Conditionally replace values of multiple columns, from values of other multiple columns - r

Suppose I have this dataset:
set.seed (1234);
data.frame(cbind(a=rep(c("si","no"),30),b=rnorm(60)),
c=rep(c("d","e","f"),20)) %>% head()
Then I want to add many columns (in this example I only added two), to identify distinct cases between each group (in this case, column "a").
set.seed(1234);
data.frame(cbind(a=rep(c("si","no"),30),b=rnorm(60)),c=rep(c("d","e","f"),20)) %>%
group_by(a) %>% dplyr::mutate_at(vars(c(b,c)), .funs= list(dups_hash_ing= ~n_distinct(.)))
This code leaves the following dataset:
If I set the dataset with dput, the outcome is
structure(list(a = structure(c(2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L), .Label = c("no", "si"), class = "factor"), b = structure(c(22L,
1L, 51L, 34L, 50L, 57L, 53L, 10L, 47L, 3L, 11L, 23L, 15L, 38L,
58L, 39L, 41L, 17L, 28L, 21L, 37L, 45L, 29L, 46L, 32L, 48L, 56L,
52L, 26L, 19L, 35L, 8L, 55L, 20L, 9L, 36L, 2L, 12L, 6L, 42L,
49L, 43L, 59L, 54L, 31L, 13L, 60L, 44L, 14L, 30L, 7L, 5L, 16L,
27L, 33L, 18L, 24L, 4L, 25L, 40L), .Label = c("-0.0997905884418961",
"-0.151736536534977", "-0.198416273822079", "-0.254874652654534",
"-0.274704218225806", "-0.304721068966714", "-0.324393300483657",
"-0.400235237343163", "-0.415751788401515", "-0.50873701541522",
"-0.538070788884863", "-0.60615111526422", "-0.659770093821306",
"-0.684320344136007", "-0.789646852263761", "-0.933503340589868",
"-0.965903210133575", "-1.07754212275943", "-1.11444896479736",
"-1.60708093984972", "-2.07823754188738", "-2.7322195229558",
"-2.85575865501923", "-3.23315213292314", "0.0295178303214797",
"0.0326639575014441", "0.116845344986082", "0.162654708118265",
"0.185513915583057", "0.186492083080971", "0.287709728313787",
"0.311681028661359", "0.319160238648117", "0.413868915451097",
"0.418057822385083", "0.42200837321742", "0.485226820569252",
"0.487814635163685", "0.500694614280786", "0.594273774110513",
"0.62021020366732", "0.629536099884472", "0.660212631820405",
"0.677415500438328", "0.696768778564913", "0.700733515544461",
"0.704180178465512", "0.760462361967838", "0.895171980275539",
"0.912322161610113", "0.976031734922396", "1.1123628412626",
"1.16910851401363", "1.17349757263239", "1.49349310261748", "1.84246362620766",
"1.98373220068438", "2.16803253951933", "2.27348352044748", "2.91914013071762"
), class = "factor"), c = structure(c(1L, 2L, 3L, 1L, 2L, 3L,
1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L,
2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L,
3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L,
1L, 2L, 3L, 1L, 2L, 3L), .Label = c("d", "e", "f"), class = "factor"),
a_dups_hash_ing = 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), b_dups_hash_ing = c(30L, 30L, 30L, 30L,
30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L,
30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L,
30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L,
30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L,
30L, 30L, 30L, 30L, 30L, 30L, 30L, 30L), c_dups_hash_ing = c(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, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L)), class = c("grouped_df",
"tbl_df", "tbl", "data.frame"), row.names = c(NA, -60L), groups = structure(list(
a = structure(1:2, .Label = c("no", "si"), class = "factor"),
.rows = list(c(2L, 4L, 6L, 8L, 10L, 12L, 14L, 16L, 18L, 20L,
22L, 24L, 26L, 28L, 30L, 32L, 34L, 36L, 38L, 40L, 42L, 44L,
46L, 48L, 50L, 52L, 54L, 56L, 58L, 60L), c(1L, 3L, 5L, 7L,
9L, 11L, 13L, 15L, 17L, 19L, 21L, 23L, 25L, 27L, 29L, 31L,
33L, 35L, 37L, 39L, 41L, 43L, 45L, 47L, 49L, 51L, 53L, 55L,
57L, 59L))), row.names = c(NA, -2L), class = c("tbl_df",
"tbl", "data.frame"), .drop = TRUE))
What I need to do, is replace, column by column, if the number of distinct cases is more than one per group, with the value of the original column. I have to do this for more than 50 columns. An example of this will be provided for only one column with mutate:
dplyr::mutate(b_dups_hash_ing= ifelse(>1,b,0))
I need to repeat the code provided above for many variables. This is very similar to a mutate_at (words in brackets is what I would do). The following example does not work, but is something I would do in an ideal world, just for your better understanding of my problem.
dplyr::mutate_at(vars(contains('_dups_hash_ing')), .funs = list(~ifelse(.>1,vars([original]),0)))


Is this what you're looking for?
df %>% dplyr::mutate_at(vars(contains('_dups_hash_ing')), ~ ifelse(. > 1, ., 0)) %>% head
#> # A tibble: 6 x 6
#> # Groups: a [2]
#> a b c a_dups_hash_ing b_dups_hash_ing c_dups_hash_ing
#> <fct> <fct> <fct> <dbl> <int> <int>
#> 1 si -2.7322195229558 d 0 30 3
#> 2 no -0.09979058844189… e 0 30 3
#> 3 si 0.976031734922396 f 0 30 3
#> 4 no 0.413868915451097 d 0 30 3
#> 5 si 0.912322161610113 e 0 30 3
#> 6 no 1.98373220068438 f 0 30 3

