Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: RE: tsset multiple imputation panel data

From   Steve Samuels <>
Subject   Re: st: RE: tsset multiple imputation panel data
Date   Wed, 12 May 2010 14:45:27 -0400

Assuming you have registered your data using -mi register-,  convert
to  wide format with -mi convert wide-.

Steven Samuels
18 Cantine's Island
Saugerties NY 12477
Voice: 845-246-0774
Fax:    206-202-4783

On Wed, May 12, 2010 at 2:21 PM, Nick Cox <> wrote:
> There are no work-arounds here.
> -tsset- demands that
> 1. panel data are -tsset- by specifying identifier and time.
> 2. panel data occur at most once for each combination of identifier and
> time.
> Either you arrange that the data meet that -- e.g. by working with one
> imputed dataset at a time -- or you work outside the framework of
> -tsset-. There is no third way.
> Nick
> I need to generate lagged predicting variables for the multiple
> imputation
> panal data. To gerenrate lagged varaibles, i need to teset the data
> first.
> However, i tried tsset id time and get the error message of "repeated
> time
> values within panel". I think that is casused by the five multiple
> imputed
> datasets and now saved in one database.
> Then i tried tsset id time _mj. The error message says "too many
> variables
> specified." Can anyone advice me on how to solve this problem?
> *

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index