Multiple Imputation and the DASP Package error

[Chris Rooney]

Good day all,

I used multiple imputation for missing wages in my data, as such I set the data as MI. This is confirmed by using the following code:

mi set

and obtaining the following output

data mi set wide, M = 10
last mi update 04jun2024 12:47:52, approximately 21 hours ago

However, I am running into problems when using the DASP package, which is the suggested package to use when undertaking poverty and inequality analysis. I set the weight using the following code:

mi svyset [ pw= house_wgt ]

However when I try to obtain, for example, a headcount ratio, I get the following error message:

ipov hh_income_nom, alpha(0) hsize(hholdsz) index(fgt) pline(799)

no; data are mi set
    Use mi svyset to set or query these data; mi svyset has the same syntax as svyset.

    Perhaps you did not type svyset.  Some commands call svyset to obtain information about the settings.  In that case, that command is not appropriate for running directly
    on mi data.  Use mi extract to select the data on which you want to run the command, which is probably m=0.
r(119);

[daniel klein]

Please explain what the DASP package is. Where did you get it from? Who recommends its use? Also, what is ipov? It's not part of official Stata and a search shows no results.

You probably want something like

mi estimate : ipov ...

assuming that ipov supports multiple imputations.

[Nick Cox]

If memory serves, DASP is a moderately popular package but the authors are not active in any Stata forum. You need to contact them directly. Look at when the code was last revised.

[daniel klein]

Seems to be this. I would ask the authors for advice on combining their commands with mi.

[Stephen Jenkins]

Check out Ben Jann's -dstat- (SSC) for a comprehensive package that may serve your needs