Related

Gtsummary output with mgcv gam

I have the following data set:
structure(list(Age = c(83L, 26L, 26L, 20L, 20L, 77L, 32L, 21L,
15L, 75L, 27L, 81L, 81L, 15L, 24L, 16L, 35L, 27L, 30L, 31L, 24L,
24L, 31L, 79L, 30L, 19L, 20L, 42L, 62L, 83L, 79L, 18L, 26L, 66L,
23L, 83L, 77L, 80L, 57L, 42L, 32L, 76L, 85L, 29L, 65L, 79L, 9L,
34L, 20L, 16L, 34L, 22L, 19L, 23L, 25L, 14L, 53L, 28L, 79L, 22L,
22L, 21L, 82L, 81L, 16L, 19L, 77L, 15L, 18L, 15L, 78L, 24L, 16L,
14L, 29L, 18L, 50L, 17L, 43L, 8L, 14L, 85L, 31L, 20L, 30L, 23L,
78L, 29L, 6L, 61L, 14L, 22L, 10L, 83L, 15L, 13L, 15L, 15L, 29L,
8L, 9L, 15L, 8L, 9L, 15L, 9L, 34L, 8L, 9L, 9L, 16L, 8L, 25L,
21L, 23L, 13L, 56L, 10L, 7L, 27L, 8L, 8L, 8L, 8L, 80L, 80L, 6L,
15L, 42L, 25L, 23L, 21L, 8L, 11L, 43L, 69L, 34L, 34L, 14L, 12L,
10L, 22L, 78L, 16L, 76L, 12L, 10L, 16L, 6L, 13L, 66L, 11L, 26L,
12L, 16L, 13L, 24L, 76L, 10L, 65L, 20L, 13L, 25L, 14L, 12L, 15L,
43L, 51L, 27L, 15L, 24L, 34L, 63L, 17L, 15L, 9L, 12L, 17L, 82L,
75L, 24L, 44L, 69L, 11L, 10L, 12L, 10L, 10L, 70L, 54L, 45L, 42L,
84L, 54L, 23L, 23L, 14L, 81L, 17L, 42L, 44L, 16L, 15L, 43L, 45L,
50L, 53L, 23L, 53L, 49L, 13L, 69L, 14L, 65L, 14L, 13L, 22L, 67L,
59L, 52L, 54L, 44L, 78L, 62L, 69L, 10L, 63L, 57L, 22L, 12L, 62L,
9L, 82L, 53L, 54L, 66L, 49L, 63L, 51L, 9L, 45L, 49L, 77L, 49L,
61L, 62L, 57L, 67L, 16L, 65L, 75L, 45L, 16L, 55L, 17L, 64L, 67L,
56L, 52L, 63L, 10L, 62L, 14L, 66L, 68L, 15L, 13L, 43L, 47L, 55L,
69L, 21L, 67L, 34L, 52L, 15L, 31L, 64L, 55L, 13L, 48L, 71L, 64L,
13L, 25L, 34L, 50L, 61L, 70L, 33L, 57L, 51L, 46L, 57L, 69L, 46L,
8L, 11L, 46L, 71L, 33L, 38L, 56L, 17L, 29L, 28L, 6L, 8L), Sex = structure(c(1L,
1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 2L,
1L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L,
2L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 1L, 2L, 2L,
2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L,
2L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 2L,
2L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 1L,
1L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 1L,
1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 2L,
2L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L,
2L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L,
2L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L,
2L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L,
2L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 2L,
2L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 1L, 2L, 1L, 2L,
2L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 2L,
2L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 1L,
2L, 2L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 1L,
2L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L,
1L, 2L, 2L), .Label = c("Male", "Female"), class = "factor"),
mean_AD_scaled = c(3.15891332561581, -0.0551328105526693,
0.582747640515478, 1.94179165777054, 1.7064645993306, 2.37250948563045,
1.015775832203, 1.36189033704266, -1.05640048650493, 0.184814975542474,
-0.143366705302007, 1.81560178585347, 2.06325078470728, -0.473088628698217,
0.414641167726219, 0.199887349084444, -0.60620959209809,
-0.17879228399189, -1.03483709078065, -1.43497010225613,
-0.958595084469815, 1.0203965598582, -1.44731404613503, -1.17191867788498,
-2.02547709312595, -1.22395687266857, -1.09952727795348,
-1.0830246791849, 1.21072653232248, 1.69997357714829, 1.53648783201423,
0.208688735094353, 0.0862394522314924, 1.08662698958276,
-0.731299290763917, 2.29307697689102, -0.660008064083659,
-1.21425334459264, 1.10191939777498, -2.0957781638801, -1.14947514355972,
0.248845058764562, 2.6526135953958, 0.197907037232212, -0.222469162066061,
1.92880961340592, 1.23328008397287, -1.17288683034607, -0.308282675662673,
-1.02603570477074, -1.32647101621898, -1.58316343919798,
-0.0440210607151585, -0.388375288352846, -0.935491446193807,
-0.63789458173376, 0.454577456746182, -1.77391147749773,
0.709267564407921, 0.125735671950958, -0.821073428064989,
-0.126534054558056, 0.519597695894384, 0.188005477971066,
0.212319306823438, -1.45807374053215, 1.5856655763446, -1.25641198358011,
-0.910847565366061, -1.1191763722206, 0.25300371365424, -0.750772357310844,
0.37932560636146, -0.871791414947088, -1.92771569802088,
-1.1752191976387, 0.210449012296334, -0.347778895382139,
-0.132254955464496, 0.953616043508016, -0.0862677135627232,
0.838977990728951, -1.8993092246739, -0.0254281327692267,
0.298022803094927, -1.21559555595915, 0.0134079829994995,
-0.763094297724715, 0.334768589686298, -1.12568939786794,
-2.11786964276497, -0.0434709740895377, 0.388237009696492,
1.30050066962355, -0.260645173884043, -0.60620959209809,
1.05945271027717, -0.275717547426008, -0.0238878902174922,
0.496604074943496, 0.534009965485611, -0.692903244295693,
-0.566933407028871, 0.125625654625835, -0.518305749324122,
1.79381835547894, -0.790708646330802, -0.227860010997131,
0.347420582075538, 0.784189362817269, -0.660118081408782,
1.29962053102256, -0.561652575422924, -0.710395998990384,
-1.29315777017148, -0.457356151205503, -1.01756437073621,
0.146528946399368, -1.07136284272178, -1.42968927065019,
0.798601632408495, -0.799730066990963, -0.431348055546223,
0.569545561500617, 2.32168148142323, 0.472070211440872, 1.65145593676866,
-0.814142336582189, -0.544489872703603, -0.315433801795725,
0.382626126115175, -0.623812364117908, 0.216279930527897,
-0.606099574772967, -0.367207954999011, 0.719829227619811,
-0.749122097433987, 0.934693063586709, -0.79026857703031,
-0.371872689584264, 0.0769979969210905, -0.793899148759394,
1.50414273842782, 0.730280873506577, -0.290569886317732,
0.303743704001367, 0.390877425499463, -1.00359217044547,
-0.534918365417827, 0.325967203676389, 0.129036191704673,
0.34434009697207, -0.141386393449775, -0.363401355549725,
-0.395416397160769, -0.0235578382421178, -1.13583299524436,
1.16781977552417, -1.31890182425046, 0.139377820266317, 0.0160483988024708,
0.481311666751279, -1.05475022662807, 0.839858129329941,
0.652498624644007, -0.350199276534864, -0.262075399110649,
0.178543988010412, -1.13198238886502, -0.05117218684821,
-1.29678834190056, 0.429603523943066, 1.05098137624263, -0.956504755292464,
0.502765045150433, -0.81678275238516, -1.50263075720731,
-0.826684311646306, 2.40100397283753, 2.06633126981075, -0.470558230220369,
0.484942238480364, 0.822035322659877, 0.143888530596397,
0.384056351341786, -0.63580425255641, 0.358422314587926,
-0.372422776209885, 0.0607154328027556, -0.113221958218067,
1.02710761669075, -0.349649189909243, 2.27195365046724, -0.507634068787109,
-0.326105482332738, -1.0396778530861, 1.06484355920824, 1.32151397872221,
-0.185173288849074, -0.651888785489516, -0.171311105883464,
-0.104200537557911, -0.693673365571561, -1.26609350819101,
0.411230630647381, -0.929770545287362, -0.481009876107135,
0.386146680519137, 0.0482834750637615, -0.198265350538812,
0.790020281048832, 0.926001694901924, -1.08918564939184,
0.50298507980068, -0.0694350628187722, 1.04966116834114,
0.00878725534429612, 1.48742010500899, 0.750194009353997,
0.423772605711498, -0.596418050162068, -0.652636903300361,
-0.308942779613417, 0.314437388003408, 0.679562886624478,
-1.24312189070515, -0.432712270377761, 0.00427654501421597,
-0.197935298563442, 0.228821905592019, 1.06957430418856,
-1.61612462980509, 1.9499329398297, -0.263285589687014, 0.156430505660519,
-0.322254875953402, -0.451085163673446, -0.35526007349056,
0.10780284795577, 0.408700232169533, -0.957604928543701,
-1.05662052115517, 1.00345389178912, -0.238751726184391,
0.300003114947154, -0.397946795638617, -0.0802167606809086,
0.943714484246865, 1.10973062785877, 1.76279346979401, 1.62087112038423,
0.25533608094687, 0.226841593739787, 0.869672824438507, -1.44960240649761,
-0.450315042397579, -0.199629565370345, 0.29813282042005,
0.760425620590513, 1.87391096816911, -0.454275666102039,
-0.0559029318285365, -0.343048150401812, -1.01371376435687,
0.68880434193488, -0.29222014619459, 1.16132875334186, -1.95715633422403,
-0.534368278792206, -0.560112332871189, 1.84508642898666,
-1.19150176175703, -0.772203732244971, -0.3443683583033,
-1.45684154649076, -0.633823940704178, -1.77454957798344,
0.279539892474118, -0.875532004001301, 1.26001429397797,
-0.536590628759707, 2.1869102581465, 0.211109116247078, 0.130246382281038,
-0.355810160116181, -0.898085555651692, -0.429741802599415,
1.13360438741065, 1.61338994227581, 0.588688576072169, 0.454137387445685,
0.747113524250528, 0.460848444278238, -0.38177424884541,
-0.169990897981981, -0.747361820232001, -0.760123829946369,
0.208028631143609, -1.28748087619509, 2.33950428809329, -0.973029357526068,
-1.06091119683501, 0.917530360867389, -0.35041931118511,
-1.90613029883158, -1.15057531681095, 0.65348878057012, 0.43147381847017
)), row.names = c(NA, -308L), class = c("tbl_df", "tbl",
"data.frame"))
I am using this gam model:
m1 <- gam(mean_AD_scaled ~ s(Age, bs = 'ad', k = -1) + Sex + ti(Age, by = Sex, bs ='fs'),
data = DF,
method = 'REML',
family = gaussian)
Output:
Family: gaussian
Link function: identity
Formula:
mean_AD_scaled ~ s(Age, bs = "ad", k = -1) + Sex + ti(Age,
by = Sex, bs = "fs")
Parametric coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 0.04691 0.06976 0.672 0.502
SexFemale -0.12950 0.09428 -1.374 0.171
Approximate significance of smooth terms:
edf Ref.df F p-value
s(Age) 2.980 3.959 8.72 2.24e-06 ***
ti(Age):SexMale 2.391 2.873 23.47 < 2e-16 ***
ti(Age):SexFemale 1.000 1.000 43.40 < 2e-16 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Rank: 48/49
R-sq.(adj) = 0.34 Deviance explained = 35.6%
-REML = 375.4 Scale est. = 0.63867 n = 308
But when I use gtsummary, I get a repeated value for each gender 'interaction':
tbl_regression(m1, tidy_fun = tidy_gam)
I see the following in a publication, which I am trying to replicate with gender and age:
I am not sure how to fix this. My goal is to print a table for a manuscript so any other gam-related information that can be added like edf and R^2.

