Related
I have a pair data as below and I want to make the expected value of the difference in the value (column called value) of pairs. In all the pairs, one has disease and the other one does not have disease as you can see from the data. In other words, the expected value of the difference of the value in one sibling compare to his/her sibling.
The description of the variable in the data are:
id = individual ID
family ID = family ID showing their dependency
status = 1 means disease and status = 0 means no-disease
Any guidance is appreciated.
d <- structure(list(id = c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20),
familyID = c(1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8, 9, 9, 10, 10),
status = c(0,1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0, 1),
value = c(29,26, 39, 22.3, 24, 41, 29.7, 24, 25.9, 21, 29,24,26,29, 15.2, 11, 35, 15.4,16, 13.4)),
class = c("tbl_df","tbl", "data.frame"), row.names = c(NA, -20L))
I'm not certain if this is what you are looking for, but I used pivot_wider from tidyr to spread the values into two columns, though with status 0 and those with status 1. Then I used mutate to take a difference between the two columns, then plotted the familyID by the newly created difference with ggplot. Note that I removed the id column for the pivot_wider to work.
d <- structure(list(id = c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20),
familyID = c(1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8, 9, 9, 10, 10),
status = c(0,1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0, 1),
value = c(29,26, 39, 22.3, 24, 41, 29.7, 24, 25.9, 21, 29,24,26,29, 15.2, 11, 35, 15.4,16, 13.4)),
class = c("tbl_df","tbl", "data.frame"), row.names = c(NA, -20L))
library(dplyr)
library(tidyr)
library(ggplot2)
d%>%
select(-id)%>%
pivot_wider(values_from = value, names_from = status)%>%
mutate("Diff" = (`0`-`1`))%>%
ggplot()+
aes(as.character(familyID), Diff)+
geom_point()
You can group by familyID, then use summarize() from the dplyr package to find the differences.
Also note the conversion of id, familyID, and status to factors, which may make life easier so they aren't confused with being integers.
library(dplyr)
library(forcats)
library(ggplot2)
d <- structure(list(id = as.factor(c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20)),
familyID = as.factor(c(1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8, 9, 9, 10, 10)),
status = as.factor(c(0,1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0, 1)),
value = c(29,26, 39, 22.3, 24, 41, 29.7, 24, 25.9, 21, 29,24,26,29, 15.2, 11, 35, 15.4,16, 13.4)),
class = c("tbl_df","tbl", "data.frame"), row.names = c(NA, -20L))
diffs <- group_by(d, familyID) %>%
summarize(., diff = (value[status == 0] - value[status == 1]))
Reordering the families by difference can help get a sense of the distribution of differences
diffs$familyID <- fct_reorder(diffs$familyID, diffs$diff, .desc = TRUE)
ggplot(diffs, aes(x = familyID, y = diff)) +
geom_bar(stat="identity")
If you really have a lot of families you may want to display a summary of the differences.
One option is with a histogram (modifying binwidth can control how fine the bins are):
ggplot(diffs, aes(x = diff)) +
geom_histogram(binwidth = 3)
Similar to a histogram is a density plot:
ggplot(diffs, aes(x = diff)) +
geom_density()
Finally, a boxplot is also a familiar summary. They're mostly meant for comparing multiple groups, but it works okay with just one. I've added the individual points using the geom_jitter() function.
ggplot(diffs, aes(y = diff)) + #If using multiple groups add x=group inside the aes() function.
geom_boxplot() +
geom_jitter(aes(x = 0))
I use ggplot and plotROC packages to draw ROC curves, but one of the drawn curves is in the opposite direction. How can I modify them to keep the two curves in the same direction?
