 54, 47, 51, 39, 44, 54, 32, 53, 39, 36,
58, 41, 34, 43, 40, 49, 49, 50, 37, 36, 54, 47, 35, 40, 50,
44, 40, 43, 45, 41, 34, 50, 46, 46, 50, 53, 53, 45, 37, 70,
51, 55, 51, 58, 58, 49, 44, 37, 32, 64, 41, 63, 46, 55, 46,
65, 43, 55, 42, 56, 39, 50, 38, 46, 45, 53, 53, 39, 45, 47,
48, 32, 45, 45, 36, 60, 30, 43, 43, 57, 36, 56, 45, 40, 40,
61, 50, 29, 55, 38, 35, 47, 42, 50, 46, 26, 60, 33, 36, 34,
44, 59, 45, 44, 55, 45, 53, 38, 50, 40, 57, 46, 48, 45, 43,
49, 53, 39, 46, 39, 36, 39, 36, 42, 40, 50, 63, 46, 45, 39,
43, 30, 57, 46, 40, 39, 39, 53, 40, 54, 56, 40, 37, 48, 43,
29, 46, 45, 82, 31, 34, 37, 41, 63, 34, 50, 37, 51, 36, 42,
41, 34, 55, 40, 42, 60, 36, 38, 52, 57, 48, 48, 46, 47, 50,
41, 48, NA, 40, 45, NA, 43, 58, 42, 48, 44, 46, 47, 55, NA,
NA, 38, 52, NA, 53, 31, 51, NA, 32, 51, 41, 38, 57, 36, 50,
41, 60, 65, 39, 52, 36, 36, 49, 43, 34, 44, 41, NA, 50, 52,
37, NA, 58, 45, 34, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
46, NA, NA, NA, NA, NA, 59, 55, 50, 46, 58, 58, 42, NA, 31,
NA, 48, 43, 66, 55, 51, 41, 50, 38, 46, 41, 43, 38, 48, NA,
46, NA, 56, 44, 46, 48, 49, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, 63, 41, 39, 46, 58, 53, 33, 53, 48, 33, 44, 46,
49, 48, 44, 55, 44, 39, 32, 46, 50, NA, 47, 53, 39, 51, 61,
48, 32, NA, 42, 46, NA, 49, 48, 52, 39, 40, 38, NA, 31, 46,
48, NA, 51, 58, 43, 49, 43, 65, 41, 61, 49, 35, 37, 36, 58,
NA, NA, NA, 38, 45, NA, 58, 31, 49, 52, 65, 32, 45, 39, 37,
41, 34, NA, 42, 51, 39, 48, 36, 35, 55, 38, 48, 53, 41, 39,
49, 63, 41, 47), label = "HDL-Cholesterol", format.spss = "F3.2", display_width = 11L),
ldl = structure(c(100, 104, 171, 153, 107, 152, 87, 101,
70, 137, 96, 95, 98, 94, 92, 102, 63, 104, 62, 75, 125, 117,
114, 132, 112, 146, 121, 91, 113, 120, 96, 96, 95, 87, 96,
134, 98, 92, 88, 101, 133, 113, 77, 128, 97, 169, 136, 96,
74, 59, 121, 66, 109, 103, 116, 86, 87, 124, 88, 94, 77,
98, 90, 133, 79, 78, 98, 129, 62, 62, 96, 72, 85, 98, 101,
132, 69, 196, 76, 125, 105, 108, 89, 108, 123, 51, 92, 50,
121, 105, 80, 103, 59, 96, 89, 65, 77, 90, 92, 65, 123, 96,
80, 128, 92, 124, 96, 83, 120, 145, 114, 134, 116, 65, 91,
103, 84, 123, 99, 96, 61, 82, 85, 116, 116, 113, 121, 69,
82, 100, 108, 99, 144, 152, 158, 128, 112, 89, 119, 61, 99,
147, 109, 121, 92, 115, 95, 62, 72, 130, 96, 76, 117, 96,
108, 131, 120, 67, 99, 105, 63, 63, 103, 128, 92, 120, 146,
106, 103, 94, 85, 122, 111, 102, 143, 74, 87, 80, 67, 140,
85, 87, 101, 94, 122, 124, 82, 150, 92, 84, 119, 98, 89,
97, 117, 122, 111, 86, 90, 110, 107, 150, 103, 94, 149, 159,
91, NA, 109, 126, NA, 167, 77, 90, 103, 80, 68, 75, 55, NA,
NA, 74, 113, NA, 102, 116, 84, NA, 66, 85, 114, 111, 101,
95, 92, 86, 96, 90, 92, 77, 91, 108, 86, 118, 85, 127, 99,
NA, 160, 80, 63, NA, 123, 86, 94, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, 106, NA, NA, NA, NA, NA, 70, 85, 70, 96,
102, 117, 101, NA, 146, NA, 94, 122, 122, 94, 110, 121, 39,
72, 48, 109, 110, 60, 95, NA, 83, NA, 79, 87, 113, 103, 55,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 157, 103, 56,
92, 114, 78, 97, 106, 117, 61, 72, 83, 91, 122, 106, 103,
89, 51, 89, 153, 90, NA, 132, 132, 110, 84, 84, 96, 72, NA,
104, 122, NA, 80, 113, 106, 62, 72, 121, NA, 102, 125, 130,
NA, 111, 119, 66, 109, 119, 91, 92, 120, 160, 93, 117, 126,
88, NA, NA, NA, 115, 100, NA, 200, 79, 95, 99, 89, 123, 108,
82, 108, 81, 103, NA, 103, 149, 116, 115, 122, 95, 106, 89,
128, 118, 123, 51, 90, 130, 119, 120), label = "LDL-Cholesterol", format.spss = "F4.2", display_width = 11L)), row.names = c(NA,
-404L), class = c("tbl_df", "tbl", "data.frame"), reshapeLong = list(
varying = list(c("age_1", "age_2"), c("whz_1", "whz_2"),
c("haz_1", "haz_2"), c("waz_1", "waz_2"), c("zbmi_1",
"zbmi_2"), c("wc_1", "wc_2"), c("abc_1", "abc_2"), c("PA_1",
"PA_2"), c("PAextra_1", "PAextra_2"), c("TVweekdays_1",
"TVweekdays_2"), c("TVweekend_1", "TVweekend_2"), c("kidmed_1",
"kidmed_2"), c("totalcholesterol_1", "totalcholesterol_2"
), c("ldl_1", "ldl_2"), c("hdl_1", "hdl_2"), c("triglycerides_1",
"triglycerides_2"), c("glucose_1", "glucose_2"), c("insuline_1",
"insuline_2"), c("hba1c_1", "hba1c_2"), c("homair_1",
"homair_2"), c("fatmass_1", "fatmass_2"), c("energykcal_1",
"energykcal_2"), c("protein_1", "protein_2"), c("proteinpc_1",
"proteinpc_2"), c("carbohydrates_1", "carbohydrates_2"
), c("carbohydratespc_1", "carbohydratespc_2"), c("sugar_1",
"sugar_2"), c("sugarpc_1", "sugarpc_2"), c("starch_1",
"starch_2"), c("fruitportions_1", "fruitportions_2"),
c("vegetablesportions_1", "vegetablesportions_2"), c("vegetalfiber_1",
"vegetalfiber_2"), c("solublefiber_1", "solublefiber_2"
), c("insolublefiber_1", "insolublefiber_2"), c("lipids_1",
"lipids_2"), c("lipidspc_1", "lipidspc_2"), c("sfa_1",
"sfa_2"), c("sfapc_1", "sfapc_2"), c("mufa_1", "mufa_2"
), c("mufapc_1", "mufapc_2"), c("pufa_1", "pufa_2"),
c("pufapc_1", "pufapc_2"), c("cholesterolintake_1", "cholesterolintake_2"
)), v.names = c("age", "whz", "haz", "waz", "zbmi", "wc",
"abc", "PA", "PAextra", "TVweekdays", "TVweekend", "kidmed",
"totalcholesterol", "ldl", "hdl", "triglycerides", "glucose",
"insuline", "hba1c", "homair", "fatmass", "energykcal", "protein",
"proteinpc", "carbohydrates", "carbohydratespc", "sugar",
"sugarpc", "starch", "fruitportions", "vegetablesportions",
"vegetalfiber", "solublefiber", "insolublefiber", "lipids",
" lipidspc", "sfa", "sfapc", "mufa", "mufapc", "pufa", "pufapc",
"cholesterolintake"), idvar = c("id", "group"), timevar = "time"))
You can drop the outliers by changing your remove_outlier function to this:
remove_outliers <- function(dflinear, cols = names(dflinear)) {
for (col in cols) {
dflinear[,col] <- ifelse(outliers(dflinear[[col]]),NA,dflinear[[col]])
}
dflinear
}
But I would think very carefully about whether this is a good approach to outlier detection and removal. This procedure is removing values that look like regular parts of the distribution. With a lot of values you would expect some to be outside of the range Q3+1.5IQR etc.
Eg, this is the qqnorm for the ldl variable. Doesn't look like any problematic values at all really, but your procedure is throwing out the top five and the lowest value:
I have this function that allows me to create multiple graphs on various variables of the dataset.
However in the output on the y-axis it always put the name of the list "varlist" instead of the name of each variable in the list, i.e. insuline, glucose, hdl and ldl.
