I am new to xtabond2 I don't know to write the proper codes for my study. I would like to study profitability determinants of banks. My data is balanced panel data for 7 years, and 12 banks. It is small T, large N.
Variables:
Dependent: ROAA
Endogenous variable: L.ROAA, CAPAD ( using-two year lags), LIQ ( using-one year lag, as predetermined)
Explanatory: SIZE DEP COST AM
Control: GDPG INF EXCH HHI
Internal Instruments: L.ROAA CAPAD LIQ
External Instruments: SIZE DEP MOST AM GDPG INF EXCH HHI
I am confused how to write the codes.
I studied Roodman 2009, and Sebastian Kripfganz 2019, but it didn't work I am totally lost about the difference between equation(diff) and equation(level). As far as my understanding from some sources, endogenous, predetermined and lag of dependent variables should be written in gmmstyle(), and strictly exogenous variables should be written in IVstyle().
N of my study is 12, I think it would be also problem, however, I would like to know how to write the codes for the study.
you can see the codes and output below:
I think I am wrong, however could you please guide me to the right direction.
Code:
. xtabond2 ROAA L.ROAA SIZE CAPAD DEP COST LIQ AM INF GDPG EXCH HHI, gmm(l.ROAA CAPAD SIZE COS > T, lag(0 0)eq(diff)collapse) gmm(l.ROAA CAPAD SIZE COST, lag(1 1)eq(level) collapse) iv(INF > GDPG EXCH, eq(level))nodiffsargan twostep robust small
HTML Code:
Dynamic panel-data estimation, two-step system GMM ------------------------------------------------------------------------------ Group variable: ID Number of obs = 72 Time variable : Year Number of groups = 12 Number of instruments = 12 Obs per group: min = 6 F(11, 11) = 425.98 avg = 6.00 Prob > F = 0.000 max = 6 ------------------------------------------------------------------------------ | Corrected ROAA | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- ROAA | L1. | -.0431055 .1986861 -0.22 0.832 -.4804107 .3941997 | SIZE | .1886509 .7227992 0.26 0.799 -1.402219 1.779521 CAPAD | -.0207815 .0878616 -0.24 0.817 -.2141635 .1726006 DEP | -.1087718 .2707801 -0.40 0.696 -.7047547 .4872111 COST | -.9433091 .2415284 -3.91 0.002 -1.474909 -.4117087 LIQ | .055603 .1581725 0.35 0.732 -.2925323 .4037382 AM | 1.064814 .3336382 3.19 0.009 .3304808 1.799146 INF | -.0320222 .0692305 -0.46 0.653 -.1843975 .1203531 GDPG | .0762658 .2876441 0.27 0.796 -.5568345 .7093661 EXCH | -.0689804 .094458 -0.73 0.480 -.2768812 .1389203 HHI | 0 (omitted) _cons | 4.710788 10.65545 0.44 0.667 -18.74169 28.16327 ------------------------------------------------------------------------------ Instruments for first differences equation GMM-type (missing=0, separate instruments for each period unless collapsed) .(L.ROAA CAPAD SIZE COST) collapsed Instruments for levels equation Standard INF GDPG EXCH _cons GMM-type (missing=0, separate instruments for each period unless collapsed) DL.(L.ROAA CAPAD SIZE COST) collapsed ------------------------------------------------------------------------------ Arellano-Bond test for AR(1) in first differences: z = -0.83 Pr > z = 0.404 Arellano-Bond test for AR(2) in first differences: z = -0.47 Pr > z = 0.642 ------------------------------------------------------------------------------ Sargan test of overid. restrictions: chi2(0) = 0.00 Prob > chi2 = . (Not robust, but not weakened by many instruments.) Hansen test of overid. restrictions: chi2(0) = 0.00 Prob > chi2 = . (Robust, but weakened by many instruments.)
0 Response to xtabond2 for System GMM code writing problem
Post a Comment