My code is as follows：
library("plotROC")
Response <- c(0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0,
0, 0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 0, 0, 1, 1, 0, 0, 1, 0,
0, 0, 1, 1, 0, 0)
len <- c(4, 7, 8, 10, 4, 10, 10, 10, 10, 10, 9, 8, 7, 7, 5, 4, 4, 4, 3, 3, 2,
2, 9, 11, 0.5, 10, 8, 5, 4, 10, 10, 9, 8, 8, 7, 5, 1, 12, 10, 11, 9,
10, 7, 10, 7, 12, 10, 11, 10, 4, 12, 7, 12, 14, 10, 9, 9, 7, 10, 2,
12, 12, 10, 16, 10, 9, 15, 10, 9, 5, 12, 12, 11, 6, 9.5, 9, 11, 3)
gc <- c(15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15,
15, 15, 15, 15, 14, 14, 14, 14, 14, 14, 14, 13, 13, 13, 13, 13, 13, 13,
13, 12, 12, 11, 10, 9, 9, 9, 9, 9, 9, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 7,
7, 7, 7, 7, 7, 7, 7, 7, 6, 6, 6, 6, 5, 5, 5, 4, 3, 3, 3,3)
d1 <- data.frame(Response = Response, Predictor = len, group = "len")
d2 <- data.frame(Response = Response, Predictor = gc, group = "gc")
mydata <- rbind(d1, d2)
ggplot(mydata, aes(d = Response, m = Predictor, color = group, linetype = group, shape = group)) +
geom_roc(n.cut = 0, show.legend = TRUE, labels=FALSE, size = 0.6)+
geom_abline(size = 0.7, color = "grey", linetype = "dashed")+
xlab("1 - Specificity") +
ylab("Sensitivity")
I have data as follows:
thevalues <- structure(c(9, 7, 9, 9, 9, 8, 9, 6, 4, 7, 9, 9, 9, 8, 7, 7, 9,
8, 8, 9, 5, 5, 8, 7, 5, 9, 9, 7, 7, 9, 8, 7, 8, 9, 4, 7, 9, 8,
6, 7, 7, 4, 8, 6, 9, 9, 8, 1, 9, 9, 9, 8, 9, 9, 6, 7, 4, 7, 9,
6, 6, 9, 9, 8, 6, 8, 7, 7, 7, 5, 9, 5, 7, 9, 8, 4, 9, 8, 8, 8,
5, 8, 1, 7, 7, 5, 6, 9, 5, 9, 6, 9, 6, 9, 9, 9, 8, 9, 9, 9, 9,
4, 6, 4, 8, 6, 8, 8, 7, 4, 6, 7, 4, 8, 8, 8, 7, 9, 3, 8, 8, 6,
9, 8, 8, 6, 5, 8, 3, 8, 6, 8, 7, 7, 6, 9, 5, 9, 8, 7, 9, 7, 9,
9, 8, 9, 6, 8, 9, 8, 6, 8, 9, 9, 9, 4, 8, 8, 5, 8, 7, 8, 8, 9,
9, 6, 8, 5, 9, 8, 7, 9, 9, 7, 6, 8, 7, 7, 8, 9, 6, 7, 8, 9, 7,
6, 6, 9, 7, 7, 8, 7, 7, 2, 4, 9, 9, 7, 7, 9, 7, 6, 9, 9, 8, 5,
5), label = NA_character_, class = c("labelled", "numeric"))
mistakes <- structure(c(0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0,
1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 0, 1,
0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 1,
0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 0, 0,
0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0,
0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0,
0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0,
0, 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 1, 0, 1,
0, 1, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0,
0), label = NA_character_, class = c("labelled", "numeric"))
I want to create a histogram of thevalues like so:
df <- data.frame(value = c(A),
variable = rep(c("thevalues"), each = length(A)))
ggplot(df, aes(value, fill = variable)) +
geom_density(aes(y = ..count..), size = 0.7, alpha = 0.1) +
geom_bar(position = "dodge") +
scale_fill_brewer(palette = "Set1") +
scale_x_continuous(breaks = c(1:9), labels = c(1:9)) +
theme(legend.title = element_blank(), legend.position = c(0.1, 0.85))
However, I would like to see the mistakes as part of these bars:
table(thevalues, mistakes)
mistakes
thevalues 0 1
1 1 1
2 1 0
3 1 1
4 9 2
5 10 4
6 17 8 # The total height of the bar is 25, 8 have a different colour.
7 24 16 # The total height of the bar is 40, 16 have a different colour.
8 33 16 # The total height of the bar is 49, 16 have a different colour.
9 49 14 # The total height of the bar is 63, 14 have a different colour.
