constant in 2SLS using ivreghdfe

[hussein bataineh]

please i need to run 2SLS with firm fixed effect and year fixed effect. scholar suggest to use ivreghdfe code

ivreghdfe EQUITY FSIZE OP_CF SD_OCF TAX BM LEV MA DPP RPP PSIZE DR Gov_score Sustain_Perf Sust_Commit (CSO = CSO_Percentage), first absorb(id year) robust endog(CSO)


the problem that the constant is not appear in the regression .Can you advice me where is the problem and how can i solve it ?

Thanks alot

 ivreghdfe EQUITY FSIZE OP_CF SD_OCF TAX  BM LEV MA DPP RPP PSIZE DR Gov_score Sustain_Perf Sust_Commit  (CSO = CSO_Percentage), first absorb(id year) robust  endog(CSO)
(dropped 7 singleton observations)
(MWFE estimator converged in 7 iterations)

First-stage regressions
-----------------------


First-stage regression of CSO:

Statistics robust to heteroskedasticity
Number of obs =                   4181
--------------------------------------------------------------------------------
               |               Robust
           CSO | Coefficient  std. err.      t    P>|t|     [95% conf. interval]
---------------+----------------------------------------------------------------
CSO_Percentage |   1.186504   .0821453    14.44   0.000     1.025451    1.347556
         FSIZE |   .0213839   .0182422     1.17   0.241    -.0143815    .0571492
         OP_CF |  -.2299433   .1500126    -1.53   0.125    -.5240549    .0641684
        SD_OCF |   1.339969   .2911594     4.60   0.000     .7691282     1.91081
           TAX |   .0201922   .0190697     1.06   0.290    -.0171955    .0575799
            BM |  -.0550446   .0301754    -1.82   0.068    -.1142058    .0041166
           LEV |   .0471235   .0717561     0.66   0.511      -.09356     .187807
            MA |  -.0166494   .0378968    -0.44   0.660    -.0909491    .0576503
           DPP |  -.0296341   .0541658    -0.55   0.584    -.1358306    .0765623
           RPP |  -.0905304   .0767933    -1.18   0.239    -.2410899     .060029
         PSIZE |   .0504669   .0165391     3.05   0.002     .0180406    .0828932
            DR |  -.0058747   .0156901    -0.37   0.708    -.0366365    .0248871
     Gov_score |   .0002265   .0003204     0.71   0.480    -.0004017    .0008547
  Sustain_Perf |   .0009879   .0004888     2.02   0.043     .0000295    .0019463
   Sust_Commit |   .0048192   .0158254     0.30   0.761    -.0262077    .0358462
--------------------------------------------------------------------------------
F test of excluded instruments:
  F(  1,  3854) =   208.63
  Prob > F      =   0.0000
Sanderson-Windmeijer multivariate F test of excluded instruments:
  F(  1,  3854) =   208.63
  Prob > F      =   0.0000



Summary results for first-stage regressions
-------------------------------------------

                                           (Underid)            (Weak id)
Variable     | F(  1,  3854)  P-val | SW Chi-sq(  1) P-val | SW F(  1,  3854)
CSO          |     208.63    0.0000 |      226.33   0.0000 |      208.63

NB: first-stage test statistics heteroskedasticity-robust

Stock-Yogo weak ID F test critical values for single endogenous regressor:
                                   10% maximal IV size             16.38
                                   15% maximal IV size              8.96
                                   20% maximal IV size              6.66
                                   25% maximal IV size              5.53
Source: Stock-Yogo (2005).  Reproduced by permission.
NB: Critical values are for i.i.d. errors only.

Underidentification test
Ho: matrix of reduced form coefficients has rank=K1-1 (underidentified)
Ha: matrix has rank=K1 (identified)
Kleibergen-Paap rk LM statistic          Chi-sq(1)=178.63   P-val=0.0000

Weak identification test
Ho: equation is weakly identified
Cragg-Donald Wald F statistic                                     220.80
Kleibergen-Paap Wald rk F statistic                               208.63

Stock-Yogo weak ID test critical values for K1=1 and L1=1:
                                   10% maximal IV size             16.38
                                   15% maximal IV size              8.96
                                   20% maximal IV size              6.66
                                   25% maximal IV size              5.53
Source: Stock-Yogo (2005).  Reproduced by permission.
NB: Critical values are for Cragg-Donald F statistic and i.i.d. errors.

Weak-instrument-robust inference
Tests of joint significance of endogenous regressors B1 in main equation
Ho: B1=0 and orthogonality conditions are valid
Anderson-Rubin Wald test           F(1,3854)=     10.35     P-val=0.0013
Anderson-Rubin Wald test           Chi-sq(1)=     11.23     P-val=0.0008
Stock-Wright LM S statistic        Chi-sq(1)=     11.23     P-val=0.0008

NB: Underidentification, weak identification and weak-identification-robust
    test statistics heteroskedasticity-robust

Number of observations               N  =       4181
Number of regressors                 K  =         15
Number of endogenous regressors      K1 =          1
Number of instruments                L  =         15
Number of excluded instruments       L1 =          1

IV (2SLS) estimation
--------------------

Estimates efficient for homoskedasticity only
Statistics robust to heteroskedasticity

                                                      Number of obs =     4181
                                                      F( 15,  3854) =     8.19
                                                      Prob > F      =   0.0000
Total (centered) SS     =  48.43091059                Centered R2   =   0.0114
Total (uncentered) SS   =  48.43091059                Uncentered R2 =   0.0114
Residual SS             =  47.87789735                Root MSE      =    .1115