How could I do that? thank you
# Multiple box plot per group per time
library(ggplot2)
names(dflinear) <- c("id", "group", "sex", "time", "insuline", "glucose", "hdl", "ldl")
# Create a list wherein the function will be applied to
varlist<-c(list(dflinear$insuline, dflinear$glucose, dflinear$hdl, dflinear$ldl))
names(varlist)<-c("insuline", "glucose", "hdl", "ldl")
# Create the function boxplot
A <- function (varlist) {
dflinear %>% group_by('group')%>%
ggplot(mapping = aes_string(x='time', y='varlist', fill='group')) +
geom_boxplot()
}
# Apply it to the whole list and graph the plots
plots<-lapply(varlist, FUN = A)
plots
Reproducible dataset
dflinear<- structure(list(id = structure(c("SA01", "SA02", "SA03", "SA04",
"SA05", "SA06", "SA07", "SA08", "SA09", "SA10", "SA11", "SA12",
"SA13", "SA14", "SA15", "SA16", "SA17", "SA18", "SA19", "SA20",
"SA21", "SA22", "SA23", "SA24", "SA25", "SA26", "SA27", "SA28",
"SA29", "SA30", "SA31", "SA32", "SA33", "SA34", "SA35", "SA36",
"SA37", "SA38", "SA39", "SA40", "SA41", "SA42", "SA43", "SA44",
"SA45", "SA46", "SA47", "SA48", "SA49", "SA50", "SA51", "SA52",
"SA53", "SA54", "SA56", "SA57", "SA58", "SA59", "SA60", "SA61",
"SA62", "SA63", "SA64", "SA65", "SA66", "SA67", "SA68", "SA69",
"SA72", "SA73", "SA74", "SA75", "SA76", "SA77", "SA78", "SA79",
"SA80", "SA81", "SA82", "SA83", "SA84", "SA85", "SA86", "SA87",
"SA88", "SA89", "SA90", "SA92", "SA93", "SA94", "SA95", "SA96",
"SA97", "SA99", "SA100", "SA101", "SA102", "SA103", "SA104",
"SA105", "SA107", "SA108", "SA109", "SA110", "SA111", "SA112",
"SA113", "SA114", "SA115", "SA116", "SA118", "SC01", "SC02",
"SC03", "SC04", "SC05", "SC06", "SC07", "SC08", "SC09", "SC10",
"SC11", "SC12", "SC13", "SC14", "SC15", "SC16", "SC17", "SC18",
"SC19", "SC20", "SC21", "SC22", "SC23", "SC24", "SC25", "SC26",
"SC27", "SC28", "SC29", "SC30", "SC31", "SC32", "SC33", "SC34",
"SC35", "SC36", "SC37", "SC38", "M01", "M02", "M03", "M04", "M05",
"M06", "M07", "M08", "M09", "M10", "M11", "M12", "M13", "M14",
"M15", "M16", "M17", "M18", "M19", "M20", "M21", "M22", "M23",
"M24", "M25", "M26", "M27", "M28", "M29", "M30", "M31", "M32",
"M33", "M34", "M35", "M36", "M37", "M38", "M39", "M40", "M41",
"M42", "M43", "M44", "M45", "M46", "M47", "M48", "M49", "M50",
"M51", "M52", "M53", "SA01", "SA02", "SA03", "SA04", "SA05",
"SA06", "SA07", "SA08", "SA09", "SA10", "SA11", "SA12", "SA13",
"SA14", "SA15", "SA16", "SA17", "SA18", "SA19", "SA20", "SA21",
"SA22", "SA23", "SA24", "SA25", "SA26", "SA27", "SA28", "SA29",
"SA30", "SA31", "SA32", "SA33", "SA34", "SA35", "SA36", "SA37",
"SA38", "SA39", "SA40", "SA41", "SA42", "SA43", "SA44", "SA45",
"SA46", "SA47", "SA48", "SA49", "SA50", "SA51", "SA52", "SA53",
"SA54", "SA56", "SA57", "SA58", "SA59", "SA60", "SA61", "SA62",
"SA63", "SA64", "SA65", "SA66", "SA67", "SA68", "SA69", "SA72",
"SA73", "SA74", "SA75", "SA76", "SA77", "SA78", "SA79", "SA80",
"SA81", "SA82", "SA83", "SA84", "SA85", "SA86", "SA87", "SA88",
"SA89", "SA90", "SA92", "SA93", "SA94", "SA95", "SA96", "SA97",
"SA99", "SA100", "SA101", "SA102", "SA103", "SA104", "SA105",
"SA107", "SA108", "SA109", "SA110", "SA111", "SA112", "SA113",
"SA114", "SA115", "SA116", "SA118", "SC01", "SC02", "SC03", "SC04",
"SC05", "SC06", "SC07", "SC08", "SC09", "SC10", "SC11", "SC12",
"SC13", "SC14", "SC15", "SC16", "SC17", "SC18", "SC19", "SC20",
"SC21", "SC22", "SC23", "SC24", "SC25", "SC26", "SC27", "SC28",
"SC29", "SC30", "SC31", "SC32", "SC33", "SC34", "SC35", "SC36",
"SC37", "SC38", "M01", "M02", "M03", "M04", "M05", "M06", "M07",
"M08", "M09", "M10", "M11", "M12", "M13", "M14", "M15", "M16",
"M17", "M18", "M19", "M20", "M21", "M22", "M23", "M24", "M25",
"M26", "M27", "M28", "M29", "M30", "M31", "M32", "M33", "M34",
"M35", "M36", "M37", "M38", "M39", "M40", "M41", "M42", "M43",
"M44", "M45", "M46", "M47", "M48", "M49", "M50", "M51", "M52",
"M53"), label = "Code of PrevenGo", format.spss = "A5", display_width = 12L),
group = structure(c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L), .Label = c("Metab", "SA", "SC"), class = "factor"),
sex = structure(c(2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 2L,
2L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L,
1L, 2L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 2L,
1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L,
2L, 2L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 2L,
1L, 2L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L,
1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 1L,
2L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 1L,
2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 1L,
1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 2L,
2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 2L,
1L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L,
1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 1L,
1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L,
1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 1L,
1L, 2L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L,
1L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 1L,
1L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 1L,
1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L,
2L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 2L,
2L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L,
2L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L,
1L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 1L,
1L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L,
1L, 2L, 2L, 2L), .Label = c("F", "M"), class = "factor"),
time = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L), insuline = structure(c(9, 4.1, 3.3, 9.4, 22.9, 16.2,
8.7, 16.7, 21.2, 21, 12.8, 7.3, 38.4, 20.2, 19.6, 6.4, 18.9,
12.1, 8.2, 17, 15.6, 12.5, 19.1, 13.7, 8, 20.1, 19.8, 6.8,
15.4, 14.7, 11.9, 8.8, 7.9, 51.2, 10.8, 8.1, 28.6, 8.6, 27.9,
13.3, 9, 16.3, 13.3, 5.8, 27.3, 4.2, 8.2, 9.9, 20.1, 11.7,
8.7, 18.1, 10.9, 27.4, 14.6, 29.1, 10.2, 20.2, 9.7, 12.3,
18.2, 1.9, 11.6, 14.6, 7.9, 11.2, 13.8, 21.2, 23.8, 18, 23.5,
21.4, 11.4, 12, 6.6, 13.5, 10.4, 25.3, 56.8, 10.7, 21.5,
8.5, 30.2, 5.3, 7.5, 15.9, 11.6, 22.4, 25.2, 6.1, 15.1, 9.3,
24.3, 30.8, 8.9, 9.8, 34.1, 13.4, 23.1, 21.1, 4.8, 20.1,
38.5, 16.1, 34.1, 16.1, 17.7, 41.4, 20.4, 21.5, 36.3, 15.9,
8.8, 6.1, 29, 4, 23.1, 36.8, 16.4, 15.5, 28.8, 15.9, NA,
7.1, 6.1, 10, 9.1, 25.2, 19.1, 6.9, 14.7, 23.1, 19.3, 12.3,
7.3, 5.9, 8, 0.5, 9, 4, 10.4, 21.4, 14.6, 8.8, 24.5, 5.3,
9.8, 17.6, 10.2, 10.7, 23, 14.5, 4.6, 33.3, 23.3, 7.2, 3.7,
13.1, 6.7, 20, 7.5, 9.2, 4.5, 2.1, 7.7, 11.7, 7.6, 22.5,
8.8, 5.1, 14.8, 15.1, 18.8, 24.3, 14, 17.2, 16.2, 23.6, 17.4,
16.5, 12.1, 15.3, 11.4, 8.7, 22.6, 10.5, 7.4, 15.1, 13.1,
24.6, 19.3, 19.7, 14.1, 5.9, 19.7, 14.9, 5.9, 17.2, 16.9,
6.2, 11.2, 4.1, 10, 3.7, 3.6, 11.6, 16.9, NA, 8, 17.3, NA,
18.3, 4, 3.1, 26.4, 12.9, 17.9, 10.3, 22.5, NA, NA, 23.4,
15.1, NA, 11.9, 27, 6.2, NA, 21.5, 11.6, 15.8, 8.6, 15.2,
10.1, 20.6, 21.7, 45.3, 8.3, 19.5, 29.2, 21.5, 11.4, 9.5,
31.8, 35.3, 11.2, 15.4, NA, 8.5, 22.6, 14.3, NA, 11.8, 11.4,
4.2, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 35.8, NA, NA,
NA, NA, NA, 19.7, 42.8, 30.6, 12.2, 5.2, 4.9, 20.4, NA, 23.5,
NA, 13.6, 19.4, 6.9, 16.7, 7.2, 14.7, 59.2, 22, 41.4, 18.1,
10.5, 19.8, 17.4, NA, 25.9, NA, 8.3, 25.9, 5.7, 17.1, 25.2,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 10.3, 9.1, 14.8,
13.7, 6.2, 17.9, 13.9, 14.6, 70.4, 23.6, 13.8, 15.2, 9.9,
14, 27.6, 14.3, 23.7, 11, 12.1, 13.5, 21, NA, 7.2, 12.3,
4.4, 6.2, 3.9, 15, 9.6, NA, 9, 10.3, NA, 13.3, 6, 11.3, 17.6,
8.5, 10, NA, 11.8, 10.4, 26.2, NA, 10, 5.7, 16.3, 4.7, 20.3,
7.7, 14.6, 9.4, 6.3, 10, 11.1, 6.7, 42.5, NA, NA, NA, 7.7,
18.6, NA, 16.7, 25.4, 21.8, 26.8, 10.2, 13.8, 11.6, 19.1,
8.3, 3.8, 31.1, NA, 7.1, 11.1, 8.7, 19, 16, 31.8, 11.7, 3.4,
17.6, 12.3, 5.1, 17.5, 6.7, 3.8, 16.6, 6.1), format.spss = "F4.2", display_width = 11L),
