Re: st: R: Re: Factor Analysis and Multiple Imputation

[Mihir <mihir.statistics@gmail.com>]

Thank you very much Maarten. It is a very useful advice.

Regards,
Mihir

On Mon, Oct 10, 2011 at 6:53 PM, Maarten Buis <maartenlbuis@gmail.com> wrote:
> On Mon, Oct 10, 2011 at 12:30 PM, Mihir wrote:
>> Any rational for doing so? Does 5 times bigger sample size will affect the
>> factor score/bartlett score?
>
> No, should not get a five times bigger sample size, you should get
> five samples of the same size. The difference between these samples
> are the imputed values, which are random draws from the posterior
> distribution. It is a different matter how you store these different
> samples, in some (correct) ways of doing so make it appear that you
> have a 5 (or 6) times larger sample size. Important is that Stata
> knows that that is not the case, and treats these cases accordingly.
> If you want/have to do it manually (i.e. cannot use -mi- or -mim-),
> you really need to be careful in order to do this right. Anyhow, the
> logic is the same as the logic underlying multiple imputation, see any
> introductory text on that.
>
> Hope this helps,
> Maarten
>
> --------------------------
> Maarten L. Buis
> Institut fuer Soziologie
> Universitaet Tuebingen
> Wilhelmstrasse 36
> 72074 Tuebingen
> Germany
>
>
> http://www.maartenbuis.nl
> --------------------------
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
>

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/