Binary independent variables with missing values. Create dummy variables or not?

General
#1

I am developing a prognostic model to predict an outcome. I have few binary variables with missing values, see below example. Is it better if I create dummy variables out of the below Gender variable in the model or keep it as it is? I have 79 binary variables like this. Please let me know which is best.

Gender
M
F
M
M
.
F
M
F
M
F
.
F
.
M
#2

One can go either way. If you have 79 binary variables and they are missing values on different observations you could end up with very little data is you drop the observations with missing data. In that case you would be better off with three dummies for each binary.

#3

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.