glucose = structure(c(90, 95, 79, 85, 95, 97, 86, 74, 88,
95, 94, 88, 86, 94, 86, 95, 97, 88, 88, 88, 83, 103, 79,
67, 88, 79, 90, 79, 97, 94, 85, 83, 88, 97, 81, 95, 92, 94,
99, 79, 83, 92, 81, 92, 79, 94, 83, 79, 81, 92, 86, 95, 92,
95, 92, 85, 94, 81, 86, 85, 99, 92, 85, 72, 86, 81, 79, 86,
97, 88, 92, 97, 83, 103, 97, 95, 85, 77, 77, 83, 99, 90,
77, 77, 83, 92, 88, 83, 88, 86, 88, 97, 101, 99, 88, 101,
94, 86, 85, 83, 86, 88, 92, 94, 94, 90, 160, 94, 83, 95,
97, 88, 88, 95, 90, 92, 113, 104, 85, 101, 91.8, 99, 94,
85, 85, 83, 86, 88, 95, 79, 101, 92, 83, 90, 85, 95, 88,
79, 90, 79, 94, 99, 83, 85, 85, 77, 99, 81, 92, 86.4, 95.4,
82.8, 73.8, 81, 90, 82.8, 79.2, 90, 82.8, 91.8, 90, 84.6,
84.6, 84.6, 77.4, 77.4, 75.6, 88.2, 79.2, 92, 90, 113, 81,
81, 81, 84.6, 88.2, 73.8, 81, 81, 82.8, 79.2, 70.2, 91.8,
97.2, 82.8, 70.2, 91.8, 93.6, 86.4, 93.6, 73.8, 95.4, 81,
97.2, 77.4, 90, 82.8, 86.4, 88.2, 88.2, 73.8, 90, 92, 83,
86, 99, NA, 86, 81, NA, 99, 83, 86, 76, 90, 85, 90, 92, NA,
NA, 79, 79, NA, 86, 81, 88, NA, 90, 86, 92, 85, 92, 83, 92,
90, 92, 95, 94, 88, 90, 86, 88, 101, 95, 92, 81, NA, 92,
90, 81, NA, 90, 81, 88, NA, NA, NA, NA, NA, NA, NA, NA, NA,
NA, 85, NA, NA, NA, NA, NA, 85, 88, 86, 88, 106, 101, 88,
NA, 79, NA, 85, 99, 92, 79, 88, 88, 95, 81, 86, 77, 81, 92,
97, NA, 86, NA, 88, 94, 81, 86, 85, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, NA, 85, 88, 95, 83, 92, 112, 94, 95, 108,
97, 90, 88, 86, 97, 95, 88, 90, 88, 77, 94, 81, NA, 79, 83,
95, 88, 81, 92, 92, NA, 88, 86, NA, 85, 85, 97, 81, 88, 90,
NA, 77.4, 94, 83, NA, 95, 85, 92, 83, 95, 88, 94, 94, 88,
77, 90, 86, 92, NA, NA, NA, 95, 92, NA, 90, 103, 90, 85,
92, 83, 81, 94, 81, 79, 94, NA, 92, 99, 95, 84, 95, 72, 90,
79, 97.5, 85, 88, 79, 81, 72, 85, 88), format.spss = "F4.2", display_width = 11L),
hdl = structure(c(54, 55, 48, 38, 46, 50, 45, 38, 50, 43,
39, 32, 35, 34, 40, 48, 53, 33, 42, 34, 41, 48, 51, 38, 53,
38, 37, 44, 37, 33, 54, 47, 51, 39, 44, 54, 32, 53, 39, 36,
58, 41, 34, 43, 40, 49, 49, 50, 37, 36, 54, 47, 35, 40, 50,
44, 40, 43, 45, 41, 34, 50, 46, 46, 50, 53, 53, 45, 37, 70,
51, 55, 51, 58, 58, 49, 44, 37, 32, 64, 41, 63, 46, 55, 46,
65, 43, 55, 42, 56, 39, 50, 38, 46, 45, 53, 53, 39, 45, 47,
48, 32, 45, 45, 36, 60, 30, 43, 43, 57, 36, 56, 45, 40, 40,
61, 50, 29, 55, 38, 35, 47, 42, 50, 46, 26, 60, 33, 36, 34,
44, 59, 45, 44, 55, 45, 53, 38, 50, 40, 57, 46, 48, 45, 43,
49, 53, 39, 46, 39, 36, 39, 36, 42, 40, 50, 63, 46, 45, 39,
43, 30, 57, 46, 40, 39, 39, 53, 40, 54, 56, 40, 37, 48, 43,
29, 46, 45, 82, 31, 34, 37, 41, 63, 34, 50, 37, 51, 36, 42,
41, 34, 55, 40, 42, 60, 36, 38, 52, 57, 48, 48, 46, 47, 50,
41, 48, NA, 40, 45, NA, 43, 58, 42, 48, 44, 46, 47, 55, NA,
NA, 38, 52, NA, 53, 31, 51, NA, 32, 51, 41, 38, 57, 36, 50,
41, 60, 65, 39, 52, 36, 36, 49, 43, 34, 44, 41, NA, 50, 52,
37, NA, 58, 45, 34, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA,
46, NA, NA, NA, NA, NA, 59, 55, 50, 46, 58, 58, 42, NA, 31,
NA, 48, 43, 66, 55, 51, 41, 50, 38, 46, 41, 43, 38, 48, NA,
46, NA, 56, 44, 46, 48, 49, NA, NA, NA, NA, NA, NA, NA, NA,
NA, NA, NA, 63, 41, 39, 46, 58, 53, 33, 53, 48, 33, 44, 46,
49, 48, 44, 55, 44, 39, 32, 46, 50, NA, 47, 53, 39, 51, 61,
48, 32, NA, 42, 46, NA, 49, 48, 52, 39, 40, 38, NA, 31, 46,
48, NA, 51, 58, 43, 49, 43, 65, 41, 61, 49, 35, 37, 36, 58,
NA, NA, NA, 38, 45, NA, 58, 31, 49, 52, 65, 32, 45, 39, 37,
41, 34, NA, 42, 51, 39, 48, 36, 35, 55, 38, 48, 53, 41, 39,
49, 63, 41, 47), label = "HDL-Cholesterol", format.spss = "F3.2", display_width = 11L),
ldl = structure(c(100, 104, 171, 153, 107, 152, 87, 101,
70, 137, 96, 95, 98, 94, 92, 102, 63, 104, 62, 75, 125, 117,
114, 132, 112, 146, 121, 91, 113, 120, 96, 96, 95, 87, 96,
134, 98, 92, 88, 101, 133, 113, 77, 128, 97, 169, 136, 96,
74, 59, 121, 66, 109, 103, 116, 86, 87, 124, 88, 94, 77,
98, 90, 133, 79, 78, 98, 129, 62, 62, 96, 72, 85, 98, 101,
132, 69, 196, 76, 125, 105, 108, 89, 108, 123, 51, 92, 50,
121, 105, 80, 103, 59, 96, 89, 65, 77, 90, 92, 65, 123, 96,
80, 128, 92, 124, 96, 83, 120, 145, 114, 134, 116, 65, 91,
103, 84, 123, 99, 96, 61, 82, 85, 116, 116, 113, 121, 69,
82, 100, 108, 99, 144, 152, 158, 128, 112, 89, 119, 61, 99,
147, 109, 121, 92, 115, 95, 62, 72, 130, 96, 76, 117, 96,
108, 131, 120, 67, 99, 105, 63, 63, 103, 128, 92, 120, 146,
106, 103, 94, 85, 122, 111, 102, 143, 74, 87, 80, 67, 140,
85, 87, 101, 94, 122, 124, 82, 150, 92, 84, 119, 98, 89,
97, 117, 122, 111, 86, 90, 110, 107, 150, 103, 94, 149, 159,
91, NA, 109, 126, NA, 167, 77, 90, 103, 80, 68, 75, 55, NA,
NA, 74, 113, NA, 102, 116, 84, NA, 66, 85, 114, 111, 101,
95, 92, 86, 96, 90, 92, 77, 91, 108, 86, 118, 85, 127, 99,
NA, 160, 80, 63, NA, 123, 86, 94, NA, NA, NA, NA, NA, NA,
NA, NA, NA, NA, 106, NA, NA, NA, NA, NA, 70, 85, 70, 96,
102, 117, 101, NA, 146, NA, 94, 122, 122, 94, 110, 121, 39,
72, 48, 109, 110, 60, 95, NA, 83, NA, 79, 87, 113, 103, 55,
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 157, 103, 56,
92, 114, 78, 97, 106, 117, 61, 72, 83, 91, 122, 106, 103,
89, 51, 89, 153, 90, NA, 132, 132, 110, 84, 84, 96, 72, NA,
104, 122, NA, 80, 113, 106, 62, 72, 121, NA, 102, 125, 130,
NA, 111, 119, 66, 109, 119, 91, 92, 120, 160, 93, 117, 126,
88, NA, NA, NA, 115, 100, NA, 200, 79, 95, 99, 89, 123, 108,
82, 108, 81, 103, NA, 103, 149, 116, 115, 122, 95, 106, 89,
128, 118, 123, 51, 90, 130, 119, 120), label = "LDL-Cholesterol", format.spss = "F4.2", display_width = 11L)), row.names = c(NA,
-404L), class = c("tbl_df", "tbl", "data.frame"), reshapeLong = list(
varying = list(c("age_1", "age_2"), c("whz_1", "whz_2"),
c("haz_1", "haz_2"), c("waz_1", "waz_2"), c("zbmi_1",
"zbmi_2"), c("wc_1", "wc_2"), c("abc_1", "abc_2"), c("PA_1",
"PA_2"), c("PAextra_1", "PAextra_2"), c("TVweekdays_1",
"TVweekdays_2"), c("TVweekend_1", "TVweekend_2"), c("kidmed_1",
"kidmed_2"), c("totalcholesterol_1", "totalcholesterol_2"
), c("ldl_1", "ldl_2"), c("hdl_1", "hdl_2"), c("triglycerides_1",
"triglycerides_2"), c("glucose_1", "glucose_2"), c("insuline_1",
"insuline_2"), c("hba1c_1", "hba1c_2"), c("homair_1",
"homair_2"), c("fatmass_1", "fatmass_2"), c("energykcal_1",
"energykcal_2"), c("protein_1", "protein_2"), c("proteinpc_1",
"proteinpc_2"), c("carbohydrates_1", "carbohydrates_2"
), c("carbohydratespc_1", "carbohydratespc_2"), c("sugar_1",
"sugar_2"), c("sugarpc_1", "sugarpc_2"), c("starch_1",
"starch_2"), c("fruitportions_1", "fruitportions_2"),
c("vegetablesportions_1", "vegetablesportions_2"), c("vegetalfiber_1",
"vegetalfiber_2"), c("solublefiber_1", "solublefiber_2"
), c("insolublefiber_1", "insolublefiber_2"), c("lipids_1",
"lipids_2"), c("lipidspc_1", "lipidspc_2"), c("sfa_1",
"sfa_2"), c("sfapc_1", "sfapc_2"), c("mufa_1", "mufa_2"
), c("mufapc_1", "mufapc_2"), c("pufa_1", "pufa_2"),
c("pufapc_1", "pufapc_2"), c("cholesterolintake_1", "cholesterolintake_2"
)), v.names = c("age", "whz", "haz", "waz", "zbmi", "wc",
"abc", "PA", "PAextra", "TVweekdays", "TVweekend", "kidmed",
"totalcholesterol", "ldl", "hdl", "triglycerides", "glucose",
"insuline", "hba1c", "homair", "fatmass", "energykcal", "protein",
"proteinpc", "carbohydrates", "carbohydratespc", "sugar",
"sugarpc", "starch", "fruitportions", "vegetablesportions",
"vegetalfiber", "solublefiber", "insolublefiber", "lipids",
" lipidspc", "sfa", "sfapc", "mufa", "mufapc", "pufa", "pufapc",
"cholesterolintake"), idvar = c("id", "group"), timevar = "time"))
Instead of making your varlist a list of vectors you could simply pass a vector with names of the colums you want to plot. Then use aes_string(..., y = varlist) inside your function and you will automatically get the name of the variable as the y axis title:
# Multiple box plot per group per time
library(ggplot2)
library(dplyr)
# Create a list wherein the function will be applied to
varlist <- c("insuline", "glucose", "hdl", "ldl")
