Dear statalist,
Using Stata 7, I am trying to calculate 'G' scores (likelihood ratio test
statistic, G, for the hypothesis that the slope coefficient is zero) for
individual covariates. I want to use these scores for variable selection
purposes in a logistic regression model.
1. Is the above definition what is typically meant by 'G' scores?
2. To calculate a univariate G score in Stata, would I run a logistic
regression with the covariate, then -lrtest, saving (0)-, then logistic
regression (constant only), then -lrtest-?
Is the "G" score the resulting "chi2" listed in the Stata output?
3. How do you run a logistic regression (constant only)? Is it
imply -logistic depvar-?
I have read the manual and findits etc but am still a bit confused about "G"
score.
Thanks,
Wendell Joice
*
* 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/
