Coding of categorical variables in logistic regression

Question

I have to do a binary logistic regression. I have a set of 7 independent variables. 4 of them are binary variables and the other 3 are categorical variables. The categorical variables are divided into 4 levels. For example, mode of payment: cash, internet banking, debit card, credit card.

I am confused whether I should make 4 columns with 0-1 dummies or just to code them 1, 2, 3, 4. What would be the right method for these variables

You probably meant, "7 explanatory variables". – StasK Mar 01 '12 at 12:08 — StasK, Mar 01 '12 at 12:08

score 4 · Answer 1 · answered Mar 01 '12 at 12:12

4

Yes, you need to separate the categories into 0/1 variables, omitting one of them. In R, this would be done with as.factor(paymentmode). In Stata, it is done with i.paymentmode (which may have to be prefixed by xi: in older versions). Some people believe in different coding schemes for these categorical variables, but really it is just a matter of how you are going to read your output, and has no effect on estimation procedure itself.

answered Mar 01 '12 at 12:12

StasK

29,235
2
80
165

3

Adding to the packages, in SAS you just need to use a CLASS statement in PROC LOGISTIC. – Peter Flom Mar 01 '12 at 14:05

Coding of categorical variables in logistic regression

1 Answers1

Linked