Something like this:
EDIT:
The solution works perfectly, but I would really like to do this when there are two variables in the histogram:
thevalues_II <- structure(c(9, 9, 9, 8, 8, 9, 6, 9, 8, 8, 6, 9, 9, 9, 6, 7, 9,
7, 8, 9, 7, 9, 9, 8, 7, 9, 8, 7, 8, 9, 8, 9, 9, 9, 9, 7, 9, 7,
8, 9, 7, 7, 8, 4, 6, 9, 7, 7, 9, 9, 9, 8, 9, 8, 9, 9, 4, 8, 9,
8, 7, 9, 9, 8, 7, 8, 9, 8, 2, 7, 8, 8, 8, 8, 8, 6, 4, 9, 9, 8,
3, 7, 3, 8, 8, 9, 7, 9, 5, 6, 7, 8, 9, 8, 9, 9, 9, 9, 9, 9, 9,
7, 3, 7, 9, 7, 7, 7, 8, 8, 9, 9, 8, 8, 9, 6, 9, 9, 6, 7, 8, 7,
8, 9, 9, 7, 6, 8, 7, 9, 6, 5, 8, 8, 7, 9, 8, 9, 9, 7, 9, 7, 9,
8, 7, 9, 4, 8, 7, 7, 9, 9, 9, 9, 9, 4, 9, 9, 6, 7, 6, 7, 8, 9,
8, 9, 5, 9, 8, 8, 8, 9, 9, 6, 8, 8, 8, 8, 8, 8, 7, 8, 9, 9, 9,
7, 4, 8, 7, 7, 9, 8, 8, 7, 5, 8, 9, 8, 8, 9, 8, 5, 8, 9, 8, 9,
7), label = NA_character_, class = c("labelled", "numeric"))
df <- data.frame(value = c(thevalues, thevalues_II),
variable = rep(c("tax", "truth"), each = length(A)))
ggplot(df, aes(value, fill = variable)) +
geom_density(aes(y = ..count..), size = 0.7, alpha = 0.3) +
geom_bar(position = "dodge") +
scale_fill_brewer(palette = "Set1") +
theme(legend.title = element_blank(), legend.position = c(0.1, 0.85))
I tried:
library(tidyverse)
mydf <- data.frame(thevalues, mistakes)
mycount <- count(mydf, thevalues, thevalues_II, mistakes)
ggplot() +
geom_col(data = mycount, aes(thevalues, thevalues_II, n, fill = as.character(mistakes))) +
geom_density(data = mydf, aes(thevalues, thevalues_II, y = ..count..), size = 0.7, alpha = 0.1) +
scale_fill_brewer(palette = "Set1") +
theme(legend.title = element_blank(), legend.position = c(0.1, 0.85))
But that does not work.
Try a summarising count first. Apologies again for lack of image - using online console with reduced facilities.
library(tidyverse)
mydf <- data.frame(thevalues, mistakes)
mycount <- count(mydf, thevalues, mistakes)
ggplot() +
geom_col(data = mycount, aes(thevalues, n, fill = as.character(mistakes))) +
geom_density(data = mydf, aes(thevalues, y = ..count..), size = 0.7, alpha = 0.1) +
scale_fill_brewer(palette = "Set1") +
theme(legend.title = element_blank(), legend.position = c(0.1, 0.85))
I have a dataset of chess positions made up of 100 groups, with each group taking one of 50 positions ("Position_number") and one of two colours ("stm_white"). I want to run a linear regression for each Position_number subsample, where stm_white is the explanatory variable and stm_perform is the outcome variable. Then, I want to display the coefficient of stm_white and the associated confidence interval for each regression in a forest plot. The idea is to be able to easily see which Position_number subsample gives significant coefficients for stm_white, and to compare coefficients across positions. For example, the plot would have 50 y-axis categories labelled with each position number, the x-axis would represent the coefficient range, and the plot would display a horizontal confidence bar for each position number.
Where I'm stuck:
Getting the confidence interval bounds for each regression
Plotting each of the 50 coefficients (with confidence intervals) on one plot. (I think this is called a forest plot?)