I think you've found a bug in the handling of these types of interactions. While we work on a fix to the bug, this code should get you what you need. Thanks
library(gtsummary)
#> #BlackLivesMatter
library(mgcv)
packageVersion("gtsummary")
#> [1] ‘1.5.2’
m1 <- gam(marker ~ s(age, bs = 'ad', k = -1) + grade + ti(age, by = grade, bs ='fs'),
data = gtsummary::trial,
method = 'REML',
family = gaussian)
tbl_regression(m1, tidy_fun = gtsummary::tidy_gam) %>%
modify_table_body(
~ .x %>%
dplyr::select(-n_obs) %>%
dplyr::distinct()
) %>%
as_kable() # convert to kable to display on SO
Characteristic
Beta
95% CI
p-value
Grade
I
—
—
II
-0.39
-0.70, -0.08
0.014
III
-0.13
-0.43, 0.18
0.4
s(age)
>0.9
ti(age):gradeI
0.6
ti(age):gradeII
>0.9
ti(age):gradeIII
0.6
Created on 2022-02-21 by the reprex package (v2.0.1)

lme4 error: boundary (singular) fit: see ?isSingular

I am trying to run lme4 package in R. I have 10 Lines in total with four plants for each line in each of the two replications. But some of the plants died and there are some missing values. Weight is the response variable. Here are some lines from the data:
Line Rep Weight PLANT
Line 1 1 NA 1
Line 1 1 NA 2
Line 1 1 NA 3
Line 1 1 NA 4
Line 2 1 26 1
Line 2 1 26 2
Line 2 1 26 3
Line 2 1 27 4
Line 1 2 26 1
Line 1 2 28 2
Line 1 2 26 3
Line 1 2 25 4
Line 2 2 24 1
Line 2 2 26 2
Line 2 2 25 3
Line 2 2 NA 4
I want to run linear mixed model using lme4 package so I tried running:
lme4 <- lmer(Weight ~ 1 + (1|Rep:Plant), data=Data)
But I got an error:
boundary (singular) fit: see ?isSingular
> dput(Data)
structure(list(Line = c("Line 1", "Line 1", "Line 1", "Line 1",
"Line 2", "Line 2", "Line 2", "Line 2", "Line 1", "Line 1", "Line 1",
"Line 1", "Line 2", "Line 2", "Line 2", "Line 2"), Rep = c(1,
1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2), Weight = c(NA,
NA, NA, NA, 26, 26, 26, 27, 26, 28, 26, 25, 24, 26, 25, NA),
PLANT = c(1, 2, 3, 4, 1, 2, 3, 4, 1, 2, 3, 4, 1, 2, 3, 4)), row.names = c(NA,
-16L), class = c("tbl_df", "tbl", "data.frame"))
I am using it for the first time and I am not sure about the error. I will appreciate any help!

