esttab output, logistic regressioin with Odds Ration, but no constant

[Jay Rege]

Hey,

I´m doing a logistic regression and I`ve created an esttab output.

esttab Migrant11a Migrant11b Migrant11c Migrant11d,eform compress

I need the eform so that the output creates my Odds ratios. But if i use eform, I do not have a constant in my output.
Whats wrong?

[Stephen Jenkins]

Nothing is wrong. One way of thinking about this: if you had a binary variable like sex among your predictors, the estimated odds ratio for sex would tell you the change in the odds of the binary outcome taking men rather than women (say). For the constant/intercept term, such a thought exercise isn't possible (it's a constant!) -- the odds of the outcome don't vary across subjects when one looks at the constant term. Maarten Buis will no doubt have a better explanation (he is an expert on this sort of thing).

[Stephen Jenkins]

Jay: I have looked at this again. In my opinion, your question was not very clearly formulated (whether to do with reporting in logit or in esttab for instance). In addition, note that reading through the help files for esttab and estout is helpful (if only to say what you cannot find). But the following technique may help you achieve what you want:

  
  . sysuse auto, clear
(1978 Automobile Data)
 
  . logit foreign price weight, nolog
  Logistic regression                               Number of obs   =         74
                                                  LR chi2(2)      =      54.11
                                                  Prob > chi2     =     0.0000
Log likelihood = -17.976341                       Pseudo R2       =     0.6008
  ------------------------------------------------------------------------------
     foreign |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
       price |   .0009296   .0002999     3.10   0.002     .0003418    .0015174
      weight |  -.0058785   .0016986    -3.46   0.001    -.0092078   -.0025493
       _cons |   9.000473   2.627577     3.43   0.001     3.850517    14.15043
------------------------------------------------------------------------------
  
. logit foreign price weight, nolog or
  
Logistic regression                               Number of obs   =         74
                                                  LR chi2(2)      =      54.11
                                                  Prob > chi2     =     0.0000
Log likelihood = -17.976341                       Pseudo R2       =     0.6008
  ------------------------------------------------------------------------------
     foreign | Odds Ratio   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
       price |    1.00093   .0003002     3.10   0.002     1.000342    1.001519
      weight |   .9941387   .0016887    -3.46   0.001     .9908345    .9974539
       _cons |   8106.921   21301.56     3.43   0.001     47.01734     1397828
------------------------------------------------------------------------------
  
. mat li e(b)
  e(b)[1,3]
       foreign:    foreign:    foreign:
         price      weight       _cons
y1    .0009296  -.00587854   9.0004734
  
. esttab, eform
  ----------------------------
                      (1)  
                  foreign  
----------------------------
foreign                    
price               1.001**
                   (3.10)  
  weight              0.994***
                  (-3.46)  
----------------------------
N                      74  
----------------------------
Exponentiated coefficients; t statistics in parentheses
* p<0.05, ** p<0.01, *** p<0.001
 
  . ge byte constant = 1
  
. logit foreign price weight constant, nolog noconstant or
  Logistic regression                               Number of obs   =         74
                                                  Wald chi2(3)    =      12.43
Log likelihood = -17.976341                       Prob > chi2     =     0.0061
  ------------------------------------------------------------------------------
     foreign | Odds Ratio   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
       price |    1.00093   .0003002     3.10   0.002     1.000342    1.001519
      weight |   .9941387   .0016887    -3.46   0.001     .9908345    .9974539
    constant |   8106.921   21301.56     3.43   0.001     47.01734     1397828
------------------------------------------------------------------------------
  
. esttab, eform
  ----------------------------
                      (1)  
                  foreign  
----------------------------
foreign                    
price               1.001**
                   (3.10)  
  weight              0.994***
                  (-3.46)  
  constant           8106.9***
                   (3.43)  
----------------------------
N                      74  
----------------------------
Exponentiated coefficients; t statistics in parentheses
* p<0.05, ** p<0.01, *** p<0.001