I have 84 continuous variables with many of them having some missing values. i am using the code below for multiple imputation. i would like to know if it is possible to change the code so that it registers automatically all the variables with missing values(second line of code) and then in the 4th line of the code put the imputed variables on the left of the sign = and the other variables on the right.
Code:
mi set wide mi register imputed plasmasalivaryamyalseul glucoseact mi describe mi impute chained (regress) plasmasalivaryamyalseul glucoseact = bodyfatbmi salivasalivaryamylaseumlnew, add (20) rseed(20) note: missing-value pattern is monotone; no iteration performed
thanks in advance
0 Response to multiple imputation
Post a Comment