names(varlist) <- varlist
# Create the function boxplot
A <- function(varlist) {
dflinear %>%
group_by("group") %>%
ggplot(mapping = aes_string(x = "time", y = varlist, fill = "group")) +
geom_boxplot()
}
# Apply it to the whole list and graph the plots
plots <- lapply(varlist, FUN = A)
plots[[1]]
I have repeated measurements data on 66 patients with either endogenous or exogenous depression (endo) and depression scores measured weekly for 0-5 weeks (hdrs, so six measurements per patients including baseline). The data is in a long format:
mydata <- structure(list(id = c(101, 101, 101, 101, 101, 101, 103, 103,
103, 103, 103, 103, 104, 104, 104, 104, 104, 104, 105, 105, 105,
105, 105, 105, 106, 106, 106, 106, 106, 106, 107, 107, 107, 107,
107, 107, 108, 108, 108, 108, 108, 108, 113, 113, 113, 113, 113,
113, 114, 114, 114, 114, 114, 114, 115, 115, 115, 115, 115, 115,
117, 117, 117, 117, 117, 117, 118, 118, 118, 118, 118, 118, 120,
120, 120, 120, 120, 120, 121, 121, 121, 121, 121, 121, 123, 123,
123, 123, 123, 123, 302, 302, 302, 302, 302, 302, 303, 303, 303,
303, 303, 303, 304, 304, 304, 304, 304, 304, 305, 305, 305, 305,
305, 305, 308, 308, 308, 308, 308, 308, 309, 309, 309, 309, 309,
309, 310, 310, 310, 310, 310, 310, 311, 311, 311, 311, 311, 311,
312, 312, 312, 312, 312, 312, 313, 313, 313, 313, 313, 313, 315,
315, 315, 315, 315, 315, 316, 316, 316, 316, 316, 316, 318, 318,
318, 318, 318, 318, 319, 319, 319, 319, 319, 319, 322, 322, 322,
322, 322, 322, 327, 327, 327, 327, 327, 327, 328, 328, 328, 328,
328, 328, 331, 331, 331, 331, 331, 331, 333, 333, 333, 333, 333,
333, 334, 334, 334, 334, 334, 334, 335, 335, 335, 335, 335, 335,
337, 337, 337, 337, 337, 337, 338, 338, 338, 338, 338, 338, 339,
339, 339, 339, 339, 339, 344, 344, 344, 344, 344, 344, 345, 345,
345, 345, 345, 345, 346, 346, 346, 346, 346, 346, 347, 347, 347,
347, 347, 347, 348, 348, 348, 348, 348, 348, 349, 349, 349, 349,
349, 349, 350, 350, 350, 350, 350, 350, 351, 351, 351, 351, 351,
351, 352, 352, 352, 352, 352, 352, 353, 353, 353, 353, 353, 353,
354, 354, 354, 354, 354, 354, 355, 355, 355, 355, 355, 355, 357,
357, 357, 357, 357, 357, 360, 360, 360, 360, 360, 360, 361, 361,
361, 361, 361, 361, 501, 501, 501, 501, 501, 501, 502, 502, 502,
502, 502, 502, 504, 504, 504, 504, 504, 504, 505, 505, 505, 505,
505, 505, 507, 507, 507, 507, 507, 507, 603, 603, 603, 603, 603,
603, 604, 604, 604, 604, 604, 604, 606, 606, 606, 606, 606, 606,
607, 607, 607, 607, 607, 607, 608, 608, 608, 608, 608, 608, 609,
609, 609, 609, 609, 609, 610, 610, 610, 610, 610, 610), week = structure(c(0,
1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3,
4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0,
1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3,
4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0,
1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3,
4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0,
1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3,
4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0,
1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3,
4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0,
1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3,
4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0,
1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3,
4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0,
1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3,
4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0,
1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3,
4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0,
1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5, 0, 1, 2, 3, 4, 5), format.spss = "F1.0", display_width = 6L),
week_fact = structure(c(1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L,
4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L,
1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L,
4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L,
1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L,
4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L,
1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L,
4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L,
1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L,
4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L,
1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L,
4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L,
1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L,
4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L,
1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L,
4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L,
1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L,
4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L,
1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L,
4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L,
1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L,
4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L,
1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L,
4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L,
1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L,
4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L,
1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L), .Label = c("Week 0",
"Week 1", "Week 2", "Week 3", "Week 4", "Week 5"), class = "factor"),
endo = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L,
1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L,
1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("Exogenous",
"Endogenous"), class = "factor"), hdrs = c(26, 22, 18, 7,
4, 3, 33, 24, 15, 24, 15, 13, 29, 22, 18, 13, 19, 0, 22,
12, 16, 16, 13, 9, 21, 25, 23, 18, 20, NA, 21, 21, 16, 19,
NA, 6, 21, 22, 11, 9, 9, 7, 21, 23, 19, 23, 23, NA, NA, 17,
11, 13, 7, 7, NA, 16, 16, 16, 16, 11, 19, 16, 13, 12, 7,
6, NA, 26, 18, 18, 14, 11, 20, 19, 17, 18, 16, 17, 20, 22,
19, 19, 12, 14, 15, 15, 15, 13, 5, 5, 18, 22, 16, 8, 9, 12,
21, 21, 13, 14, 10, 5, 21, 27, 29, NA, 12, 24, 19, 17, 15,
11, 5, 1, 22, 21, 18, 17, 12, 11, 22, 22, 16, 19, 20, 11,
24, 19, 11, 7, 6, NA, 20, 16, 21, 17, NA, 15, 17, NA, 18,
17, 17, 6, 21, 19, 10, 11, 11, 8, 27, 21, 17, 13, 5, NA,
32, 26, 23, 26, 23, 24, 17, 18, 19, 21, 17, 11, 24, 18, 10,
14, 13, 12, 28, 21, 25, 32, 34, NA, 17, 18, 15, 8, 19, 17,
22, 24, 28, 26, 28, 29, 19, 21, 18, 16, 14, 10, 23, 20, 21,
20, 24, 14, 31, 25, NA, 7, 8, 11, 21, 21, 18, 15, 12, 10,
27, 22, 23, 21, 12, 13, 22, 20, 22, 23, 19, 18, 27, NA, 14,
12, 11, 12, NA, 21, 12, 13, 13, 18, 29, 27, 27, 22, 22, 23,
25, 24, 19, 23, 14, 21, 18, 15, 14, 10, 8, NA, 24, 21, 12,
13, 12, 5, 17, 19, 15, 12, 9, 13, 22, 25, 12, 16, 10, 16,
30, 27, 23, 20, 12, 11, 21, 19, 18, 15, 18, 19, 27, 21, 24,
22, 16, 11, 28, 27, 27, 26, 23, NA, 22, 26, 20, 13, 10, 7,
27, 22, 24, 25, 19, 19, 21, 28, 27, 29, 28, 33, 30, 22, 11,
8, 7, 19, 29, 30, 26, 22, 19, 24, 21, 22, 13, 11, 2, 1, 19,
17, 15, 16, 12, 12, 21, 11, 18, 0, 0, 4, 27, 26, 26, 25,
24, 19, 28, 22, 18, 20, 11, 13, 27, 27, 13, 5, 7, NA, 19,
33, 12, 12, 3, 1, 30, 39, 30, 27, 20, 4, 24, 19, 14, 12,
3, 4, NA, 25, 22, 14, 15, 2, 34, NA, 33, 23, NA, 11)), row.names = c(NA,
-396L), class = "data.frame")
And looks like this:
head(reisby_long)
id week week_fact endo hdrs
1 101 0 Week 0 Exogenous 26
2 101 1 Week 1 Exogenous 22
3 101 2 Week 2 Exogenous 18
4 101 3 Week 3 Exogenous 7
5 101 4 Week 4 Exogenous 4
6 101 5 Week 5 Exogenous 3
My question is if I can obtain a variance-covariance matrix from this dataset without converting it to a wide format first. I ask because I have another dataset for which converting to a wide format is going to take me a long time (because I'm not very experienced in doing so) and the only reason for doing it would be to get a variance-covariance matrix.
