xtivreg2* (factor-variable operators not allowed)

[hussein bataineh]

Hi, im new in using STATA

im trying to use xtivreg2 and control for time at the same time by using i.year im facing problem as it give me (factor-variable operators not allowed)

How can i solve this problem

. ssc install xtivreg2, replace
checking xtivreg2 consistency and verifying not already installed...
all files already exist and are up to date.

. xtivreg2 EQUITY CSO  FSIZE OP_CF SD_OCF TAX   BM LEV MA DPP RPP PSIZE   DR  Gov_score Sustain_Perf Sust_Commit   i.year (CSO = Instrumental),  fe  robust
factor-variable operators not allowed
r(101);

[George Ford]

tab year , generate(yr)
then add yr* as regressors

[George Ford]

look at ivreghdfe too.

ssc install ivreghdfe

[hussein bataineh]

Thanks George

plesae i did what you suggested

but it give me

Warning - singleton groups detected. 7 observation(s) not used.
Warning - duplicate variables detected
Duplicates: CSO
Warning - collinearities detected
Vars dropped: yr19


please what you sugeest i used ivreghdfe but the result was bad totally different than my the main regression

xtivreg2 EQUITY CSO  FSIZE OP_CF SD_OCF TAX   BM LEV MA DPP RPP PSIZE   DR  Gov_score Sustain_Perf Sust_Commit   yr*  (CSO = Instrumental),  fe  robust
Warning - singleton groups detected.  7 observation(s) not used.
Warning - duplicate variables detected
Duplicates:         CSO
Warning - collinearities detected
Vars dropped:       yr19

FIXED EFFECTS ESTIMATION
------------------------
Number of groups =       281                    Obs per group: min =         2
                                                               avg =      14.4
                                                               max =        19
Warning - duplicate variables detected
Duplicates:    CSO
Warning - collinearities detected
Vars dropped:  yr19

OLS estimation
--------------

Estimates efficient for homoskedasticity only
Statistics robust to heteroskedasticity

                                                      Number of obs =     4044
                                                      F( 33,  3730) =    86.67
                                                      Prob > F      =   0.0000
Total (centered) SS     =  84.86900113                Centered R2   =   0.4795
Total (uncentered) SS   =  84.86900113                Uncentered R2 =   0.4795
Residual SS             =  44.17832177                Root MSE      =    .1084

------------------------------------------------------------------------------
             |               Robust
      EQUITY | Coefficient  std. err.      z    P>|z|     [95% conf. interval]
-------------+----------------------------------------------------------------
         CSO |  -.0245001   .0061191    -4.00   0.000    -.0364933    -.012507
       FSIZE |   .0088576   .0077466     1.14   0.253    -.0063254    .0240406
       OP_CF |  -.0483011    .061843    -0.78   0.435     -.169511    .0729089
      SD_OCF |  -.3418531   .1272211    -2.69   0.007    -.5912019   -.0925043
         TAX |  -.0103754   .0072893    -1.42   0.155    -.0246622    .0039114
          BM |  -.0197849   .0115391    -1.71   0.086    -.0424011    .0028313
         LEV |  -.0372171   .0293147    -1.27   0.204    -.0946729    .0202386
          MA |   .0062033   .0148769     0.42   0.677    -.0229549    .0353615
         DPP |   .1404479   .0252074     5.57   0.000     .0910422    .1898535
         RPP |   .1150126   .0316234     3.64   0.000     .0530318    .1769934
       PSIZE |   .0144853   .0083952     1.73   0.084    -.0019689    .0309396
          DR |   .0432099   .0069073     6.26   0.000     .0296719    .0567478
   Gov_score |  -.0000846   .0001207    -0.70   0.483    -.0003211    .0001519
Sustain_Perf |   -.000248   .0001865    -1.33   0.183    -.0006135    .0001174
 Sust_Commit |  -.0082043   .0063486    -1.29   0.196    -.0206473    .0042387
         yr1 |   .2679397   .0284086     9.43   0.000       .21226    .3236194
         yr2 |   .2690732   .0263761    10.20   0.000     .2173771    .3207693
         yr3 |   .2544232    .026361     9.65   0.000     .2027566    .3060898
         yr4 |   .2213576   .0258864     8.55   0.000     .1706212     .272094
         yr5 |   .1762084   .0238107     7.40   0.000     .1295402    .2228766
         yr6 |   .1643163   .0250262     6.57   0.000      .115266    .2133667
         yr7 |   .1842541   .0243775     7.56   0.000     .1364751     .232033
         yr8 |   .1758366   .0228243     7.70   0.000     .1311019    .2205713
         yr9 |   .1845816   .0242418     7.61   0.000     .1370686    .2320946
        yr10 |   .1536788    .023142     6.64   0.000     .1083213    .1990362
        yr11 |   .1567697   .0239015     6.56   0.000     .1099237    .2036158
        yr12 |   .1440244   .0221715     6.50   0.000      .100569    .1874798
        yr13 |   .1423335   .0236824     6.01   0.000     .0959168    .1887502
        yr14 |   .1302711   .0248925     5.23   0.000     .0814826    .1790595
        yr15 |   .0714838   .0220454     3.24   0.001     .0282756    .1146921
        yr16 |   .0887847   .0265665     3.34   0.001     .0367152    .1408542
        yr17 |   .1153496    .028267     4.08   0.000     .0599473    .1707518
        yr18 |   .0723285   .0271801     2.66   0.008     .0190564    .1256006
        yr19 |          0  (omitted)
------------------------------------------------------------------------------
Hansen J statistic (overidentification test of all instruments):         7.084
                                                   Chi-sq(1) P-val =    0.0078
------------------------------------------------------------------------------
Included instruments: CSO FSIZE OP_CF SD_OCF TAX BM LEV MA DPP RPP PSIZE DR
                      Gov_score Sustain_Perf Sust_Commit yr1 yr2 yr3 yr4 yr5 yr6
                      yr7 yr8 yr9 yr10 yr11 yr12 yr13 yr14 yr15 yr16 yr17 yr18
Excluded instruments: Instrumental
Duplicates:           CSO
Dropped collinear:    yr19
------------------------------------------------------------------------------

