# RE: st: Predict and adjust

 From "Scott Merryman" <[email protected]> To <[email protected]> Subject RE: st: Predict and adjust Date Tue, 2 Jan 2007 14:40:24 -0600

```> -----Original Message-----
> From: [email protected] [mailto:owner-
> [email protected]] On Behalf Of Tim Wade
> Sent: Thursday, December 28, 2006 9:16 AM
> To: [email protected]
> Subject: Re: st: Predict and adjust
>
> wanted to point out that if you use adjust to generate predicted
> probabilities based on each individual covariate pattern in the
> example  Fred provided where no variables or by variables are
> specified in the adjust command, the results are the same as those
> obtained from predict. There appear to be some very slight
> differences, but I would imagine these are just artificats resulting
> from the calculations (rounding or precision). To my understanding,
> they should be the same.

If you open up -adjust- and search and replace "_predict" with "_predict
double" and save as -myadjust- the differences disappear.

. do "C:\DOCUME~1\Scott_2\LOCALS~1\Temp\STD0i000000.tmp"

. use http://www.stata-press.com/data/r9/lbw,clear
(Hosmer & Lemeshow data)

. qui xi: logistic low age lwt i.race smoke,nolog

. predict double p
(option p assumed; Pr(low))

. /*probabilities from adjust and predict are equal to 6 decimal places*/
. assert round(p, 0.000001)==round(p2, 0.000001)

. assert round(p, 0.0000001)==round(p2, 0.0000001)

. list p p2 if p~=p2

.
end of do-file

Scott

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/
```