Thanks!
Not sure if you can use that directly, but you wouldn't have to manually change the data to a wide format. You can use acast from the reshape2 library.
library(reshape2)
mat <- reshape2::acast(data = mydata, formula = id ~ week)
You can change the formula to obtain whichever rows and columns data is needed.
I have two data.frame that I'm trying to merge using three key variables. This really should be a left outer join resulting in 1633 observations.
I've run it using merge() and data.table() and haven't had success with either. I've been running this as a full outer join, just to see where issues are occurring.
The first data.frame has the 1633 observations with 12 variables, and the second has 46800 observations with 7 variables. I am merging on "Date", "State", and "County". The issue that keeps coming up is for date 2015-12-01 for Anchorage, Alaska. I have two IDs from the first data.frame that won't merge with the data from the second data.frame.
I've tried all forms of the merge(file1, file2, by=c("Date", "State", "County"), all=TRUE), alternating the "all" argument. I've kept it this way because it's the easiest way to see what's not matching up.
Any ideas why this isn't working?
The below is the code, looking at just the Alaska data:
dput(file1)
structure(list(Date = structure(c(16770, 16738, 17100, 16738,
16770, 17100), class = "Date"), ID = c(93L, 228L, 1109L, 1218L,
1267L, 1736L), State = structure(c(2L, 2L, 2L, 2L, 2L, 2L), .Label = c("Alabama",
"Alaska", "Arizona", "California", "Colorado", "Connecticut",
"District Of Columbia", "Florida", "Georgia", "Hawaii", "Illinois",
"Kansas", "Kentucky", "Louisiana", "Maryland", "Massachusetts",
"Mississippi", "Missouri", "Nebraska", "Nevada", "New Mexico",
"New York", "North Carolina", "North Dakota", "Ohio", "Oklahoma",
"Pennsylvania", "Rhode Island", "South Carolina", "Tennessee",
"Texas", "Utah", "Virginia", "Washington"), class = "factor"),
County = structure(c(1L, 1L, 1L, 1L, 1L, 1L), .Label = c("Anchorage",
"Anne Arundel", "Arapahoe", "Arlington", "Bay", "Beaufort",
"Bell", "Bernalillo", "Bexar", "Bossier", "Brevard", "Camden",
"Charles", "Chatham", "Chattahoochee", "Chesapeake", "Christian",
"Clark", "Comanche", "Craven", "Cumberland", "Davis", "District Of Columbia",
"Duval", "El Paso", "Escambia", "Fairfax", "Frederick", "Geary",
"Greene", "Hampton City", "Hardin", "Harrison", "Hillsborough",
"Hinds", "Honolulu", "Houston", "Island", "Jefferson", "Kings",
"Kitsap", "Kleberg", "Lake", "Lakewood", "Liberty", "Madison",
"Mary's", "Middlesex", "Monroe", "Monterey", "Montgomery",
"New London", "Newport", "Newport News", "Norfolk City",
"Nueces", "Okaloosa", "Onslow", "Orange", "Otero", "Peoria",
"Pierce", "Pima", "Portsmouth", "Prince George's", "Prince William",
"Pulaski", "Richmond", "San Bernadino", "San Diego", "Santa Barbra",
"Santa Rosa", "Sarpy", "Shelby", "Snohomish", "Solano", "Stafford",
"Tarrant", "Tom Green", "Val Verde", "Ventura", "Vernon",
"Virginia Beach City", "Ward", "Yuba", "Yuma"), class = "factor")), row.names = c(NA,
-6L), class = c("grouped_df", "tbl_df", "tbl", "data.frame"), groups = structure(list(
ID = c(93L, 228L, 1109L, 1218L, 1267L, 1736L), .rows = list(
1L, 2L, 3L, 4L, 5L, 6L)), row.names = c(NA, -6L), class = c("tbl_df",
"tbl", "data.frame"), .drop = TRUE))
dput(file2)
structure(list(Date = structure(c(16436, 16437, 16438, 16439,
16440, 16441, 16442, 16443, 16444, 16445, 16446, 16447, 16448,
16449, 16450, 16451, 16452, 16453, 16454, 16455, 16456, 16457,
16458, 16459, 16460, 16461, 16462, 16463, 16464, 16465, 16466,
16467, 16468, 16469, 16470, 16471, 16472, 16473, 16474, 16475,
16476, 16477, 16478, 16479, 16480, 16481, 16482, 16483, 16484,
16485, 16486, 16487, 16488, 16489, 16490, 16491, 16492, 16493,
16494, 16495, 16496, 16497, 16498, 16499, 16500, 16501, 16502,
16503, 16504, 16505, 16506, 16507, 16508, 16509, 16510, 16511,
16512, 16513, 16514, 16515, 16516, 16517, 16518, 16519, 16520,
16521, 16522, 16523, 16524, 16525, 16526, 16527, 16528, 16529,
16530, 16531, 16532, 16533, 16534, 16535, 16536, 16537, 16538,
16539, 16540, 16541, 16542, 16543, 16544, 16545, 16546, 16547,
16548, 16549, 16550, 16551, 16552, 16553, 16554, 16555, 16556,
16557, 16558, 16559, 16560, 16561, 16562, 16563, 16564, 16565,
16566, 16567, 16568, 16569, 16570, 16571, 16572, 16573, 16574,
16575, 16576, 16577, 16578, 16579, 16580, 16581, 16582, 16583,
16584, 16587, 16588, 16589, 16590, 16591, 16592, 16593, 16594,
16595, 16596, 16597, 16598, 16599, 16600, 16601, 16602, 16603,
16604, 16605, 16606, 16607, 16608, 16609, 16610, 16611, 16612,
16613, 16614, 16615, 16616, 16617, 16618, 16619, 16620, 16621,
16622, 16623, 16624, 16625, 16626, 16627, 16628, 16629, 16630,
16631, 16632, 16633, 16634, 16635, 16636, 16637, 16638, 16639,
16640, 16641, 16642, 16643, 16644, 16645, 16646, 16647, 16648,
16649, 16650, 16651, 16652, 16653, 16654, 16655, 16656, 16657,
16658, 16659, 16660, 16661, 16662, 16663, 16664, 16665, 16666,
16667, 16668, 16669, 16670, 16671, 16672, 16673, 16674, 16675,
16676, 16677, 16678, 16679, 16680, 16681, 16682, 16683, 16684,
16685, 16686, 16687, 16688, 16689, 16690, 16691, 16692, 16693,
16694, 16695, 16696, 16697, 16698, 16699, 16700, 16701, 16702,
16703, 16704, 16705, 16706, 16707, 16708, 16709, 16710, 16711,
16712, 16713, 16714, 16715, 16716, 16717, 16718, 16719, 16720,
16721, 16722, 16723, 16724, 16725, 16726, 16727, 16728, 16729,
16730, 16731, 16732, 16733, 16734, 16735, 16736, 16737, 16738,
16739, 16740, 16741, 16742, 16743, 16744, 16745, 16746, 16747,
16748, 16749, 16750, 16751, 16752, 16753, 16754, 16755, 16756,
16757, 16758, 16759, 16760, 16761, 16762, 16763, 16764, 16765,
16766, 16767, 16768, 16769, 16770, 16771, 16772, 16773, 16774,
16775, 16776, 16777, 16778, 16779, 16780, 16781, 16782, 16783,
16784, 16785, 16786, 16787, 16788, 16789, 16790, 16791, 16792,
16793, 16794, 16795, 16796, 16797, 16798, 16799), class = "Date"),
State = structure(c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("Alabama", "Alaska",
"Arizona", "California", "Colorado", "Connecticut", "District Of Columbia",
"Florida", "Georgia", "Hawaii", "Illinois", "Kentucky", "Maryland",
"Mississippi", "Missouri", "Nebraska", "Nevada", "New Mexico",
"New York", "North Carolina", "North Dakota", "Ohio", "Oklahoma",
"Pennsylvania", "Tennessee", "Texas", "Utah", "Virginia",
"Washington", "Louisiana"), class = "factor"), County = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L), .Label = c("Anchorage ", "Anne Arundel", "Arapahoe",
"Arlington", "Bell", "Bernalillo", "Bexar", "Brevard", "Charles",
"Chatham", "Christian", "Clark", "Comanche", "Cumberland",
"Davis", "District of Columbia", "Duval", "El Paso", "Escambia",
"Fairfax", "Frederick", "Greene", "Hampton City", "Hardin",
"Harrison", "Hillsborough", "Hinds", "Honolulu", "Houston",
"Kings", "Kitsap", "Madison", "Monterey", "Montgomery", "New London",