. 
end of do-file

[George Ford]

*Warning - singleton groups detected. 7 observation(s) not used. You've perfectly predicted 7 observations with your X's. It happens. Figure out why; but it may not be a problem. It's probably some groups having only 2 years of data. *Warning - duplicate variables detected *Duplicates: CSO Drop CSO as a regressor. It is being treated as endogenous. *Warning - collinearities detected *Vars dropped: yr19 Not a problem. Just avoiding the dummy trap. You could say yr2-yr19 in place of yr*.

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

[hussein bataineh]

Thank you very much George for Gudance and support

plesae i have two enquires if you can advice me on how to solve them

1. i want to identify this singleton groups detected. 7 observation(s) so i can delete them in order to have same same number of observations in main regression and 2SLS
2. the Endogeneity test does not appear for me , I'm not sure why , is this is because of singleton groups and is there a way to display the Endogeneity test results

.  ivreghdfe EQUITY FSIZE OP_CF SD_OCF TAX  BM LEV MA DPP RPP PSIZE DR Gov_score Sustain_Perf Sust_Commit (CSO = Instrumental), first absorb(id year) robust
(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 =                   4044
------------------------------------------------------------------------------
             |               Robust
         CSO | Coefficient  std. err.      t    P>|t|     [95% conf. interval]
-------------+----------------------------------------------------------------
Instrumental |   .0156519   .0025056     6.25   0.000     .0107394    .0205644
       FSIZE |    .008078   .0195748     0.41   0.680    -.0303003    .0464563
       OP_CF |  -.0828493   .1580706    -0.52   0.600    -.3927627     .227064
      SD_OCF |   1.446089   .3084335     4.69   0.000     .8413738    2.050804
         TAX |   .0273629   .0207085     1.32   0.186    -.0132381    .0679639
          BM |  -.0247828   .0320633    -0.77   0.440    -.0876462    .0380806
         LEV |   .1534906   .0765237     2.01   0.045     .0034582     .303523
          MA |  -.0171832    .039259    -0.44   0.662    -.0941545     .059788
         DPP |  -.0248049   .0594157    -0.42   0.676    -.1412954    .0916856
         RPP |  -.1013338   .0869353    -1.17   0.244    -.2717791    .0691115
       PSIZE |   .0500369   .0181621     2.76   0.006     .0144282    .0856456
          DR |  -.0142629   .0173658    -0.82   0.412    -.0483102    .0197845
   Gov_score |   .0003102    .000337     0.92   0.357    -.0003506    .0009709
Sustain_Perf |   .0011279   .0005123     2.20   0.028     .0001236    .0021322
 Sust_Commit |   .0079999   .0161499     0.50   0.620    -.0236636    .0396634
------------------------------------------------------------------------------
F test of excluded instruments:
  F(  1,  3730) =    39.02
  Prob > F      =   0.0000
Sanderson-Windmeijer multivariate F test of excluded instruments:
  F(  1,  3730) =    39.02
  Prob > F      =   0.0000



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

                                           (Underid)            (Weak id)
Variable     | F(  1,  3730)  P-val | SW Chi-sq(  1) P-val | SW F(  1,  3730)
CSO          |      39.02    0.0000 |       42.31   0.0000 |       39.02

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)=41.78    P-val=0.0000

Weak identification test
Ho: equation is weakly identified
Cragg-Donald Wald F statistic                                      52.18
Kleibergen-Paap Wald rk F statistic                                39.02

