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: How do the Wald test chi-square statistic and the pseudo r-square relate to each other in clogit?


From   LUCIA SUMMERS <summers_lucia@hotmail.com>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: How do the Wald test chi-square statistic and the pseudo r-square relate to each other in clogit?
Date   Thu, 2 Feb 2012 19:17:42 +0000

Hello,

I am trying to understand some results I got (see below) and any assistance will be greatly appreciated.
I have run a number of conditional logit models (with cluster-adjusted robust SEs) and usually, if you get a greater Wald chi-square value, you also get a greater pseudo r-square. 
But the models below are strange in that the first one has a great pseudo r-square value while the second one has a greater Wald chi-square value. The only thing that changes from one model to the next are the third and fourth variables starting from the bottom (i.e., in the second model, a_lneuclkm and m_lneuclkm have been substituted by a_lneuclmins and m_lneuclmins).
Does anyone have any information about how the Wald test statistic is calculated so that I can relate this to how the log-likelihood and the pseudo r-square are calculated (and work out why they might be behaving in this way)?
Thanks very much,
Lucia.

Model 1
. clogit choice commerc100 nostations popdens unemp10 imdincome imdhealth imdeducation imdhousing imdliving age15to29p10 seh100 eh100 mob10 a_lneuclkm m_lneuclkm sameethnic10 barrier, group(accno) vce(cluster crid) or
Iteration 0:   log pseudolikelihood = -3001.5126  Iteration 1:   log pseudolikelihood = -2981.3624  Iteration 2:   log pseudolikelihood = -2981.1934  Iteration 3:   log pseudolikelihood = -2981.1934  
Conditional (fixed-effects) logistic regression   Number of obs   =    2434915                                                  Wald chi2(17)   =    2123.56                                                  Prob > chi2     =     0.0000Log pseudolikelihood = -2981.1934                 Pseudo R2       =     0.3111
                                 (Std. Err. adjusted for 276 clusters in crid)------------------------------------------------------------------------------             |               Robust      choice | Odds Ratio   Std. Err.      z    P>|z|     [95% Conf. Interval]-------------+----------------------------------------------------------------  commerc100 |   1.085783   .0265569     3.36   0.001      1.03496    1.139101  nostations |   1.031757   .1310436     0.25   0.806     .8043889    1.323392     popdens |   .9933222   .0018225    -3.65   0.000     .9897565    .9969008     unemp10 |   2.113067   1.908653     0.83   0.408     .3597953    12.40998   imdincome |   8.174588   14.58476     1.18   0.239     .2476213    269.8633   imdhealth |   1.317499   .3145333     1.15   0.248     .8251607    2.103595imdeducation |   .9797458   .0111904    -1.79   0.073     .9580568    1.001926  imdhousing |   .9871881   .0132498    -0.96   0.337     .9615576    1.013502   imdliving |   1!
 .007555   .0072077     1.05   0.293      .993527    1.021781age15to29p10 |   .9085186   .2040912    -0.43   0.669     .5849496    1.411072      seh100 |   1.080342   .0875577     0.95   0.340     .9216681    1.266333       eh100 |   1.002131   .0102836     0.21   0.836     .9821768    1.022491       mob10 |     1.5589   .4010742     1.73   0.084     .9415009    2.581164  a_lneuclkm |   .1852571   .0089984   -34.71   0.000      .168434    .2037605  m_lneuclkm |   .1642576   .0171001   -17.35   0.000     .1339401    .2014374sameethnic10 |   1.320282   .0669419     5.48   0.000     1.195387    1.458226     barrier |   .4008838   .0867893    -4.22   0.000     .2622634    .6127725------------------------------------------------------------------------------


Model 2
. clogit
choice commerc100 nostations popdens unemp10 imdincome imdhealth imdeducation
imdhousing imdliving age15to29p10 seh100 eh100 mob10 a_lneuclmins m_lneuclmins
sameethnic10 barrier, group(accno) vce(cluster crid) or

 

Iteration
0:   log pseudolikelihood =
-3055.2028  

Iteration
1:   log pseudolikelihood =
-3035.5308  

Iteration
2:   log pseudolikelihood =
-3035.4117  

Iteration
3:   log pseudolikelihood =
-3035.4117  

 

Conditional
(fixed-effects) logistic regression  
Number of obs   =    2434915

                                                 
Wald chi2(17)   =    3070.44

                                                  Prob
> chi2     =     0.0000

Log
pseudolikelihood = -3035.4117                
Pseudo R2       =     0.2986

 

                                 (Std. Err.
adjusted for 276 clusters in crid)

------------------------------------------------------------------------------

             |               Robust

      choice | Odds Ratio   Std. Err.      z   
P>|z|     [95% Conf. Interval]

-------------+----------------------------------------------------------------

  commerc100 |  
1.080073   .0234639     3.55  
0.000      1.03505    1.127055

  nostations |    .973521  
.1170455    -0.22   0.823    
.7691413    1.232209

     popdens |  
.9921836   .0018916    -4.12  
0.000      .988483     .995898

     unemp10 |  
2.280424   2.013854     0.93  
0.351     .4039385    12.87407

   imdincome |  
5.966666   10.39074     1.03  
0.305      .196514    181.1632

   imdhealth |  
1.307199    .289918     1.21  
0.227     .8463645    2.018952

imdeducation
|   .9814027   .0110888   
-1.66   0.097     .9599079   
1.003379

  imdhousing |    .984771  
.0126269    -1.20   0.231    
.9603312    1.009833

   imdliving |  
1.005372   .0071359     0.75  
0.450      .991483    1.019456

age15to29p10
|   .9137366   .2075709   
-0.40   0.691     .5854045   
1.426218

      seh100 |  
1.080684   .0880311     0.95  
0.341     .9212152    1.267759

       eh100 |  
1.003857   .0098699     0.39  
0.695     .9846979    1.023389

       mob10 |  
1.478928   .3834865     1.51  
0.131     .8896727    2.458464

a_lneuclmins
|    .100379   .0054367  
-42.44   0.000     .0902694   
.1116209

m_lneuclmins
|   .0900161   .0094458  
-22.95   0.000     .0732825   
.1105708

sameethnic10
|   1.329318   .0638578    
5.93   0.000      1.20987   
1.460558

     barrier |  
.2776155   .0561903    -6.33  
0.000     .1867057    .4127905

------------------------------------------------------------------------------
 		 	   		   		 	   		   		 	   		  
*
*   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