------------------------------------------------------------------------------
             |               Robust
      EQUITY | Coefficient  std. err.      t    P>|t|     [95% conf. interval]
-------------+----------------------------------------------------------------
         CSO |  -.0892582    .028242    -3.16   0.002    -.1446289   -.0338875
       FSIZE |   .0107465   .0078442     1.37   0.171    -.0046327    .0261257
       OP_CF |  -.0650899   .0626089    -1.04   0.299    -.1878396    .0576597
      SD_OCF |  -.2200024   .1347572    -1.63   0.103    -.4842046    .0441999
         TAX |  -.0098609   .0073923    -1.33   0.182    -.0243541    .0046323
          BM |  -.0211888   .0116607    -1.82   0.069    -.0440505    .0016729
         LEV |  -.0290775   .0296273    -0.98   0.326    -.0871641    .0290091
          MA |   .0067771    .014232     0.48   0.634    -.0211258      .03468
         DPP |   .1312567   .0239277     5.49   0.000     .0843445    .1781689
         RPP |   .1006525   .0315921     3.19   0.001     .0387137    .1625914
       PSIZE |   .0175778   .0085408     2.06   0.040      .000833    .0343227
          DR |   .0389498   .0067774     5.75   0.000     .0256621    .0522375
   Gov_score |  -.0000623   .0001213    -0.51   0.608       -.0003    .0001755
Sustain_Perf |   -.000138    .000195    -0.71   0.479    -.0005203    .0002443
 Sust_Commit |   -.007984   .0063319    -1.26   0.207    -.0203982    .0044303
------------------------------------------------------------------------------
Underidentification test (Kleibergen-Paap rk LM statistic):            178.632
                                                   Chi-sq(1) P-val =    0.0000
------------------------------------------------------------------------------
Weak identification test (Cragg-Donald Wald F statistic):              220.804
                         (Kleibergen-Paap rk Wald F statistic):        208.628
Stock-Yogo weak ID test critical values: 10% maximal IV size             16.38
                                         15% maximal IV size              8.96
                                         20% maximal IV size              6.66
                                         25% maximal IV size              5.53
Source: Stock-Yogo (2005).  Reproduced by permission.
NB: Critical values are for Cragg-Donald F statistic and i.i.d. errors.
------------------------------------------------------------------------------
Hansen J statistic (overidentification test of all instruments):         0.000
                                                 (equation exactly identified)
-endog- option:
Endogeneity test of endogenous regressors:                               6.597
                                                   Chi-sq(1) P-val =    0.0102
Regressors tested:    CSO
------------------------------------------------------------------------------
Instrumented:         CSO
Included instruments: FSIZE OP_CF SD_OCF TAX BM LEV MA DPP RPP PSIZE DR
                      Gov_score Sustain_Perf Sust_Commit
Excluded instruments: CSO_Percentage
Partialled-out:       _cons
                      nb: total SS, model F and R2s are after partialling-out;
                          any small-sample adjustments include partialled-out
                          variables in regressor count K
------------------------------------------------------------------------------

Absorbed degrees of freedom:
-----------------------------------------------------+
 Absorbed FE | Categories  - Redundant  = Num. Coefs |
-------------+---------------------------------------|
          id |       294           0         294     |
        year |        19           1          18     |
-----------------------------------------------------+

[George Ford]

It's fixed effects. constant doesn't really mean anything, so is left out.

you can retrieve the fixed effects.

[hussein bataineh]

Thanks you very much for your clarification

Actually the supervisor ask to added the constant

Could you please advice me if these is a way to display the constant

thanks a lot

[George Ford]

I'd ask him why, since it is left off because it is meaningless. in reghdfe, it is the fixed effect of the 1st id.

If you must, use ivreg2 and include i.year as a covariate.

sysuse auto, clear

 ivreghdfe price weight (length=gear), absorb(rep78, savefe) tol(1e-6)
 summ __hdfe1__ if rep78==1
 
 ivreg2 price weight i.rep78 (length=gear)

[hussein bataineh]

please professor if we use If we use ivreg2 and include i.year as a covariate.. we just includes year fixed effect and we do not include firm fixed effect that is control in our ivreghdfe model

ivreghdfe EQUITY FSIZE OP_CF SD_OCF TAX BM LEV MA DPP RPP PSIZE DR Gov_score Sustain_Perf Sust_Commit (CSO = CSO_Percentage), first absorb(id year) robust endog(CSO)

can we include include i.year and i.id as a covariat?

can you give me advice related to this please?

[George Ford]

sorry. include i.id. the SE won't be the same in this model, but you'll get a constant term.

I'd tell you to use xtivreg2, but it also does not report the meaningless constant term.

I'd recommend fighting your advisor on this one. Maybe show the results of this exercise.

sysuse auto, clear

 ivreghdfe price weight (length=gear), absorb(rep78, savefe) tol(1e-6)
 summ __hdfe1__ if rep78==1
 
ivreg2 price weight b1.rep78 (length=gear)
ivreg2 price weight b2.rep78 (length=gear)
ivreg2 price weight b3.rep78 (length=gear)
ivreg2 price weight b4.rep78 (length=gear)
ivreg2 price weight b5.rep78 (length=gear)

[hussein bataineh]

Thanks professor for your explanation