(ssc) esttab and stcrreg: option equations() invalid

[lucas reddinger]

For some reason esttab (an ssc package) will not let me combine these two outputs:

. stcrreg contrib vx1adultHazRtHat, compete(dosedByNow==2)

[ . . . ]

Competing-risks regression                        No. of obs      =      5,482
                                                  No. of subjects =        539
Failure event:   dosedByNow == 1                  No. failed      =        194
Competing event: dosedByNow == 2                  No. competing   =         37
                                                  No. censored    =        308

                                                  Wald chi2(2)    =       5.88
Log pseudolikelihood = -1184.7533                 Prob > chi2     =     0.0528

                               (Std. err. adjusted for 539 clusters in subject_id)
----------------------------------------------------------------------------------
                 |               Robust
              _t |        SHR   std. err.      z    P>|z|     [95% conf. interval]
-----------------+----------------------------------------------------------------
         contrib |   1.125542   .0549522     2.42   0.015     1.022831    1.238568
vx1adultHazRtHat |   1.024642    .043759     0.57   0.569      .942367      1.1141
----------------------------------------------------------------------------------

. eststo e1, title("cr")

. stcrreg contrib vx1adultHazRtHat, compete(dosedByNow==2) tvc(contrib vx1adultHazRtHat)

[ . . . ]

Competing-risks regression                        No. of obs      =      5,482
                                                  No. of subjects =        539
Failure event:   dosedByNow == 1                  No. failed      =        194
Competing event: dosedByNow == 2                  No. competing   =         37
                                                  No. censored    =        308

                                                  Wald chi2(4)    =       6.33
Log pseudolikelihood = -1184.4078                 Prob > chi2     =     0.1759

                               (Std. err. adjusted for 539 clusters in subject_id)
----------------------------------------------------------------------------------
                 |               Robust
              _t |        SHR   std. err.      z    P>|z|     [95% conf. interval]
-----------------+----------------------------------------------------------------
main             |
         contrib |   1.167825   .0900622     2.01   0.044     1.003999    1.358382
vx1adultHazRtHat |   1.058385   .0715551     0.84   0.401     .9270347    1.208347
-----------------+----------------------------------------------------------------
tvc              |
         contrib |   .9991668   .0012241    -0.68   0.496     .9967704    1.001569
vx1adultHazRtHat |   .9991421   .0013809    -0.62   0.535     .9964393    1.001852
----------------------------------------------------------------------------------
Note: Variables in tvc equation interacted with _t.

. eststo e2, title("tvc")

. esttab e1

----------------------------
                      (1)  
                       _t  
----------------------------
eq1                        
contrib             0.118*  
                   (2.42)  

vx1adultHa~t       0.0243  
                   (0.57)  
----------------------------
N                    5482  
----------------------------
t statistics in parentheses
* p<0.05, ** p<0.01, *** p<0.001

. esttab e2

----------------------------
                      (1)  
                       _t  
----------------------------
main                        
contrib             0.155*  
                   (2.01)  

vx1adultHa~t       0.0567  
                   (0.84)  
----------------------------
tvc                        
contrib         -0.000834  
                  (-0.68)  

vx1adultHa~t    -0.000858  
                  (-0.62)  
----------------------------
N                    5482  
----------------------------
t statistics in parentheses
* p<0.05, ** p<0.01, *** p<0.001

. esttab e1 e2
option equations() invalid
specified equation name already occurs in model 2
r(198);

Anyone have an idea of what is going wrong? I tried specifying "equations()" to try to clear out whatever it dislikes, to no avail. Thanks!!

[Andrew Musau]

Can you provide a reproducible example?

[lucas reddinger]

Thanks for your response. Here is one:

. use https://www.stata-press.com/data/r17/hypoxia
(Hypoxia study)

. stset dftime, failure(failtype == 1)

Survival-time data settings

         Failure event: failtype==1
Observed time interval: (0, dftime]
     Exit on or before: failure

--------------------------------------------------------------------------
        109  total observations
          0  exclusions
--------------------------------------------------------------------------
        109  observations remaining, representing
         33  failures in single-record/single-failure data
    353.129  total analysis time at risk and under observation
                                                At risk from t =         0
                                     Earliest observed entry t =         0
                                          Last observed exit t =     8.454

. stcrreg ifp tumsize pelnode, compete(failtype == 2)

        Failure _d: failtype==1
  Analysis time _t: dftime

Iteration 0:   log pseudolikelihood = -138.67925  
Iteration 1:   log pseudolikelihood = -138.53082  
Iteration 2:   log pseudolikelihood =  -138.5308  
Iteration 3:   log pseudolikelihood =  -138.5308  