Your model did fit, but it generated that warning because your random effects are very small. You can read more about this in this post or the help page
Let us look at your data:
ggplot(Data,aes(x=PLANT,y=Weight,col=Rep)) + geom_jitter() + geom_boxplot(alpha=0.2) + facet_wrap(~Rep)
The effects of PLANT and in combination with Rep is extremely small. Let's look at the fitted model:
fit = lmer(Weight ~ 1 + (1|PLANT:Rep),data=Data)
boundary (singular) fit: see ?isSingular
ranef(fit)
$`PLANT:Rep`
(Intercept)
1:1 0
1:2 0
2:1 0
2:2 0
3:1 0
3:2 0
4:1 0
4:2 0
This is exactly what happened. So we can try to account for some other effects and we still see very small coefficients:
fit = lmer(Weight ~ Line + (1|Rep:PLANT),data=Data)
ranef(fit)
$`Rep:PLANT`
(Intercept)
1:1 1.397563e-19
1:2 2.811371e-19
1:3 8.112169e-20
1:4 1.813251e-19
2:1 -1.725964e-19
2:2 -2.463986e-20
2:3 -2.027357e-19
2:4 -2.833681e-19
The takehome message is, there's no really systematic effect coming from PLANT, so you don't need to specify a highly complicated model, do something like:
fit = lmer(Weight ~ Line + (1|Rep),data=Data)
The data in case anyone is interested:
Data = structure(list(Line = structure(c(1L, 1L, 1L, 1L, 12L, 12L, 12L,
12L, 23L, 23L, 23L, 23L, 34L, 34L, 34L, 34L, 45L, 45L, 45L, 45L,
56L, 56L, 56L, 56L, 65L, 65L, 65L, 65L, 66L, 66L, 66L, 66L, 67L,
67L, 67L, 67L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L,
5L, 5L, 5L, 5L, 6L, 6L, 6L, 6L, 7L, 7L, 7L, 7L, 8L, 8L, 8L, 8L,
9L, 9L, 9L, 9L, 10L, 10L, 10L, 10L, 11L, 11L, 11L, 11L, 13L,
13L, 13L, 13L, 14L, 14L, 14L, 14L, 15L, 15L, 15L, 15L, 16L, 16L,
16L, 16L, 8L, 8L, 8L, 8L, 66L, 66L, 66L, 66L, 17L, 17L, 17L,
17L, 18L, 18L, 18L, 18L, 9L, 9L, 9L, 9L, 19L, 19L, 19L, 19L,
20L, 20L, 20L, 20L, 21L, 21L, 21L, 21L, 22L, 22L, 22L, 22L, 24L,
24L, 24L, 24L, 25L, 25L, 25L, 25L, 2L, 2L, 2L, 2L, 26L, 26L,
26L, 26L, 27L, 27L, 27L, 27L, 10L, 10L, 10L, 10L, 28L, 28L, 28L,
28L, 29L, 29L, 29L, 29L, 30L, 30L, 30L, 30L, 31L, 31L, 31L, 31L,
67L, 67L, 67L, 67L, 32L, 32L, 32L, 32L, 32L, 32L, 32L, 32L, 33L,
33L, 33L, 33L, 35L, 35L, 35L, 35L, 36L, 36L, 36L, 36L, 37L, 37L,
37L, 37L, 38L, 38L, 38L, 38L, 39L, 39L, 39L, 39L, 40L, 40L, 40L,
40L, 25L, 25L, 25L, 25L, 19L, 19L, 19L, 19L, 24L, 24L, 24L, 24L,
41L, 41L, 41L, 41L, 42L, 42L, 42L, 42L, 30L, 30L, 30L, 30L, 43L,
43L, 43L, 43L, 44L, 44L, 44L, 44L, 22L, 22L, 22L, 22L, 46L, 46L,
46L, 46L, 47L, 47L, 47L, 47L, 17L, 17L, 17L, 17L, 48L, 48L, 48L,
48L, 49L, 49L, 49L, 49L, 27L, 27L, 27L, 27L, 23L, 23L, 23L, 23L,
50L, 50L, 50L, 50L, 51L, 51L, 51L, 51L, 52L, 52L, 52L, 52L, 41L,
41L, 41L, 41L, 7L, 7L, 7L, 7L, 46L, 46L, 46L, 46L, 11L, 11L,
11L, 11L, 33L, 33L, 33L, 33L, 53L, 53L, 53L, 53L, 54L, 54L, 54L,
54L, 13L, 13L, 13L, 13L, 38L, 38L, 38L, 38L, 4L, 4L, 4L, 4L,
37L, 37L, 37L, 37L, 55L, 55L, 55L, 55L, 57L, 57L, 57L, 57L, 44L,
44L, 44L, 44L, 58L, 58L, 58L, 58L, 59L, 59L, 59L, 59L, 12L, 12L,
12L, 12L, 47L, 47L, 47L, 47L, 48L, 48L, 48L, 48L, 60L, 60L, 60L,
60L, 21L, 21L, 21L, 21L, 18L, 18L, 18L, 18L, 28L, 28L, 28L, 28L,
26L, 26L, 26L, 26L, 61L, 61L, 61L, 61L, 31L, 31L, 31L, 31L, 59L,
59L, 59L, 59L, 52L, 52L, 52L, 52L, 29L, 29L, 29L, 29L, 62L, 62L,
62L, 62L, 63L, 63L, 63L, 63L, 54L, 54L, 54L, 54L, 55L, 55L, 55L,
55L, 53L, 53L, 53L, 53L, 51L, 51L, 51L, 51L, 50L, 50L, 50L, 50L,
64L, 64L, 64L, 64L, 20L, 20L, 20L, 20L, 58L, 58L, 58L, 58L, 16L,
16L, 16L, 16L, 57L, 57L, 57L, 57L, 14L, 14L, 14L, 14L, 63L, 63L,
63L, 63L, 64L, 64L, 64L, 64L, 61L, 61L, 61L, 61L, 36L, 36L, 36L,
36L, 40L, 40L, 40L, 40L, 6L, 6L, 6L, 6L, 39L, 39L, 39L, 39L,
45L, 45L, 45L, 45L, 15L, 15L, 15L, 15L, 1L, 1L, 1L, 1L, 42L,
42L, 42L, 42L, 43L, 43L, 43L, 43L, 65L, 65L, 65L, 65L, 49L, 49L,
49L, 49L, 56L, 56L, 56L, 56L, 3L, 3L, 3L, 3L, 62L, 62L, 62L,
62L, 35L, 35L, 35L, 35L, 5L, 5L, 5L, 5L, 60L, 60L, 60L, 60L,
34L, 34L, 34L, 34L), .Label = c("Line1", "Line10", "Line11",
"Line12", "Line13", "Line14", "Line15", "Line16", "Line17", "Line18",
"Line19", "Line2", "Line20", "Line21", "Line22", "Line23", "Line24",
"Line25", "Line26", "Line27", "Line28", "Line29", "Line3", "Line30",
"Line31", "Line32", "Line33", "Line34", "Line35", "Line36", "Line37",
"Line38", "Line39", "Line4", "Line40", "Line41", "Line42", "Line43",
"Line44", "Line45", "Line46", "Line47", "Line48", "Line49", "Line5",
"Line50", "Line51", "Line52", "Line53", "Line54", "Line55", "Line56",
"Line57", "Line58", "Line59", "Line6", "Line60", "Line61", "Line62",
"Line63", "Line64", "Line65", "Line66", "Line67", "Line7", "Line8",
"Line9"), class = "factor"), Rep = 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, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 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, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
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, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 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), .Label = c("1", "2"), class = "factor"), Weight = c(NA,
