Hi everyone,

The dataset I am using for my thesis is the ‘Survey of Consumer Finances’ - a feature of the dataset is that any missing values (from survey respondents who do not answer or miss questions) are imputed. Specifically, for every respondent, there are 5 imputations.

The problem is, I am unsure of how to perform regressions and econometric analysis in a way that accounts for this multiple imputation. I have searched online for ways to do it. Although Stata does have an in-built command feature that lets you deal with multiple imputation analysis, unfortunately I do not think I can use it, as it requires the original, raw and ‘unimputed’ numbers - this is something the SCF does not provide. This inability is mentioned in both the manual I just linked and here.

I have found an alternative command here but I lack a method of verification - even when I get it to run, there is no way for me to know whether what I have done is correct.

Can somebody who has experienced this provide me with some guidance on what to do?

Thank you!