"Norfolk City", "Nueces", "Orange", "Peoria", "Pierce", "Pima",
"Richmond", "San Bernardino", "San Diego", "Santa Barbara",
"Sarpy", "Shelby", "Snohomish", "Solano", "Tarrant", "Ventura",
"Virginia Beach City", "Ward", "Yuma", "Bossier", "Okaloosa",
"Prince George's"), class = "factor"), AQI_25 = c(27, 40.5,
54, 70.5, 65.5, 64, 47.5, 29, 40, 60.5, 60, 36.5, 26, 21.5,
26, 28, 32, 31, 30, 30, 47, 26.5, 6.5, 6, 48.5, 31.5, 27,
45.5, 45.5, 38, 51, 47, NA, NA, 70, 41.5, 12, 58.5, 38.5,
29, 26, 36, 22, 34.5, 38.5, 27, 7.5, 11.5, 29, 46.5, 37,
14.5, 27.5, 15.5, 26, 26.5, 46, 45, 40, 38.5, 31, 21.5, 26.5,
21.5, 22.5, 11.5, 9.5, 16.5, 15, 27.5, 23.5, 17, 22, 15,
13, 22.5, 33.5, 28.5, 31.5, 40.5, 28, 35.5, 39, 25.5, 32.5,
28.5, 29.5, 26.5, 24.5, 19.5, 16, 18.5, 17, 20.5, 15.5, 8.5,
4, 6, 7, 16, 21.5, 16.5, 7.5, 16, 13.5, 10.5, 9, 5.5, 5,
7, 10, 14.5, 24.5, 24.5, 23.5, 20, 15, 15.5, 9, 13.5, 17,
16, 15, 14, 17.5, 19.5, 14, 12.5, 12, 9, 12.5, 15.5, 18,
23, 22, 14, 16.5, 18, 11.5, 20.5, 17.5, 23, 18, 21.5, 14,
16, 18, 31.5, NA, NA, 29.5, 19.5, 21.5, 19.5, 23, 24, 28,
20, 20.5, 24, 31, 30, 39.5, 61.5, 72, 59.5, 60.5, 57, 51.5,
47.5, 40, 44, 49, 41.5, 34, 32.5, 25.5, 27, 26.5, 17.5, 25,
49, 32.5, 35.5, 29.5, 20, 19, 19.5, 13, 15, 12.5, 12.5, 9.5,
6, 11, 13, 10, 15, 14.5, 29.5, 38.5, 18.5, 19, 24.5, 11,
12.5, 15.5, 18, 16.5, 18, 21.5, 32, 34, 32, 24.5, 19, 39,
30.5, 25, 8, 11, 9, 16, 23, 26, 24.5, 17.5, 18, 8.5, 14.5,
17.5, 16.5, 4, 11, 17, 19.5, 10, 13.5, 10, 6, 6.5, 10, 16,
18, 10, 16.5, 25.5, 24.5, 19.5, 14.5, 15, 18, 15, 10.5, 8.5,
21.5, 9.5, 9, 8.5, 18.5, 23, 26.5, 10, 13, 15, 14.5, 5, 3,
13, 6.5, 10.5, 29.5, 15.5, 10.5, 12, 11.5, 14.5, 16.5, 27,
19, 22, 19.5, 21, 27.5, 18.5, 21.5, 20, 11.5, 17, 20, 18,
28, 37, 37, 15.5, 40.5, 27.5, 30, 37, 51, 11.5, 38.5, 27,
24, 20, 23, 8.5, 25, 25.5, 22.5, 13.5, 28, 28, 28.5, 55,
51.5, 58, 56, 63, 46, 9, 15, 14.5, 19, 16.5, 8.5, 8.5, 15.5,
10, 34.5, 49, 38, 31, 38.5, 46.5, 27.5, 49, 61, 38.5, 37,
33, 39, 46, 31.5, 20, 23, 15.5, 23, 39.5, 31.5, 38.5, 61,
57, 59, 59, 40.5, 39.5, 56, 34, 11, 6, 7.5), Mean2.5 = c(6.51041675,
9.65833325, 14.12291675, 21.475, 19.07708325, 18.1125, 11.975,
7.06394925, 9.631069, 16.725, 16.3683875, 8.725, 6.29166675,
5.225, 6.15833325, 5.19855066666667, 7.7458335, 7.4083335,
7.3166665, 7.51554666666667, 11.8617753333333, 6.32708325,
1.60681825, 1.41875, 11.6229165, 7.48541675, 6.475, 11.17916675,
10.8833335, 6.96944466666667, 12.2041665, 11.3375, 8, 35.222222,
19.5324076666667, 10.20416675, 2.82028975, 15.56666675, 9.29166675,
6.9808875, 6.2708335, 8.71684775, 5.37291675, 8.21458325,
9.37291675, 6.40833325, 1.8729165, 2.725, 6.975, 11.5208335,
8.9291665, 3.4291665, 6.5666665, 3.65833325, 6.23541675,
6.3625, 11.16875, 10.7708335, 9.6791665, 9.32708325, 7.42916675,
5.1369565, 6.31666675, 5.1895835, 5.3375, 2.77083325, 2.27083325,
3.9854165, 3.7458335, 6.68958325, 5.67916675, 4.064855, 5.3625,
4.05555566666667, 2.71944466666667, 5.475, 8.0770835, 6.8833335,
7.54166675, 10.28125, 6.725, 8.53260875, 9.3625, 6.21458325,
7.78125, 6.9214675, 7.06666675, 6.45416675, 5.82708325, 4.71458325,
3.78125, 4.35208325, 4.15833325, 4.88333325, 3.68958325,
2.0875, 0.89791675, 1.5, 1.671591, 3.91875, 5.06666675, 3.95416675,
1.88333325, 3.8729165, 3.225, 2.6333335, 2.1369565, 1.32708325,
1.2604165, 1.70869575, 2.4395835, 3.43958325, 5.93958325,
5.89375, 5.66875, 4.80625, 3.62291675, 3.76041675, 2.06666675,
3.1791665, 4.16875, 3.7604165, 3.5770835, 3.37291675, 4.1333335,
4.7617755, 3.31666675, 2.95416675, 2.91875, 2.1882245, 2.965942,
3.73541675, 4.3729165, 5.46458325, 5.3375, 3.41875, 3.8729165,
4.367029, 2.7708335, 4.93958325, 4.2145835, 5.475, 4.3214015,
5.1791665, 3.39375, 3.82708325, 4.41875, 7.53487325, 7.7916665,
9.2007575, 7.0666665, 4.7413045, 5.16875, 4.7145835, 5.56666675,
5.776515, 6.49722233333333, 4.87916675, 4.87291675, 5.78125,
7.41875, 7.28125, 9.43958325, 17.013587, 22.151087, 16.2086955,
16.81666675, 14.92418475, 12.6791665, 11.81666675, 9.52083325,
10.63662275, 11.2075396666667, 10.04166675, 8.16875, 7.8166665,
6.12291675, 6.46458325, 6.28125, 4.26190475, 6.01934525,
11.667803, 7.76988625, 8.56458325, 7.1125, 4.77083325, 4.53125,
4.65833325, 3.12291675, 3.608114, 3.02490925, 3.01875, 2.34047625,
1.59188033333333, 2.6125, 2.08531766666667, 2.46458325, 3.57708325,
3.555344, 7.054762, 9.28125, 4.41875, 4.6229165, 5.91875,
2.62291675, 2.92237325, 3.65833325, 4.41875, 3.98541675,
4.32708325, 5.1583335, 7.63333325, 7.66944433333333, 7.723512,
5.98125, 4.476894, 9.33402775, 7.338735, 6.06666675, 1.9607955,
2.60208325, 2.18541675, 3.91875, 5.4645835, 6.26041675, 5.90833325,
4.16875, 4.28125, 2.13333325, 3.48043475, 4.23541675, 3.9645835,
1.064855, 2.6157895, 4.06666675, 4.68958325, 2.36547625,
3.23322375, 2.46458325, 1.4958335, 1.57708325, 2.53125, 3.82708325,
4.3729165, 2.41875, 3.89375, 6.1092105, 5.80208325, 4.7703805,
3.48257575, 3.5625, 4.60555566666667, 2.52777766666667, 2.6125,
2.03518325, 5.17767875, 2.3729165, 2.1377195, 2.07219675,
4.44682975, 5.52083325, 6.3729165, 2.41875, 2.83055566666667,
3.28333333333333, 3.475, 1.23541675, 0.5, 3.12291675, 1.51041675,
2.5203805, 7.07708325, 3.67916675, 2.46458325, 2.82708325,
2.810779, 3.5770835, 4.01041675, 6.56666675, 4.56666675,
5.3375, 4.66875, 4.85931366666667, 6.5666665, 4.45416675,
5.225, 4.7839675, 2.71458325, 4.05625, 4.87440475, 8.786111,
8.89116166666667, 8.88333325, 8.8375, 3.67916675, 9.725,
6.57708325, 7.29166675, 8.9291665, 12.65833325, 2.8833335,
9.90833325, 9.09444466666667, 6.89722233333333, 5.322222,
5, 2.12563425, 6.03125, 6.225, 5.40833325, 3.17916675, 6.7789855,
6.78125, 6.85416675, 12.9381313333333, 13.7708335, 15.32613625,
14.417844, 17.9395835, 11.53125, 2.20416675, 3.55625, 3.5208335,
4.5416665, 3.975, 2.0666665, 2.1125, 3.67916675, 2.51041675,
8.35208325, 11.77083325, 9.0770835, 7.475, 9.27083325, 11.32708325,
6.57708325, 11.975, 16.8375, 9.78125, 8.90833325, 7.8729165,
9.4854165, 11.16875, 7.55625, 4.82708325, 5.475, 3.71458325,
5.6229165, 9.43958325, 7.53125, 9.3270835, 17.62291675, 15.03125,
15.92282625, 16.05760875, 10.4395835, 9.475, 14.3625, 8.16875,
2.725, 1.29583325, 1.78508775), AQI_10 = c(7, 11.5, 15, 25,
24, 22.5, 17, 18.5, 18.5, 17.5, 16.5, 9, 6.5, 6, 6.5, NA,
NA, NA, NA, NA, 17.5, 8.5, 2.5, 4, 15, 10, 8.5, 13.5, 15,
11.5, 16.5, 17.5, 19, 25, 23, 45.5, 56.5, 49.5, 27.5, 20,
12, 19, 9, 12, 11.5, 8.5, 4, 4.5, 16, 21, 23.5, 6, 7, 4,
10, 23.5, 59.5, 59, 45, 13.5, 26.5, 17, 7.5, 9, 9, 7, 25.5,
35.5, 38.5, 45, 34.5, 25, 24, 23, 30, 29, 48, 47, 53, 47,
32, 44.5, 54.5, 43, 50.5, 44.5, 46, 29, 41.5, 36, 30.5, 30,
35, 24.5, 9, 23, 8, 7.5, 19, 24.5, 23, 14, 19, 32.5, 26,
10.5, 11, 10.5, 8.5, 4.5, 6.5, 18.5, 34, 32, 23, 19, 14.5,
13.5, 9, 14, 15.5, 13.5, 9, 16, 19, 26, 14.5, 7.5, 7.5, 7.5,
9.5, 11, 16, 20.5, 19, 8.5, 10.5, 11, 11, 17.5, 15, 16.5,
9.5, 8, 6.5, 9.5, 11.5, 17, NA, NA, 9, 12.6666666666667,
12.6666666666667, 9.66666666666667, 9.66666666666667, 9.33333333333333,