NA, NA, NA, 26L, 26L, 26L, 27L, NA, NA, NA, NA, 26L, 28L, 26L,
25L, 22L, 17L, 20L, 20L, 28L, 20L, 27L, 26L, 22L, 25L, 21L, 25L,
18L, 18L, 19L, 18L, 24L, 28L, 23L, 30L, 29L, 25L, 26L, 27L, NA,
NA, NA, NA, 29L, 30L, 29L, 30L, NA, NA, NA, NA, 33L, NA, NA,
NA, 21L, 23L, 18L, 23L, 32L, 29L, 30L, 30L, 18L, 19L, 21L, 21L,
25L, 25L, 25L, 26L, 26L, 27L, NA, NA, 29L, 29L, 27L, 29L, 26L,
NA, NA, NA, 26L, 20L, 23L, 27L, NA, NA, NA, NA, 32L, 32L, 30L,
30L, 20L, 20L, 20L, 19L, 22L, 21L, 22L, 22L, 24L, 23L, 23L, 25L,
20L, 25L, NA, NA, 27L, 26L, NA, NA, NA, NA, NA, NA, 30L, 28L,
NA, NA, 25L, 26L, 27L, 26L, NA, NA, NA, NA, 20L, 19L, NA, NA,
19L, 27L, 26L, 29L, 26L, 29L, 31L, 29L, 25L, 25L, 24L, 25L, 26L,
25L, 26L, 26L, 25L, 24L, 24L, 28L, 22L, 26L, 24L, 28L, 29L, 30L,
26L, NA, NA, NA, NA, NA, 26L, 24L, 24L, 24L, NA, NA, NA, NA,
NA, NA, NA, NA, 30L, 30L, 30L, 31L, 24L, 25L, 28L, 22L, 28L,
31L, 30L, NA, 31L, 30L, 29L, 25L, 25L, 22L, 24L, 20L, 30L, 30L,
30L, 29L, 26L, 32L, 28L, 29L, 20L, 15L, 15L, 11L, 25L, 24L, 24L,
24L, 26L, 29L, 31L, 30L, 24L, 28L, 20L, 22L, 29L, 26L, 26L, 28L,
27L, 27L, 27L, 26L, 21L, 22L, 21L, NA, 28L, 29L, 24L, 24L, 28L,
29L, 28L, 27L, 28L, 29L, 27L, 29L, NA, NA, NA, NA, 22L, 26L,
21L, 21L, 26L, 30L, 28L, 30L, 27L, 26L, 28L, 26L, 25L, 25L, 26L,
26L, 27L, 26L, 23L, 29L, NA, NA, NA, NA, 27L, 23L, 29L, 23L,
28L, 29L, 28L, 26L, 20L, NA, NA, NA, 28L, 23L, 26L, 21L, 28L,
26L, 26L, 29L, 20L, 27L, 20L, 26L, 29L, 26L, 28L, 28L, 30L, 27L,
NA, NA, 26L, 21L, 26L, 25L, 27L, 26L, 27L, 24L, 25L, 20L, 21L,
20L, 25L, 25L, 31L, 24L, 29L, 28L, 31L, 27L, 25L, 28L, 26L, 26L,
NA, NA, NA, NA, 24L, 25L, 23L, 27L, 20L, 26L, 25L, 25L, 29L,
28L, 29L, 29L, 26L, 27L, 25L, 28L, NA, NA, NA, NA, 26L, 28L,
NA, NA, 21L, 20L, 31L, 25L, 31L, 28L, 30L, 29L, 23L, 25L, 24L,
28L, 25L, 22L, 25L, 25L, 28L, 29L, 28L, 29L, 26L, 24L, 25L, 26L,
29L, 27L, NA, NA, 26L, 29L, 29L, 30L, 25L, 24L, 25L, 24L, 28L,
25L, 29L, 28L, 24L, 24L, 24L, 24L, 28L, 30L, 27L, 27L, 26L, 25L,
25L, 25L, 25L, 25L, 28L, 25L, 25L, 30L, 28L, 25L, 22L, 24L, 25L,
24L, NA, NA, NA, NA, 5L, 7L, 4L, 5L, 21L, 20L, 22L, 24L, 25L,
27L, 25L, 28L, 32L, 31L, NA, NA, 19L, 26L, 20L, NA, 26L, 26L,
30L, 25L, 28L, 31L, 30L, 26L, 5L, 8L, 4L, 8L, 25L, 25L, 28L,
25L, 28L, 28L, 27L, 26L, 30L, 27L, 27L, 24L, 32L, 29L, 31L, 25L,
30L, 30L, 27L, 28L, 16L, 20L, 16L, 21L, 25L, 22L, 25L, 20L, 24L,
25L, 18L, 25L, 25L, 26L, 29L, 29L, 21L, 20L, 22L, 21L, 19L, 22L,
19L, 21L, 28L, 25L, 26L, 24L, 28L, 26L, 24L, 25L, NA, NA, NA,
NA, 25L, NA, NA, NA, 23L, 21L, 19L, 23L, 25L, 24L, 25L, NA, 22L,
30L, 29L, 26L, 25L, 25L, 24L, 24L), PLANT = structure(c(1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L,
3L, 4L, 1L, 2L, 3L, 4L), .Label = c("1", "2", "3", "4"), class = "factor"),
X = structure(c(4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L,
6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L,
5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L,
2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L,
4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L,
6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L,
5L, 6L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L,
7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L,
3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L,
1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L,
8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L,
7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L,
4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L,
6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L,
5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L,
2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L,
4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L,
6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L,
5L, 6L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L,
7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L,
3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L,
1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L,
8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L,
7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L,
3L, 7L, 8L, 1L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L,
6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L,
5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L,
2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L,
4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L,
6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L, 5L, 6L, 4L, 2L,
5L, 6L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L,
7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L,
3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L,
1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L,
8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L,
7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L, 3L, 7L, 8L, 1L
), .Label = c("24", "12", "21", "11", "13", "14", "22", "23"
), class = "factor")), row.names = c(NA, -536L), class = "data.frame")

