Re: st: Pseudo R2 after "mi estimate:logit"

[Richard Williams <richardwilliams.ndu@gmail.com>]

At 03:12 PM 3/14/2011, Aggie Chidlow wrote:
> Hi (again) Rich,
>
> My do-file is:
>
> mi set mlong
> mi query
> mi describe
> mi misstable sum
> generate lnx = cond(x==0, mindouble(), log(x3))
> mi register imputed lnx
> set seed 29390
> mi describe
> mi impute mvn lnx = x1 x2 x3 x4 x5 x6 x7,add(30)
> mi estimate: logit x1 x2 x3 x4 x5 x6 x7 lnx
> mi xeq 0 1 30: logit x1 x2 x3 x4 x5 x6 x7 lnx
>
> For example from "mi xeq 30:logit x1 x2 x3 x4 x5 x6 x7 lnx" I can see
> Wald test.However, from "mi estimate: logit x1 x2 x3 x4 x5 x6 x7 lnx"
> I can only see F test. So, how can I get Wald test from "mi estimate:
> logit"?

I can't see your output, but I am guessing that you are referring to 
the fact that -mi ex 30- gives you a line that looks like

LR chi2(8)

whereas -mi estimate- gives you something like

F(   8,1000)

If so, then F is the appropriate statistic for the MI model rather 
than a Likelihood Ratio Chi Square.

Or, maybe you are referring to the fact that -mi estimate- gives you 
T values for each coefficient whereas -mi xeq- gives you Z values. 
Again, T values are correct.

I don't claim to be able to explain why but I suggest you read the 
Manual entries for -mi-. Among other things, its says

"With a small number of imputations, the reference distribution for 
the MI inference is Student's t (or F in multiple-hypothesis 
testing). The residual degrees of freedom depend
on M and the rates of missing information and thus are different for 
each parameter of interest."

> Further, how do I know that 30 imputations (M=30) is the adequate
> number? I am asking because according to Rubin (1987) only 3-10
> imputations may be needed?

The Stata Manual says "A small number of imputations (5 to 20) may be 
sufficient when fractions of missing data are low. High fractions of 
missing data as well as particular data structures may require up to 
100 (or more) imputations. Whenever feasible to do so, we recommend 
that you vary the number of imputations to see if this affects your results."

For more, I suggest you type

help mi_intro_substantive

and then read the manual entry.


-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
WWW:    http://www.nd.edu/~rwilliam

*
*   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/