18, 10.6666666666667, 11.3333333333333, 12.3333333333333,
15, 13.3333333333333, 17.6666666666667, 33, 42, 32, 33.3333333333333,
28, 19, 16.3333333333333, 16.6666666666667, 21.6666666666667,
20.6666666666667, 24.6666666666667, 14, 11.3333333333333,
10, 15.3333333333333, 13.6666666666667, 10.6666666666667,
13.6666666666667, 15, 11, 13, 17.3333333333333, 10, 6, 11.3333333333333,
10.6666666666667, 11.5, 7.66666666666667, 10.5, 9, 9.33333333333333,
10, 7.66666666666667, 6.66666666666667, 8, 13, 19, 19.3333333333333,
9.33333333333333, 13.6666666666667, 11.3333333333333, 4,
9, 10.5, 10.5, 10.5, 12, 12.3333333333333, 13.3333333333333,
16.3333333333333, 19.3333333333333, 15, 13.3333333333333,
19, 12.3333333333333, 6.33333333333333, 7.5, 7, 8.66666666666667,
13, 13.3333333333333, 10, 6.33333333333333, 5.33333333333333,
8.33333333333333, 10, 11.3333333333333, 15, 15, 6.33333333333333,
11.3333333333333, 17, 10.3333333333333, 22, 8.66666666666667,
6.66666666666667, 7.33333333333333, 10.3333333333333, 13.3333333333333,
22, 10.3333333333333, 7, 7, 10, 7.66666666666667, 7.66666666666667,
8, 9.33333333333333, 11.5, 4.33333333333333, 4.66666666666667,
5, 6, 5.33333333333333, 5.33333333333333, 6.33333333333333,
10.3333333333333, 10.3333333333333, 13.6666666666667, 9,
15.5, 13, 20, 3.5, 2.33333333333333, 4.66666666666667, 4.5,
12.5, 22.3333333333333, 6.66666666666667, 5, 4, 4.5, 9.66666666666667,
6.33333333333333, 18, 19.6666666666667, 14, 8.33333333333333,
16.6666666666667, 12.6666666666667, 6.33333333333333, 9.66666666666667,
5.66666666666667, 4, 3.66666666666667, 10.5, 13.5, 23.5,
43.3333333333333, 32.6666666666667, 15.3333333333333, 17,
19.6666666666667, 29.6666666666667, 41.3333333333333, 38.6666666666667,
9, 39.3333333333333, 25, 6, 6, 15, 10.6666666666667, 6.66666666666667,
39, 18, 6.66666666666667, 7.66666666666667, 10, 29, 33, 23.3333333333333,
21.6666666666667, 21.3333333333333, 26.3333333333333, 14.3333333333333,
7, 5.33333333333333, 6, 5.5, 4.5, 4.66666666666667, 5, 3.66666666666667,
3.66666666666667, 10.3333333333333, 16.6666666666667, 25,
46, 22.3333333333333, 28.3333333333333, 8, 11.6666666666667,
19.6666666666667, 10, 11.6666666666667, 12, 13.6666666666667,
15.6666666666667, 7.66666666666667, 7, 6.66666666666667,
7, 8, 16, 14.6666666666667, 12, 20.6666666666667, 18, 21,
17.3333333333333, 9.33333333333333, 11.6666666666667, 17.3333333333333,
6.66666666666667, 4.33333333333333, 6.33333333333333, 12.5
), Mean10 = c(7.5, 12.5, 16, 27, 26, 24.5, 18, 20, 20, 19,
17.5, 10, 7.5, 6.5, 7, NA, NA, NA, NA, NA, 18.5, 9.5, 2.5,
4, 16, 11, 9.5, 14.5, 16, 12.5, 17.5, 19, 21, 27, 25, 51.5,
69.5, 54, 29.5, 21.5, 13, 20.5, 9.5, 13, 12.5, 9.5, 4, 5,
17, 22.5, 25.5, 6.5, 8, 4, 11, 25, 72, 72, 48.5, 14.5, 28.5,
18, 8.5, 10, 10, 8, 27.5, 39.5, 42, 49, 37, 27, 26, 25, 32.5,
31, 52.5, 52.5, 59.5, 51, 34.5, 48.5, 63, 46.5, 56, 48.5,
49.5, 31, 44.5, 39, 33, 32.5, 38, 26.5, 10, 25, 8.5, 8, 21,
26, 25, 15, 20.5, 35, 28, 11.5, 12, 11.5, 9, 4.5, 7.5, 20,
36.5, 34.5, 24.5, 20.5, 15.5, 14.5, 10, 15, 16.5, 14.5, 10,
17, 20.5, 28, 15.5, 8.5, 8, 8.5, 10.5, 12, 17, 22.5, 21,
9.5, 11.5, 12, 12, 18.5, 16, 17.5, 10.5, 9, 7, 10.5, 12.5,
18, NA, NA, 10, 14, 14, 10.3333333333333, 10.3333333333333,
10.3333333333333, 19.5, 11.6666666666667, 12.3333333333333,
13.6666666666667, 16.3333333333333, 14.3333333333333, 19,
35.3333333333333, 46, 34.3333333333333, 35.6666666666667,
30.3333333333333, 20.3333333333333, 17.6666666666667, 17.6666666666667,
23.3333333333333, 22.6666666666667, 27, 15, 12.3333333333333,
11, 16.6666666666667, 14.6666666666667, 11.6666666666667,
14.6666666666667, 16, 12, 14, 18.6666666666667, 11, 6.5,
12.6666666666667, 11.6666666666667, 12.5, 8.33333333333333,
11.5, 10, 10, 11, 8, 7, 9, 14, 20.3333333333333, 20.6666666666667,
10.3333333333333, 15, 12.3333333333333, 4.5, 9.66666666666667,
11, 11.5, 11.5, 13.3333333333333, 13.3333333333333, 14.3333333333333,
17.6666666666667, 20.6666666666667, 16.3333333333333, 14.3333333333333,
20.3333333333333, 13.3333333333333, 7.33333333333333, 8,
7.66666666666667, 9.33333333333333, 14, 14.3333333333333,
11, 7, 5.33333333333333, 9, 11, 12.3333333333333, 16.3333333333333,
16.3333333333333, 6.66666666666667, 12.3333333333333, 18.3333333333333,
11.3333333333333, 24, 9.66666666666667, 7, 8.33333333333333,
11.3333333333333, 14.6666666666667, 24, 11.3333333333333,
7.5, 7.33333333333333, 11, 8.33333333333333, 8.66666666666667,
8.66666666666667, 10.3333333333333, 12.5, 4.33333333333333,
5, 5.33333333333333, 6.5, 5.66666666666667, 5.66666666666667,
6.66666666666667, 11.3333333333333, 11, 15, 9.66666666666667,
17, 14.5, 21.6666666666667, 3.5, 2.33333333333333, 4.66666666666667,
4.5, 13.5, 23.6666666666667, 7, 5, 4, 5, 10.3333333333333,
7, 19.3333333333333, 21, 15.3333333333333, 9.33333333333333,
18, 14, 7, 10.6666666666667, 6, 4, 3.66666666666667, 11.5,
14.5, 25.5, 52.3333333333333, 35.3333333333333, 16.6666666666667,
18.3333333333333, 21, 32, 45.3333333333333, 42, 9.66666666666667,
44, 27, 6.66666666666667, 6.33333333333333, 16.3333333333333,
11.6666666666667, 7.33333333333333, 43.5, 19.3333333333333,
7, 8.33333333333333, 11, 33.6666666666667, 39, 25.3333333333333,
23.3333333333333, 23, 28.3333333333333, 15.6666666666667,
7.66666666666667, 5.66666666666667, 6.66666666666667, 6,
4.5, 5, 5.33333333333333, 3.66666666666667, 4, 11.3333333333333,
18, 27, 51.3333333333333, 24, 30.6666666666667, 9, 12.6666666666667,
21.3333333333333, 11, 12.6666666666667, 13, 14.6666666666667,
16.6666666666667, 8.66666666666667, 7.66666666666667, 7,
7.66666666666667, 8.33333333333333, 17, 16, 13, 22, 19.3333333333333,
23, 18.3333333333333, 10, 12.6666666666667, 18.6666666666667,
7, 4.66666666666667, 6.66666666666667, 14)), row.names = c(1L,
37L, 77L, 133L, 168L, 205L, 265L, 300L, 337L, 390L, 422L, 458L,
516L, 549L, 589L, 646L, 681L, 720L, 781L, 816L, 854L, 912L, 947L,
986L, 1047L, 1083L, 1121L, 1178L, 1214L, 1253L, 1314L, 1349L,
1386L, 1443L, 1478L, 1516L, 1577L, 1611L, 1650L, 1706L, 1740L,
1778L, 1840L, 1876L, 1915L, 1968L, 2001L, 2037L, 2094L, 2128L,
2164L, 2215L, 2250L, 2288L, 2350L, 2385L, 2424L, 2479L, 2512L,
2550L, 2614L, 2648L, 2686L, 2742L, 2775L, 2813L, 2874L, 2909L,
2947L, 3004L, 3040L, 3079L, 3142L, 3178L, 3217L, 3275L, 3311L,
3350L, 3414L, 3449L, 3488L, 3547L, 3583L, 3622L, 3686L, 3722L,
3760L, 3815L, 3850L, 3888L, 3951L, 3986L, 4024L, 4081L, 4115L,
4153L, 4216L, 4250L, 4288L, 4346L, 4381L, 4419L, 4481L, 4516L,
4553L, 4609L, 4643L, 4682L, 4742L, 4776L, 4814L, 4872L, 4907L,
4944L, 5006L, 5040L, 5077L, 5133L, 5167L, 5203L, 5266L, 5300L,
5338L, 5394L, 5429L, 5466L, 5529L, 5564L, 5601L, 5655L, 5690L,
5729L, 5791L, 5828L, 5867L, 5924L, 5959L, 5997L, 6058L, 6096L,
6136L, 6195L, 6231L, 6270L, 6330L, 6368L, 6407L, 6462L, 6499L,
6633L, 6672L, 6726L, 6763L, 6800L, 6863L, 6901L, 6939L, 6996L,
7031L, 7069L, 7132L, 7167L, 7206L, 7265L, 7302L, 7340L, 7404L,
7439L, 7476L, 7534L, 7570L, 7607L, 7671L, 7706L, 7743L, 7802L,