Use rbind() in nested for loop with apply() in r

How can you use rbind in a for loop that runs through a list of dataframes? I tried to follow Looping through list of data frames in R but receive the following:
Error in apply(dataFramesList, 2, function(x) { :
dim(X) must have a positive length
I have two dataframes, dfTraining and dfAccuracy (code to reproduce dataframes is below), and need to add a row for any of the crop types missing from either of two columns, CROP or CROP_LABEL. I believe my problem is in my last line of code.
My code block is:
dataFramesList <- list(dfTraining, dfAccuracy)
apply(dataFramesList, 2, function(x){
cropNumbers <- seq(1,23, by = 1)
cropNumbers <- cropNumbers[-c(3)]
cropNumbers <- append(cropNumbers, 34)
listofCROPandCROP_LABELColumns <- list(dataFrameList$CROP, dataFrameList$CROP_LABEL)
missingCROP <- NULL
for (i in listofCROPandCROP_LABELColumns){
for (j in cropNumbers){
if (!j %in% i){
# If crop number is missing from CROP_LABEL, add missingCROP observation (row)
# Make row for missing crop type
missingCrop <- list(FREQUENCY = 0, AA = 1, CROP = j, CROP_LABEL = j, ACRES = 0)
dataFrameList <- rbind(dataFrameList, missingCrop)
}
}
}
})
My dfAccuracy dataframe:
structure(list(FREQUENCY = c(4L, 2L, 1L, 1L, 1L, 1L, 65L, 1L,
1L, 4L, 1L, 5L, 5L, 2L, 4L, 1L, 1L, 1L, 1L, 4L, 9L, 2L, 1L, 1L,
1L, 2L, 4L, 1L, 2L, 18L, 1L, 10L, 3L, 1L, 7L, 1L, 1L, 1L, 3L,
1L, 7L, 1L), AA = 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),
CROP = c(1L, 4L, 12L, 13L, 14L, 18L, 1L, 1L, 1L, 1L, 1L,
4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 6L, 6L, 6L, 6L, 7L, 13L,
13L, 13L, 13L, 14L, 14L, 14L, 18L, 18L, 18L, 18L, 18L, 19L,
19L, 21L, 21L, 21L, 21L), CROP_LABEL = c(1L, 4L, 14L, 13L,
12L, 18L, 1L, 4L, 5L, 6L, 18L, 1L, 4L, 6L, 14L, 18L, 12L,
14L, 18L, 1L, 6L, 14L, 18L, 18L, 4L, 6L, 13L, 21L, 12L, 14L,
18L, 1L, 6L, 14L, 18L, 21L, 1L, 19L, 6L, 13L, 21L, 34L),
ACRES = c(331.737184484, 193.772138572, 26.48543619, 73.2696289437,
112.470306056, 66.6556450342, 3905.71121736, 24.9581079934,
39.9287379709, 259.662359273, 85.2786247851, 306.051491303,
368.342995232, 154.82030835, 265.754349805, 70.3722566979,
35.4066607701, 139.336463432, 58.4307705147, 251.070357093,
471.031628349, 150.965736858, 28.2780117926, 35.3426930108,
34.5730542194, 67.7383953308, 144.442123948, 33.2746560126,
69.4072817311, 1219.65459596, 92.4840910734, 582.983473317,
191.957841327, 35.708775262, 319.638682538, 60.6889287642,
82.6244195055, 36.2898952104, 267.422844756, 72.8352758659,
489.746546145, 65.5392893502)), row.names = c(25L, 26L, 27L,
29L, 30L, 31L, 60L, 61L, 62L, 63L, 64L, 65L, 66L, 67L, 68L, 69L,
70L, 71L, 72L, 73L, 74L, 75L, 76L, 77L, 78L, 79L, 80L, 81L, 82L,
83L, 84L, 85L, 86L, 87L, 88L, 89L, 90L, 91L, 92L, 93L, 94L, 95L
), class = "data.frame")
and my dfTraining dataframe is:
structure(list(FREQUENCY = c(7L, 1L, 1L, 4L, 2L, 6L, 1L, 107L,
1L, 21L, 1L, 1L, 1L, 2L, 1L, 19L, 3L, 1L, 1L, 12L, 1L, 2L, 32L,
2L, 2L, 29L, 2L, 18L, 1L), AA = 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), CROP = c(1L, 1L, 4L, 4L, 12L, 13L, 21L,
1L, 1L, 4L, 4L, 5L, 5L, 5L, 5L, 6L, 6L, 7L, 12L, 13L, 14L, 14L,
14L, 18L, 18L, 18L, 19L, 21L, 34L), CROP_LABEL = c(1L, 4L, 1L,
4L, 12L, 13L, 21L, 1L, 6L, 4L, 6L, 1L, 5L, 14L, 18L, 6L, 14L,
1L, 12L, 13L, 1L, 6L, 14L, 6L, 14L, 18L, 19L, 21L, 34L), ACRES = c(624.940370218,
26.9188766351, 37.8773839813, 291.79294767, 140.949264214, 391.571023675,
44.5217011939, 6806.02216989, 72.7500299887, 1676.12121152, 14.8739557721,
67.0700291739, 59.7438207953, 82.6713019474, 75.62666152, 1370.78710769,
145.215281276, 41.7380537313, 66.5236760194, 679.91208779, 70.9661875374,
38.8514254734, 1749.63365551, 109.917242057, 79.7758083723, 1660.85759895,
96.8771921798, 1428.71888481, 69.473161379)), row.names = c(18L,
19L, 20L, 21L, 22L, 23L, 24L, 38L, 39L, 40L, 41L, 42L, 43L, 44L,
45L, 46L, 47L, 48L, 49L, 50L, 51L, 52L, 53L, 54L, 55L, 56L, 57L,
58L, 59L), class = "data.frame")

