Bookmark and Share

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.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Re: Test equality of predictors after logistic regression


From   Debs Majumdar <debs_stata@yahoo.com>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   st: Re: Test equality of predictors after logistic regression
Date   Mon, 24 Sep 2012 22:27:58 -0700 (PDT)

Pressed enter too soon.

I think  
test  score_v1 score_v2 score_v3 score_v4 


 ( 1)  [status]score_v1 = 0
 ( 2)  [status]score_v2 = 0
 ( 3)  [status]score_v3 = 0
 ( 4)  [status]score_v4 = 0

           chi2(  4) =   11.86
         Prob > chi2 =    0.0185



tests if the coefficients of the four scores are simultaneously equals to zero with 4 degrees of freedom..


whereas if I want to test if the four scores are equal or not, then I would just do


test  score_v1=score_v2=score_v3=score_v4 

which will test

( 1)  [status]score_v1 - [status]score_v2 = 0
 ( 2)  [status]score_v1 - [status]score_v3 = 0
 ( 3)  [status]score_v1 - [status]score_v4 = 0

           chi2(  3) =    9.57
         Prob > chi2 =    0.0276


Am I right here?

 Thanks




----- Original Message -----
From: Debs Majumdar <debs_stata@yahoo.com>
To: "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Cc: 
Sent: Monday, September 24, 2012 9:36 PM
Subject: Test equality of predictors after logistic regression

Hi All,

 I ran the following logistic regression:

logit status score_v1 score_v2 score_v3 score_v4  c1-c3   site1 - site14


I am supposed to test if the effects of the four scores (v1-v4) are different or not?


 Should I just run 

test  score_v1 score_v2 score_v3 score_v4   


after running the logistic regression?

Thanks,

Debs

*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index