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(1,3730)=      9.36     P-val=0.0022
Anderson-Rubin Wald test           Chi-sq(1)=     10.14     P-val=0.0014
Stock-Wright LM S statistic        Chi-sq(1)=     10.30     P-val=0.0013

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

Number of observations               N  =       4044
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 =     4044
                                                      F( 15,  3730) =     7.52
                                                      Prob > F      =   0.0000
Total (centered) SS     =  46.32975885                Centered R2   =  -0.1074
Total (uncentered) SS   =  46.32975885                Uncentered R2 =  -0.1074
Residual SS             =  51.30371339                Root MSE      =    .1173

------------------------------------------------------------------------------
             |               Robust
      EQUITY | Coefficient  std. err.      t    P>|t|     [95% conf. interval]
-------------+----------------------------------------------------------------
         CSO |  -.1729897   .0609084    -2.84   0.005    -.2924066   -.0535728
       FSIZE |   .0123795   .0083681     1.48   0.139     -.004027    .0287859
       OP_CF |     -.0683   .0678452    -1.01   0.314    -.2013172    .0647173
      SD_OCF |  -.1461356   .1548982    -0.94   0.346     -.449829    .1575579
         TAX |  -.0058738   .0080836    -0.73   0.467    -.0217225    .0099749
          BM |  -.0258302   .0125445    -2.06   0.040    -.0504249   -.0012355
         LEV |   -.020226   .0329623    -0.61   0.540    -.0848519    .0443999
          MA |   .0038532   .0151436     0.25   0.799    -.0258374    .0335438
         DPP |   .1396388    .025668     5.44   0.000     .0893142    .1899635
         RPP |   .0998273   .0365839     2.73   0.006     .0281009    .1715537
       PSIZE |   .0209352   .0093783     2.23   0.026     .0025481    .0393223
          DR |   .0404173   .0074463     5.43   0.000     .0258182    .0550165
   Gov_score |  -.0000358   .0001305    -0.27   0.784    -.0002918    .0002201
Sustain_Perf |   -.000039    .000214    -0.18   0.855    -.0004586    .0003806
 Sust_Commit |  -.0079053   .0067824    -1.17   0.244     -.021203    .0053923
------------------------------------------------------------------------------
Underidentification test (Kleibergen-Paap rk LM statistic):             41.775
                                                   Chi-sq(1) P-val =    0.0000
------------------------------------------------------------------------------
Weak identification test (Cragg-Donald Wald F statistic):               52.182
                         (Kleibergen-Paap rk Wald F statistic):         39.022
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)
------------------------------------------------------------------------------
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: Instrumental
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 |       281           0         281     |
        year |        19           1          18     |
-----------------------------------------------------+

[George Ford]

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

the resid option produces _reghdfe_resid. Look for missing values, which are the excluded observations.

[hussein bataineh]

please Prof George

i tried to run the code but unfortunately , it give me

  ivreghdfe EQUITY FSIZE OP_CF SD_OCF TAX  BM LEV MA DPP RPP PSIZE DR Gov_score Sustain_Perf Sust_Commit (CSO = Instrumental), first absorb(id year) cluster(id) resid endog(CSO)
option resid not allowed

[George Ford]

hmm. no problems at my end with it.

try

ssc install reghdfe, replace

[George Ford]

might try reghdfe, include CSO, and see if you get the same number of singularities.

[Jeff Wooldridge]

Hussein: You haven't properly specified "resid." It's supposed to be something like resid(uhat).

[George Ford]

with reghdfe or ivreghdfe, if you just put in resid alone, then it produces _reghdfe_resid as the resid. but you can name them, say uhat as Jeff suggests.

[hussein bataineh]

Please professor

when i try to see the the residual it work for ivreghdfe but when i try to do it for xtivreg2 it does not work , can you guide me how can i identify residual for xtivreg2

This is the code i used for ivreghdfe


qui: 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) endog(CSO) resid
predict resid1, residuals

This is the code i used for xtivreg2

xtset id year
ssc install xtivreg2, replace
tab year , generate(yr)

qui: xtivreg2 EQUITY FSIZE OP_CF SD_OCF TAX BM LEV MA DPP RPP PSIZE DR Gov_score Sustain_Perf Sust_Commit yr2-yr19 (CSO = Instrumental), fe first endog(CSO) resid
predict resid1, residuals

 . . qui: xtivreg2 EQUITY   FSIZE OP_CF SD_OCF TAX   BM LEV MA DPP RPP PSIZE   DR  Gov_score Sustain_Perf Sust_Commit   yr2-yr19 (CSO = Inst
> rumental),  fe first  endog(CSO) resid
option resid not allowed
r(198);

end of do-file

r(198);

[George Ford]

after xtivreg2, you should be able to

predict uhat, residuals

or, you could try

list id year if !e(sample)

[hussein bataineh]

Please professor do you have any note why it wok for ivreghdfe but not to xtivreg2