This is how I current get a list of the coefficients for each regression:
fits <- by(df, df[,"Position_number"],
function(x) lm(stm_perform ~ stm_white, data = x))
# Combine coefficients from each model
do.call("rbind", lapply(fits, coef))
And here is a sample of 10 positions (apologies if there's a better way to show reproducible data):
>dput(droplevels(dfMWE[,c("Position_number","stm_white","stm_perform")]))
structure(list(Position_number = c(0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 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, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
5, 5, 5, 5, 5, 5, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,
6, 6, 6, 6, 6, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
7, 7, 7, 7, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,
8, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9,
9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,
10, 10, 10, 10, 10, 10), stm_white = c(0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1), stm_perform = c(0.224847134350316, -0.252000458803946,
0.263005239459311, -0.337712202569111, 0.525880930891169, -0.5,
0.514387184165999, 0.520136722035817, -0.471249436107731, -0.557311633762293,
-0.382774969095054, -0.256365477992672, -0.592466230584332, 0.420100239642119,
0.35728693116738, -0.239203909010858, 0.492804918290949, -0.377349804212738,
0.498560888290847, 0.650604627933873, 0.244481117928803, 0.225852022298169,
0.448376452689039, 0.305090287270497, 0.275461757157464, 0.0232950364735793,
-0.117225030904946, 0.103523492101814, 0.098301745397805, 0.435599509759579,
-0.323024628921732, -0.790798102797238, 0.326223812111678, -0.331305043692668,
0.300230596737942, -0.340292005855252, 0.196181480575316, -0.0606495585093978,
0.789844179758131, -0.0862623926308338, -0.560150145231903, 0.697345078589853,
-0.425719796345476, 0.65321716721887, -0.878090073942596, 0.393712176214572,
0.636076899687882, 0.530184680003902, -0.567228844342952, 0.767024918145021,
-0.207303615824231, -0.332581578126777, -0.511510891217792, 0.227871326531416,
-0.0140876421179904, -0.891010911045765, -0.617225030904946,
-0.335142021445235, -0.517262524432376, 0.676301669492737, 0.375998241382333,
-0.0882899718631629, -0.154706189382, -0.108431333126633, 0.204584592662721,
0.475554538879339, 0.0840205872617279, -0.403370826694226, -0.74253555894307,
0.182570385474772, -0.484175014735265, -0.332581578126777, -0.427127748605496,
0.474119069108831, -0.0668284645696687, -0.0262098994728823,
-0.255269593134965, -0.313699742316688, -0.485612815834001, 0.302654921410147,
-0.425719796345476, 0.65321716721887, 0.393712176214572, 0.60766106412682,
0.530184680003902, 0.384135895746244, 0.564400490240421, 0.767024918145021,
0.702182602090521, 0.518699777929559, -0.281243170101218, -0.283576305897061,
0.349395372066127, -0.596629173305774, 0.0849108889395813, -0.264122555898524,
0.593855385236178, -0.418698521631085, 0.269754586702576, -0.719919005947152,
0.510072446927438, -0.0728722513945044, -0.0849108889395813,
0.0650557537775339, 0.063669188530584, -0.527315973006493, -0.716423694102939,
-0.518699777929559, 0.349395372066127, -0.518699777929559, 0.420100239642119,
-0.361262250888275, 0.431358608116332, 0.104596852632671, 0.198558626418023,
0.753386077785615, 0.418698521631085, -0.492804918290949, -0.636076899687882,
-0.294218640287997, 0.617225030904946, -0.333860575416878, -0.544494573083008,
-0.738109032540419, -0.192575818328721, -0.442688366237707, 0.455505426916992,
0.13344335621046, 0.116471711943561, 0.836830966002895, -0.125024693001636,
0.400603203290743, -0.363923100312118, -0.157741327529574, -0.281243170101218,
-0.326223812111678, -0.548774335859742, 0.104058949158278, -0.618584122089031,
-0.148779202375097, -0.543066492022212, -0.790798102797238, -0.541637702714763,
0.166337530816562, -0.431358608116332, -0.471249436107731, -0.531618297828107,
