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, statalist.org is already up and running.

# st: RE: polytomous logistic regression and logistic regression using weights

 From "CJ Lan" To Subject st: RE: polytomous logistic regression and logistic regression using weights Date Wed, 9 Nov 2011 16:01:20 -0500

```For the multinomial logit, disregard univariate or multivariate, the
covariate could be category dependent initially.  After parameter
estimation, the covariate could be eliminated if it is tested not
statistically significant.

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Miranda
Sent: Tuesday, November 08, 2011 11:05 PM
To: statalist@hsphsun2.harvard.edu
Subject: st: polytomous logistic regression and logistic regression
using weights

Hello,

I have a statistical question, which may or may not be related using
Stata.

I have a categorical outcome variable which has three categories. I will
use the multinominal logistic regression for both the univariate and
multivariate analysis. However, with regarding to the univariate
analysis, their might be such circumstances that certain covariate is
associated with one category of the outcome while not with the other
category. Then how should I make the decision of whether or not to
include this covariate in multivariate analysis? Any other techniques I
could use for the bivariate analysis?

Another question: I am using the respondent driven sampling (RDS)
methods for recruit participants in the study and thus using the related
analytical tool (RDSAT) to do the data analysis. For those of you who
are familiar with this technique, individual or population weights of
the outcome variable are usually exported from the RDSAT and imported
with original data. When doing univariate and/or multivariate analysis,
these weights are usually applied to the outcome variable. When using
Stata, it does have a tab for weights selection in the logistic
regression model. I am not sure whether I need to choose frequency
weights, sampling weights.

Best,
*
*   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/

PLEASE NOTE: Florida has a very broad public records law. Most written communications to or from the Town of Jupiter officials and employees regarding public business are public records available to the public and media upon request. Your e-mail communications may be subject to public disclosure. Under Florida law, e-mail addresses are public records. If you do not want your e-mail address released in response to a public records request, do not send electronic mail to this entity. Instead, contact this office by phone or in writing. The views expressed in this message may not necessarily reflect those of the Town of Jupiter. If you have received this message in error, please notify us immediately by replying to this message, and please delete it from your computer. Thank you.

This message has been scanned for malware by Websense. www.websense.com

*
*   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/
```