I am using multiple imputation and survey data with a logit model and would like to calculate Pseudo R2 for each model.
I have followed the procedure laid out here: https://www.stata.com/support/faqs/s...-imputed-data/ and I am able to calculate the cstat with the following code:
Code:
local model1 "IVs" no mi estimate, or saving(miest, replace): svy: logit DV `model1' mi query local M = r(M) scalar r2 = 0 scalar cstat = 0 qui mi xeq 1/`M': svy: logit DV `model1'; scalar r2=r2+e(r2_p); lroc, nog; scalar cstat=cstat+r(area) scalar r2 = r2/`M' scalar cstat = cstat/`M' noi di "Pseudo R-squared over imputed data=" r2 noi di "C statistic over imputed data=" cstat
Code:
Pseudo R-squared over imputed data =.
Thank you,
Marc
0 Response to Pseudo R2 for logit and mlogit in multiple imputation
Post a Comment