missing values for categorical variables

[apxprdtr10]

I have 65 categorical variables and all of them have around 15% missing values. It would be great if you can help me to suggest how to impute missing values for categorical variables.

[PeterClemmensen]

Well, it depends largely on what you want to do with the data.. However, you can use PROC STDIZE to impute the data. 

Also, see the article Mean imputation in SAS where some issues with mean imputation are highlighted.

[apxprdtr10]

I want to impute mode values for missing categorical variables.

[PeterClemmensen]

Ok. Do you have By Groups in your data?

[apxprdtr10]

yes

[Ksharp]

One way is using its MODE to replace missing.

Another smart way is using PROC MI .