-0.135452994588696, 0.444109038883147, -0.309993792719686, 0.472684026993507,
-0.672509643334985, -0.455505426916992, -0.0304828450187082,
-0.668694956307332, 0.213036720610531, -0.370611452782498, -0.100361684849949,
-0.167940159469667, -0.256580594295053, 0.41031649686005, 0.544494573083008,
-0.675040201040299, 0.683816314193659, 0.397841906825283, 0.384135895746244,
0.634743335052317, 0.518699777929559, -0.598013765769344, -0.524445461120661,
-0.613136820153143, 0.12949974225673, -0.337712202569111, -0.189904841395243,
0.588289971863163, 0.434184796930767, -0.703385003471829, 0.505756208411145,
0.445530625978324, -0.167137309739621, 0.437015271896404, -0.550199353253537,
-0.489927553072562, -0.791748837508184, 0.434184796930767, 0.264122555898524,
-0.282408276808469, -0.574280203654524, 0.167940159469667, -0.439849854768097,
-0.604912902007957, 0.420100239642119, 0.35728693116738, 0.239220254140668,
-0.276612130560829, -0.25746444105693, 0.593855385236178, -0.632070012100074,
0.314483587504712, 0.650604627933873, -0.226860086923233, -0.702182602090521,
0.25746444105693, -0.174474012638818, 0.0166045907672774, 0.535915926945102,
0.141635395826102, 0.420100239642119, 0.557311633762293, 0.593855385236178,
0.6961287704296, 0.0444945730830079, -0.234005329233511, 0.448376452689039,
-0.86655664378954, 0.22107824319756, 0.148051654147426, 0.543066492022212,
-0.448376452689039, 0.373300918333268)), row.names = c(NA, -220L
), groups = structure(list(Position_number = c(0, 1, 2, 3, 4,
5, 6, 7, 8, 9, 10), .rows = structure(list(1:20, 21:40, 41:60,
61:80, 81:100, 101:120, 121:140, 141:160, 161:180, 181:200,
201:220), ptype = integer(0), class = c("vctrs_list_of",
"vctrs_vctr", "list"))), row.names = c(NA, 11L), class = c("tbl_df",
"tbl", "data.frame"), .drop = TRUE), class = c("grouped_df",
"tbl_df", "tbl", "data.frame"))
confint() can get you the confidence interval of a model.
forestplot() from the forestplot R package can make you a forest plot.
library(dplyr)
library(forestplot)
results <- lapply(unique(df$Position_number), function(pos) {
fit = filter(df, Position_number == pos) %>%
lm(data = ., stm_perform ~ stm_white)
stm_white_lm_index = 2 # the second term in lm() output is "stm_white"
coefficient = coef(fit)[stm_white_lm_index]
lb = confint(fit)[stm_white_lm_index,1] # lower bound confidence
ub = confint(fit)[stm_white_lm_index,2] # upper bound confidence
output = data.frame(Position_number = pos, coefficient, lb, ub)
return(output)
}) %>% bind_rows() # bind_rows() combines output from each model in the list
with(results, forestplot(Position_number, coefficient, lb, ub))
The forest plot shows the "Position_number" labels on the left and the regression coefficients of "stm_white" with the 95% confidence intervals plotted. You can further customize the plot. See forestplot::forestplot() or this introduction by Max Gordon for details.
The columns represent the grade of response of the respondent and the rows are the representation of the groups of ages. The table was generated with a (matrix?), the goal is to (graph? O make graphic) how the different groups of ages behave with the responses
tabla<-matrix(c(0, 0, 0, 1, 0, 0,
1, 0, 0, 0, 9, 0,
9, 1, 1, 5, 22, 0,
18, 1, 3, 1, 27, 1,
25, 7, 4, 6, 22, 3,
20, 2, 0, 0, 18, 1,
6, 2, 0, 2, 22, 0,
2, 0, 1, 1, 0, 4,
12, 0, 0, 5, 6, 0),ncol=6,byrow=TRUE)
colnames(tabla)<-c("No","is a problem","lite preblem","a moderate proble","Big problem","No respond")
rownames(tabla)<-c("16-24.5","24.5-33","33-41.5","41.5-50","50-58.5","58.5-67","67-75.5","75.5-84","No responde")
I think heatmap is a good choice. Here is a solution using the tidyverse package.
library(tidyverse)
tabla2 <- tabla %>%
as.data.frame() %>%
rownames_to_column() %>%
gather(Column, Value, -rowname)
ggplot(tabla2, aes(x = rowname, y = Column, fill = Value)) +
geom_tile() +
scale_fill_gradientn(name = "", colors = terrain.colors(10)) +
scale_x_discrete(name = "") +
scale_y_discrete(name = "")