Making simple function to clean up data (removing rows conditionally without NA)

Hi I have animal abundance data collected from quadrats with 4 quadrats per station.
In the field, some quadrats were missed.
ex
St/ Q /Anim1 abundance /Anim 2 abundance/....etc
1 /1 /
1 /2 /
1 /3 /
1 /4 /
2 /1 /
2 /2 /
2 /4 /
3 /1 /
3 /2 /
3 /3 /
3 /4 /
Station 2 is missing quadrat 3. I would like to remove all rows (including animal abundance data) associated with station 2 from further analysis. I would like to do this in a function as I have multiple large csv files I need to clean up.
I tried subset and for loops but struggling with both
Thank you for your time
******update I'm working with this qc_Large29 <- Large29[Large29[, 5]>=4,]
which gives me all the 4th quadrats from each station. Is there a way to add a length() to it so that the new dataframe will only be the data associated with stations that have 4 quadrats?
**********update
dput(Large29[1:30,1:5])
structure(list(FID = 652:681, areaContro = c(29L, 29L, 29L, 29L,
29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L,
29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L, 29L
), areaShortN = 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), .Label = "CAIIN", class = "factor"), station = c(1L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 5L,
5L, 5L, 5L, 6L, 6L, 6L, 6L, 7L, 7L, 7L, 7L, 8L, 8L), quadrat = c(1L,
2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L,
2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L, 3L, 4L, 1L, 2L)), .Names = c("FID",
"areaContro", "areaShortN", "station", "quadrat"), row.names = c(NA,
30L), class = "data.frame")
>

This selects everything but the "2" stations:
Large29[Large29$station!=2,]
for you second question (the edit), I would suggest to use dplyr, where you can group by stations:
library(dplyr)
Large29 %>% group_by(station) %>% filter(n()>=4) %>% as.data.frame()

