CODEWITHSUNDEEP
rcategoriesdummy-variable
amisos55
amisos55

Reputation: 1979

Creating dummy variables (n-1) categories

I found similar entries but not exactly what I want. For two categorized variable (e.g., gender(1,2)), I need to create a dummy variable, 0s being male and 1s being female.

Here how my data look like and what I did. 

 data <- as.data.frame(as.matrix(c(1,2,2,1,2,1,1,2),8,1))
  V1
1  1
2  2
3  2
4  1
5  2
6  1
7  1
8  2 
library(dummies)
data <- cbind(data, dummy(data$V1, sep = "_"))
   > data
  V1 data_1 data_2
1  1      1      0
2  2      0      1
3  2      0      1
4  1      1      0
5  2      0      1
6  1      1      0
7  1      1      0
8  2      0      1

In this code, the second category is also (0,1). Also, is there a way to determine which to determine the baseline (assigning 0 to any category)?

I want it to look like this:

   > data
  V1     V1_dummy
1  1      0 
2  2      1 
3  2      1 
4  1      0 
5  2      1  
6  1      0  
7  1      0  
8  2      1

Also, I want to extend this to three category variables, having two categories after recoding (n-1).

Thanks in advance!

Upvotes: 2

Views: 390

Answers (1)

Julius Vainora
Julius Vainora

Reputation: 48191

You can use model.matrix in the following way. Some sample data with a three level factor:

set.seed(1)
(df <- data.frame(x = factor(rbinom(5, 2, 0.4))))
#   x
# 1 0
# 2 1
# 3 1
# 4 2
# 5 0

Then

model.matrix(~ x, df)[, -1]
#   x1 x2
# 1  0  0
# 2  1  0
# 3  1  0
# 4  0  1
# 5  0  0

If you want to specify which group disappears, we need to rearrange the factor levels. It is the first group that disappears. So, e.g.,

levels(df$x) <- c("1", "0", "2")
model.matrix(~x, df)[, -1]
#   x0 x2
# 1  0  0
# 2  1  0
# 3  1  0
# 4  0  1
# 5  0  0

Upvotes: 1

Related Questions