7837L, 7874L, 7938L, 7972L, 8009L, 8067L, 8102L, 8140L, 8204L,
8240L, 8278L, 8337L, 8373L, 8411L, 8471L, 8506L, 8542L, 8600L,
8635L, 8671L, 8734L, 8768L, 8805L, 8862L, 8898L, 8936L, 9000L,
9036L, 9074L, 9129L, 9163L, 9199L, 9261L, 9296L, 9333L, 9389L,
9424L, 9461L, 9523L, 9559L, 9596L, 9650L, 9685L, 9722L, 9782L,
9817L, 9855L, 9913L, 9947L, 9984L, 10047L, 10082L, 10119L, 10176L,
10210L, 10245L, 10308L, 10344L, 10381L, 10439L, 10476L, 10513L,
10576L, 10608L, 10643L, 10698L, 10735L, 10772L, 10834L, 10868L,
10905L, 10961L, 10997L, 11034L, 11095L, 11130L, 11169L, 11226L,
11262L, 11298L, 11361L, 11396L, 11433L, 11489L, 11522L, 11558L,
11622L, 11658L, 11694L, 11749L, 11785L, 11822L, 11884L, 11922L,
11959L, 12014L, 12051L, 12088L, 12146L, 12179L, 12214L, 12270L,
12305L, 12341L, 12402L, 12437L, 12474L, 12531L, 12565L, 12600L,
12662L, 12696L, 12732L, 12787L, 12819L, 12854L, 12912L, 12946L,
12981L, 13035L, 13068L, 13103L, 13165L, 13201L, 13238L, 13293L,
13327L, 13362L, 13423L, 13456L, 13490L, 13547L, 13579L, 13613L,
13672L, 13705L, 13740L, 13798L, 13831L, 13866L, 13925L, 13958L,
13992L, 14047L, 14080L, 14115L, 14173L, 14205L, 14239L, 14295L,
14329L, 14364L, 14423L, 14455L, 14490L, 14546L, 14579L, 14615L,
14677L, 14712L, 14748L, 14805L, 14840L, 14877L, 14938L, 14974L,
15012L, 15067L, 15100L, 15136L, 15199L, 15234L, 15271L, 15329L,
15363L, 15400L, 15462L, 15498L, 15535L, 15592L, 15627L, 15665L,
15727L, 15763L, 15800L, 15857L), class = "data.frame")
I have two plots from two different data frames
The DPUT from data frame 1 is as follows
ppv_npv2 <- structure(list(pred.prob = c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11,
12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27,
28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43,
44, 45, 46, 47, 48, 49, 50, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11,
12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27,
28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43,
44, 45, 46, 47, 48, 49, 50, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11,
12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27,
28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43,
44, 45, 46, 47, 48, 49, 50), variable = structure(c(1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L), .Label = c("ppv_2.5", "ppv_50", "ppv_97.5"), class = "factor"),
value = c(4.8, 9.3, 13.4, 17.2, 20.8, 24.2, 27.3, 30.3, 33.1,
35.7, 38.2, 40.5, 42.8, 44.9, 46.9, 48.8, 50.6, 52.3, 54,
55.6, 57.1, 58.5, 59.9, 61.2, 62.5, 63.7, 64.9, 66, 67.1,
68.2, 69.2, 70.2, 71.1, 72, 72.9, 73.8, 74.6, 75.4, 76.2,
76.9, 77.7, 78.4, 79, 79.7, 80.4, 81, 81.6, 82.2, 82.8, 83.3,
7.2, 13.6, 19.3, 24.4, 28.9, 33, 36.8, 40.2, 43.3, 46.2,
48.9, 51.3, 53.6, 55.7, 57.7, 59.6, 61.3, 62.9, 64.5, 65.9,
67.3, 68.6, 69.8, 70.9, 72, 73.1, 74.1, 75, 75.9, 76.8, 77.6,
78.4, 79.2, 79.9, 80.6, 81.3, 82, 82.6, 83.2, 83.8, 84.3,
84.8, 85.4, 85.9, 86.3, 86.8, 87.3, 87.7, 88.1, 88.5, 11.7,
21.1, 28.8, 35.3, 40.8, 45.5, 49.7, 53.3, 56.4, 59.3, 61.8,
64.1, 66.2, 68.1, 69.8, 71.4, 72.9, 74.2, 75.5, 76.6, 77.7,
78.7, 79.7, 80.5, 81.4, 82.2, 82.9, 83.6, 84.3, 84.9, 85.5,
86, 86.6, 87.1, 87.6, 88.1, 88.5, 88.9, 89.3, 89.7, 90.1,
90.5, 90.8, 91.1, 91.5, 91.8, 92.1, 92.4, 92.6, 92.9)),
.Names =c("pred.prob","variable", "value"), row.names = c(NA, -150L),
class = "data.frame")
The plot that i have created is from the following code
p1 <- ggplot(ppv_npv2,aes(x=pred.prob,y=value))+
geom_line(data=ppv_npv2[ppv_npv2$variable=="ppv_50",],
colour="red",linetype=2)+
geom_line(data=ppv_npv2[ ppv_npv2$variable=="ppv_2.5", ],
colour="blue",linetype=4)+
geom_line(data=ppv_npv2[ ppv_npv2$variable=="ppv_97.5", ],
colour="blue",linetype=4)+
theme_classic()+
ylab("Predicted positive predictive value (%) \n")+
xlab("\n Prevalence (%)")+
scale_x_continuous(limits=c(0,50),breaks=seq(0,50,2))+
scale_y_continuous(limits=c(0,100),breaks=seq(0,100,10), expand=c(0,0))+
theme(axis.text.x = element_text(size=12,hjust=.5,vjust=.8,face="plain"),
axis.text.y = element_text(size=12,hjust=.5,vjust=.8,face="plain"))+
theme(axis.title.x = element_text(size=14,face="bold"),
axis.title.y = element_text(size=14,face="bold"))
p1
The dput for the second data frame is
dat <- structure(list(PPV = c(57, 89, 19, 52, 52, 62, 63, 46, 31, 52,
54, 13, 17, 47, 48, 52, 96, 88, 64, 33, 62, 77, 75, 72), Prevalence = c(19,
35, 12, 16, 24, 6, 28, 13, 8, 19, 30, 6, 8, 20, 11, 25, 29, 55,
46, 13, 16, 22, 23, 20), total = c(939L, 323L, 306L, 703L, 137L,
833L, 360L, 317L, 440L, 2072L, 209L, 386L, 142L, 358L, 167L,
503L, 180L, 233L, 342L, 478L, 4870L, 1104L, 1813L, 1567L),
Author = structure(c(1L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 9L, 10L, 11L, 12L,
15L,18L, 19L, 8L, 14L, 16L, 17L, 21L, 20L, 20L, 13L, 10L),
.Label = c("Aldous",
"Bahrmann", "Body", "Christ ", "Collinson", "Eggers", "Freund",
"Giannitis", "Hammerer-Lercher", "Hoeller", "Inoue", "Invernizi",
"Keller", "Khan", "Lotze", "Melki ", "Normann", "Santalol", "Sebbane",
"Shah", "Thelin "), class = "factor"), Study.assay = structure(c(2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 1L, 1L, 1L, 1L), .Label = c("TnI", "TnT"), class = "factor")),
.Names = c("PPV", "Prevalence", "total", "Author", "Study.assay"),
class ="data.frame", row.names = c(NA, -24L))
And the plot from dataframe 2 is as follows
p2 <- ggplot(dat, aes(x=dat$Prevalence, y=dat$PPV, size=dat$total,
label=dat$Author),guide=F)+
geom_point(colour="white", fill="red", shape=21)+
scale_size_area(max_size = 10)+
scale_x_continuous(name="\n Prevalence", limits=c(0,100))+
scale_y_continuous(name="Predicted positive predictive value (%) \n",
limits=c(0,100))+
geom_text(size=2.5)+
theme_classic()+
ylab("Predicted positive predictive value (%) \n")+
xlab("\n Prevalence (%)")+
scale_x_continuous(limits=c(0,50),breaks=seq(0,50,2))+
scale_y_continuous(limits=c(0,100),breaks=seq(0,100,10), expand=c(0,0))+
theme(axis.text.x = element_text(size=12,hjust=.5,vjust=.8,face="plain"),
axis.text.y = element_text(size=12,hjust=.5,vjust=.8,face="plain"))+
theme(axis.title.x = element_text(size=14,face="bold"),
axis.title.y = element_text(size=14,face="bold"))+
theme(legend.position='none')
p2
As you can see both plots have the same axis and limits. I have two questions:
a) Can i overlay plot 2 onto plot 1?
b) Can i make the bubbles on plot 2 more transparent and choose colours by the factor dat$Study.assay (green and purple)?
Many thanks in advance - have spent a day researching this but no solution yet.
Here's a start using your data,
(plot2 <- ggplot() +
geom_line(data = ppv_npv2,aes(pred.prob, value,
group= variable, colour = variable)) +
geom_point(data = dat, aes(Prevalence, PPV, label=Author, size = total,
colour = Study.assay), alpha = I(0.4)) +
geom_text(data = dat, aes(Prevalence, PPV, label=Author,
size = total), size=3, hjust=-1, vjust=0)
)
It's not the orthodox ggplot2 way, but it's a start.