Re: st: Calculation of likelihood ratio when using svy

[Richard Williams <Richard.A.Williams.5@ND.edu>]

At 08:44 AM 2/20/2008, Rodriguez, Liliana F wrote:
> Hello list,
> I'm building a logistic regression model with data from a survey. 
> Therefore, I'm using the survey function of STATA. When trying to 
> run the Likelihood Ratio to compare the model with and without a 
> Variable (potentially poor predictor), I get a message stating that 
> "lrtest is not appropriate with survey estimation results." What is 
> my alternative command to run the LR test and decide if I should 
> keep or discard this variable?
>
> Thank you,
> Liliana R.
LR tests are not appropriate with survey data because the ML 
assumption that observations are independent is violated.  Instead 
use Wald tests.  For the case of one variable, you can just look at 
the t value.  For more complicated tests, use the -test- command.

For more info, see

http://www.stata.com/support/faqs/stat/lrtest.html

http://www.stata.com/support/faqs/stat/svyml.html




-------------------------------------------
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/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/