histogram with multiple binary variables

Question

I have a dataset where columns represents variables and rows interviewers. I have 5 binary variables indicating the region where the respondent comes from (Central, South, North, East, Ovest). Central is 1 if the individual lives there, 0 otherwise. The same for the other 4 dummies.

I want to visualize a bar plot or histogram, where on the y axis I have the absolute frequencies, and on the x axis I have two sub sections, 0 and 1. For each subsection I need a bar of the absolute frequencies for Central when is 0, a bar of the absolute frequencies for South when is 0, and so on. The same for the sub section 1.

Like in the figure

You could just convert your dummy variables into a factor. See this previous answer [Recoding dummy variable to ordered factor](https://stackoverflow.com/q/14161202/4752675) — G5W, Sep 06 '22 at 17:30

score 0 · Accepted Answer · answered Sep 07 '22 at 03:43

You will get a faster response if you provide a reproducible data set. From your description, you data seems to be something like this:

set.seed(42)
x <- sample.int(5, 15, replace=TRUE)
dta <- matrix(0, 15, 5)
dta[cbind(1:15, x)] <- 1
colnames(dta) <- c("Central", "South", "North", "East", "Ovest")
head(dta)
#      Central South North East Ovest
# [1,]       1     0     0    0     0
# [2,]       0     0     0    0     1
# [3,]       1     0     0    0     0
# [4,]       1     0     0    0     0
# [5,]       0     1     0    0     0
# [6,]       0     0     0    1     0

You want to produce bar plots for each region:

freq <- colSums(dta)
bars <- rbind(Present=freq, Absent=nrow(dta) - freq)
#         Central South North East Ovest
# Present       5     5     0    3     2
# Absent       10    10    15   12    13
barplot(bars, beside=TRUE, legend=TRUE)

histogram with multiple binary variables

1 Answers1