Linear model with repeated measures factors

I have a dataframe df
df<-structure(list(subject = c(1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L,
10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 21L, 22L,
23L, 24L, 25L, 26L, 27L, 28L, 29L, 30L, 31L, 32L, 33L, 34L, 35L,
36L, 37L, 38L, 39L, 40L, 41L, 42L, 43L, 44L, 45L, 46L, 47L, 48L,
49L, 50L, 51L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L,
12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 21L, 22L, 23L, 24L,
25L, 26L, 27L, 28L, 29L, 30L, 31L, 32L, 33L, 34L, 35L, 36L, 37L,
38L, 39L, 40L, 41L, 42L, 43L, 44L, 45L, 46L, 47L, 48L, 49L, 50L,
51L), sex = c(1L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L,
1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L,
1L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 1L,
2L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 1L,
1L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 2L,
2L, 2L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 1L), age = c(29L, 54L, 67L,
36L, 48L, 37L, 25L, 46L, 37L, 33L, 25L, 26L, 28L, 59L, 46L, 50L,
55L, 56L, 37L, 30L, 38L, 30L, 50L, 39L, 29L, 46L, 48L, 46L, 55L,
32L, 66L, 35L, 48L, 54L, 38L, 31L, 42L, 36L, 27L, 63L, 45L, 31L,
26L, 38L, 43L, 52L, 36L, 43L, 65L, 46L, 42L, 29L, 54L, 67L, 36L,
48L, 37L, 25L, 46L, 37L, 33L, 25L, 26L, 28L, 59L, 46L, 50L, 55L,
56L, 37L, 30L, 38L, 30L, 50L, 39L, 29L, 46L, 48L, 46L, 55L, 32L,
66L, 35L, 48L, 54L, 38L, 31L, 42L, 36L, 27L, 63L, 45L, 31L, 26L,
38L, 43L, 52L, 36L, 43L, 65L, 46L, 42L), edu = c(4L, 3L, 3L,
3L, 4L, 2L, 3L, 3L, 1L, 3L, 4L, 4L, 5L, 1L, 1L, 2L, 2L, 3L, 4L,
4L, 4L, 4L, 4L, 4L, 2L, 2L, 1L, 2L, 2L, 4L, 2L, 4L, 4L, 3L, 3L,
4L, 5L, 3L, 3L, 4L, 1L, 1L, 3L, 1L, 3L, 1L, 3L, 1L, 6L, 1L, 3L,
4L, 3L, 3L, 3L, 4L, 2L, 3L, 3L, 1L, 3L, 4L, 4L, 5L, 1L, 1L, 2L,
2L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 2L, 2L, 1L, 2L, 2L, 4L, 2L, 4L,
4L, 3L, 3L, 4L, 5L, 3L, 3L, 4L, 1L, 1L, 3L, 1L, 3L, 1L, 3L, 1L,
6L, 1L, 3L), biz_exp = c(5L, 15L, 3L, 4L, 10L, 6L, 0L, 5L, 8L,
5L, 0L, 8L, 3L, 23L, 5L, 7L, 5L, 11L, 4L, 4L, 11L, 3L, 15L, 4L,
4L, 6L, 6L, 5L, 13L, 2L, 13L, 6L, 8L, 27L, 7L, 3L, 11L, 5L, 1L,
4L, 8L, 8L, 4L, 15L, 18L, 30L, 9L, 14L, 18L, 21L, 16L, 5L, 15L,
3L, 4L, 10L, 6L, 0L, 5L, 8L, 5L, 0L, 8L, 3L, 23L, 5L, 7L, 5L,
11L, 4L, 4L, 11L, 3L, 15L, 4L, 4L, 6L, 6L, 5L, 13L, 2L, 13L,
6L, 8L, 27L, 7L, 3L, 11L, 5L, 1L, 4L, 8L, 8L, 4L, 15L, 18L, 30L,
9L, 14L, 18L, 21L, 16L), turnov = c(36L, NA, 12L, 9L, 48L, 9L,
8L, 24L, 4L, 250L, NA, 600L, 6L, 6L, 10L, 10L, 5L, 4L, 250L,
200L, 50L, 150L, 48L, NA, 9L, 6L, 2L, NA, NA, 3L, 7L, 23L, 75L,
7L, 5L, NA, 20L, 450L, 5L, 32L, 21L, 12L, 6L, 4L, 24L, 7L, 10L,
12L, 12L, 14L, 18L, 36L, NA, 12L, 9L, 48L, 9L, 8L, 24L, 4L, 250L,
NA, 600L, 6L, 6L, 10L, 10L, 5L, 4L, 250L, 200L, 50L, 150L, 48L,
NA, 9L, 6L, 2L, NA, NA, 3L, 7L, 23L, 75L, 7L, 5L, NA, 20L, 450L,
5L, 32L, 21L, 12L, 6L, 4L, 24L, 7L, 10L, 12L, 12L, 14L, 18L),
loc_pr = c(1L, 1L, 1L, 6L, 1L, 6L, 4L, 1L, 8L, 5L, 1L, 3L,
1L, 1L, 1L, 1L, 5L, 8L, 2L, 1L, 1L, 1L, 1L, 2L, 8L, 2L, 4L,
4L, 2L, 2L, 2L, 1L, 4L, 5L, 4L, 4L, 4L, 4L, NA, 4L, 5L, 5L,
5L, 8L, 1L, 2L, 4L, 3L, 3L, 4L, 3L, 1L, 1L, 1L, 6L, 1L, 6L,
4L, 1L, 8L, 5L, 1L, 3L, 1L, 1L, 1L, 1L, 5L, 8L, 2L, 1L, 1L,
1L, 1L, 2L, 8L, 2L, 4L, 4L, 2L, 2L, 2L, 1L, 4L, 5L, 4L, 4L,
4L, 4L, NA, 4L, 5L, 5L, 5L, 8L, 1L, 2L, 4L, 3L, 3L, 4L, 3L
), type = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 5L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 2L, 2L, 2L, 1L, 1L, 4L, 2L, 1L, 1L, 2L, 4L, 1L, 2L, 1L,
1L, 4L, 1L, 3L, 1L, 1L, 1L, 3L, 2L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 5L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 4L, 2L, 1L,
1L, 2L, 4L, 1L, 2L, 1L, 1L, 4L, 1L, 3L, 1L, 1L, 1L, 3L, 2L
), age_rec = c(2L, 4L, 4L, 100L, 4L, 100L, 100L, 4L, 100L,
2L, 1L, 2L, 2L, 4L, 4L, 4L, 4L, 100L, 3L, 2L, 3L, 2L, 4L,
3L, 100L, 27L, 100L, 100L, 4L, 2L, 100L, 2L, 4L, 30L, 3L,
2L, 59L, 8L, 100L, 27L, 3L, 59L, 2L, 59L, 3L, 59L, 3L, 3L,
4L, 64L, 3L, 2L, 4L, 4L, 100L, 4L, 100L, 100L, 4L, 100L,
2L, 1L, 2L, 2L, 4L, 4L, 4L, 4L, 100L, 3L, 2L, 3L, 2L, 4L,
3L, 100L, 27L, 100L, 100L, 4L, 2L, 100L, 2L, 4L, 30L, 3L,
2L, 59L, 8L, 100L, 27L, 3L, 59L, 2L, 59L, 3L, 59L, 3L, 3L,
4L, 64L, 3L), biz_exp_rec = c(2L, 4L, 2L, 3L, 3L, 3L, 1L,
2L, 3L, 2L, 1L, 3L, 2L, 4L, 2L, 3L, 2L, 4L, 2L, 2L, 4L, 2L,
4L, 2L, 2L, 4L, 4L, 4L, 4L, 1L, 4L, 3L, 3L, 4L, 3L, 2L, 3L,
3L, 2L, 4L, 3L, 2L, 2L, 3L, 4L, 4L, 3L, 4L, 4L, 4L, 4L, 2L,
4L, 2L, 3L, 3L, 3L, 1L, 2L, 3L, 2L, 1L, 3L, 2L, 4L, 2L, 3L,
2L, 4L, 2L, 2L, 4L, 2L, 4L, 2L, 2L, 4L, 4L, 4L, 4L, 1L, 4L,
3L, 3L, 4L, 3L, 2L, 3L, 3L, 2L, 4L, 3L, 2L, 2L, 3L, 4L, 4L,
3L, 4L, 4L, 4L, 4L), turnov_rec = structure(c(3L, NA, 3L,
2L, 3L, 3L, 1L, 3L, 3L, 4L, NA, 4L, 2L, 2L, 2L, 2L, 2L, 4L,
4L, 4L, 3L, 4L, 3L, 5L, 2L, 3L, 3L, 2L, NA, 2L, 4L, 3L, 4L,
4L, 2L, NA, 4L, 2L, 1L, 2L, 3L, 3L, 2L, 4L, 3L, 4L, 2L, 3L,
3L, 4L, 3L, 3L, NA, 3L, 2L, 3L, 3L, 1L, 3L, 3L, 4L, NA, 4L,
2L, 2L, 2L, 2L, 2L, 4L, 4L, 4L, 3L, 4L, 3L, NA, 2L, 3L, 3L,
2L, NA, 2L, 4L, 3L, 4L, 4L, 2L, NA, 4L, 2L, 1L, 2L, 3L, 3L,
2L, 4L, 3L, 4L, 2L, 3L, 3L, 4L, 3L), .Label = c("1", "2",
"3", "4", "MA"), class = "factor"), bundle = 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, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), investment = c(86L,
100L, 100L, 75L, 100L, 59L, 68L, 86L, 80L, 100L, 86L, 100L,
100L, 100L, 100L, 100L, 100L, 93L, 64L, 100L, 24L, 18L, 89L,
75L, 80L, 29L, 54L, 65L, 100L, 27L, 59L, 30L, 59L, 43L, 59L,
59L, 5L, 26L, 100L, 75L, 59L, 5L, 59L, 74L, 59L, 79L, 75L,
75L, 86L, 66L, 86L, 55L, 100L, 68L, 1L, 75L, 1L, 1L, 79L,
1L, 54L, 48L, 33L, 55L, 90L, 85L, 39L, 70L, 1L, 45L, 54L,
33L, 3L, 44L, 75L, 1L, 1L, 1L, 1L, 96L, 26L, 1L, 23L, 66L,
1L, 89L, 83L, 52L, 61L, 1L, 88L, 45L, 72L, 60L, 1L, 60L,
2L, 86L, 10L, 63L, 1L, 88L)), .Names = c("subject", "sex",
"age", "edu", "biz_exp", "turnov", "loc_pr", "type", "age_rec",
"biz_exp_rec", "turnov_rec", "bundle", "investment"), class = "data.frame", row.names = c(NA,
-102L))
In this dataframe investment is my dependent variable and the other variables are my independent variables. My subjects are crossed within type of bundle. First of all, I would like know whether my subjects do bundle or not (bundle= 1 means that people bundle and bundle=0 means that people do not bundle), it will have an effect on the investment.
I have done this mixed effect linear model but I am not sure if this is correct as my p-value are equal to zero.
library(nlme)
model <- lme(investment~bundle, random = ~1|subject/bundle, data=df)
I have also tried to make an anova with repeated measures as such:
aov(investment~bundle+ Error(subject/bundle), data=df)
It works but not sure if the model formula is right
Anyone could help me with that?

Resources