Competing-risks regression                        No. of obs      =        109
                                                  No. of subjects =        109
Failure event:   failtype == 1                    No. failed      =         33
Competing event: failtype == 2                    No. competing   =         17
                                                  No. censored    =         59

                                                  Wald chi2(3)    =      33.21
Log pseudolikelihood =  -138.5308                 Prob > chi2     =     0.0000

------------------------------------------------------------------------------
             |               Robust
          _t |        SHR   std. err.      z    P>|z|     [95% conf. interval]
-------------+----------------------------------------------------------------
         ifp |   1.033206   .0178938     1.89   0.059     .9987231    1.068879
     tumsize |   1.297332   .1271191     2.66   0.008     1.070646    1.572013
     pelnode |   .4588123   .1972067    -1.81   0.070     .1975931    1.065365
------------------------------------------------------------------------------

. eststo e1, title("cr")

. stcrreg ifp tumsize pelnode, compete(failtype == 2) tvc(ifp tumsize pelnode)

        Failure _d: failtype==1
  Analysis time _t: dftime

Iteration 0:   log pseudolikelihood = -137.02685  
Iteration 1:   log pseudolikelihood =  -136.7927  
Iteration 2:   log pseudolikelihood = -136.79001  
Iteration 3:   log pseudolikelihood =    -136.79  

Competing-risks regression                        No. of obs      =        109
                                                  No. of subjects =        109
Failure event:   failtype == 1                    No. failed      =         33
Competing event: failtype == 2                    No. competing   =         17
                                                  No. censored    =         59

                                                  Wald chi2(6)    =      44.93
Log pseudolikelihood =    -136.79                 Prob > chi2     =     0.0000

------------------------------------------------------------------------------
             |               Robust
          _t |        SHR   std. err.      z    P>|z|     [95% conf. interval]
-------------+----------------------------------------------------------------
main         |
         ifp |   1.026556   .0179091     1.50   0.133     .9920479    1.062264
     tumsize |   1.460779   .1601932     3.46   0.001     1.178255    1.811047
     pelnode |   .4647006   .2201166    -1.62   0.106     .1836459    1.175886
-------------+----------------------------------------------------------------
tvc          |
         ifp |   1.005606   .0082267     0.68   0.494     .9896103     1.02186
     tumsize |   .8680375   .0789007    -1.56   0.119     .7263871    1.037311
     pelnode |   1.062947   .6033474     0.11   0.914     .3494259    3.233468
------------------------------------------------------------------------------
Note: Variables in tvc equation interacted with _t.

. eststo e2, title("tvc")

. esttab e1

----------------------------
                      (1)   
                       _t   
----------------------------
eq1                         
ifp                0.0327   
                   (1.89)   

tumsize             0.260**
                   (2.66)   

pelnode            -0.779   
                  (-1.81)   
----------------------------
N                     109   
----------------------------
t statistics in parentheses
* p<0.05, ** p<0.01, *** p<0.001

. esttab e2

----------------------------
                      (1)   
                       _t   
----------------------------
main                        
ifp                0.0262   
                   (1.50)   

tumsize             0.379***
                   (3.46)   

pelnode            -0.766   
                  (-1.62)   
----------------------------
tvc                         
ifp               0.00559   
                   (0.68)   

tumsize            -0.142   
                  (-1.56)   

pelnode            0.0610   
                   (0.11)   
----------------------------
N                     109   
----------------------------
t statistics in parentheses
* p<0.05, ** p<0.01, *** p<0.001

. esttab e1 e2
option equations() invalid
specified equation name already occurs in model 2
r(198);

.

[Andrew Musau]

Thanks for the reproducible example. Specify option -equations(1:1)- to match the equations one-to-one.

use https://www.stata-press.com/data/r17/hypoxia, clear
stset dftime, failure(failtype == 1)
stcrreg ifp tumsize pelnode, compete(failtype == 2)
eststo e1, title("cr")
stcrreg ifp tumsize pelnode, compete(failtype == 2) tvc(ifp tumsize pelnode)
eststo e2, title("tvc")
esttab e1 e2, equations(1:1) nomtitles

Res.:

. esttab e1 e2, equations(1:1)  nomtitles

--------------------------------------------
                      (1)             (2)   
--------------------------------------------
#1                                          
ifp                0.0327          0.0262   
                   (1.89)          (1.50)   

tumsize             0.260**         0.379***
                   (2.66)          (3.46)   

pelnode            -0.779          -0.766   
                  (-1.81)         (-1.62)   
--------------------------------------------
tvc                                         
ifp                               0.00559   
                                   (0.68)   

tumsize                            -0.142   
                                  (-1.56)   

pelnode                            0.0610   
                                   (0.11)   
--------------------------------------------
N                     109             109   
--------------------------------------------
t statistics in parentheses
* p<0.05, ** p<0.01, *** p<0.001