Hi experts and researchers,
I am working on a Panel data model using system GMM, xtabond2 command.
I use the interaction terms between Financial development and inflation (fdxihs_inf), Financial development squared and inflation (fdxsqrihs_inf)
Here are the results, I am wondering if it's normal getting high coefficients values of the interaction terms Financial development and inflation (64.64) and Financial development squared and inflation (-64.30876) although they have significant p-values, also AR(2)and Hansen tests values are good!
Commands:
. reg rgdpg ihs_inigdppc fdx ihs_inf ihs_gov ihs_gfcf ihs_trd ihs_lbor
Source | SS df MS Number of obs = 344
-------------+---------------------------------- F(7, 336) = 21.41
Model | 842.761954 7 120.394565 Prob > F = 0.0000
Residual | 1889.01653 336 5.62207301 R-squared = 0.3085
-------------+---------------------------------- Adj R-squared = 0.2941
Total | 2731.77848 343 7.96436876 Root MSE = 2.3711
------------------------------------------------------------------------------
rgdpg | Coefficient Std. err. t P>|t| [95% conf. interval]
-------------+----------------------------------------------------------------
ihs_inigdppc | -.5050419 .2287499 -2.21 0.028 -.9550044 -.0550795
fdx | -2.570679 1.031912 -2.49 0.013 -4.600501 -.5408573
ihs_inf | -.2163242 .1283409 -1.69 0.093 -.4687771 .0361286
ihs_gov | -1.052389 .6752113 -1.56 0.120 -2.380563 .2757845
ihs_gfcf | 4.525075 .6973592 6.49 0.000 3.153335 5.896815
ihs_trd | .6255223 .2538116 2.46 0.014 .1262623 1.124782
ihs_lbor | 1.649964 1.507447 1.09 0.275 -1.315258 4.615187
_cons | -14.97247 8.128953 -1.84 0.066 -30.96252 1.017586
------------------------------------------------------------------------------
. estat vif
Variable | VIF 1/VIF
-------------+----------------------
ihs_inigdppc | 3.27 0.306053
fdx | 2.70 0.369795
ihs_gov | 1.55 0.644058
ihs_inf | 1.46 0.683864
ihs_trd | 1.37 0.729436
ihs_gfcf | 1.26 0.795661
ihs_lbor | 1.16 0.865620
-------------+----------------------
Mean VIF | 1.82
xtabond2 rgdpg ihs_inigdppc_lag1 fdx fdxsqr ihs_inf fdxihs_inf fdxsqrihs_inf ihs_gfcf ihs_gov ihs_trd ihs_lbor y*, gmm (ihs_inigdppc_lag2 fdx_lag1 ihs_inf_lag1 , collapse) iv(fdx_lag2 ihs_inf_lag2 ihs_gfcf ihs_gov ihs_trd ihs_lbor y*, equation(level)) twostep robust small
Favoring speed over space. To switch, type or click on mata: mata set matafavor space, perm.
year dropped due to collinearity
yr_1 dropped due to collinearity
yr_3 dropped due to collinearity
yr_8 dropped due to collinearity
Warning: Two-step estimated covariance matrix of moments is singular.
Using a generalized inverse to calculate optimal weighting matrix for two-step estimation.
Difference-in-Sargan/Hansen statistics may be negative.
Dynamic panel-data estimation, two-step system GMM
------------------------------------------------------------------------------
Group variable: id Number of obs = 258
Time variable : year Number of groups = 43
Number of instruments = 31 Obs per group: min = 6
F(15, 42) = 26.77 avg = 6.00
Prob > F = 0.000 max = 6
-----------------------------------------------------------------------------------
| Corrected
rgdpg | Coefficient std. err. t P>|t| [95% conf. interval]
------------------+----------------------------------------------------------------
ihs_inigdppc_lag1 | 4.268642 3.15253 1.35 0.183 -2.093422 10.63071
fdx | -149.1703 57.26215 -2.61 0.013 -264.73 -33.61061
fdxsqr | 124.0305 45.2724 2.74 0.009 32.66707 215.3939
ihs_inf | -14.47922 4.504356 -3.21 0.003 -23.56938 -5.38906
fdxihs_inf | 64.64833 17.76636 3.64 0.001 28.79437 100.5023
fdxsqrihs_inf | -64.30876 16.47319 -3.90 0.000 -97.55301 -31.06452
ihs_gfcf | 6.826989 4.106349 1.66 0.104 -1.459958 15.11394
ihs_gov | -5.932954 3.309612 -1.79 0.080 -12.61202 .7461137
ihs_trd | -.6892453 1.663613 -0.41 0.681 -4.046551 2.668061
ihs_lbor | -2.684804 6.807573 -0.39 0.695 -16.42304 11.05343
year3 | .0234427 .0583441 0.40 0.690 -.0943004 .1411858
yr_2 | .401837 .5988671 0.67 0.506 -.8067257 1.6104
yr_4 | 1.507502 .5133429 2.94 0.005 .4715338 2.54347
yr_5 | -2.611209 .8814609 -2.96 0.005 -4.390069 -.8323486
yr_6 | -.5894495 .6881631 -0.86 0.397 -1.978219 .7993199
yr_7 | -.5367535 .898236 -0.60 0.553 -2.349467 1.27596
_cons | -35.58086 122.4317 -0.29 0.773 -282.658 211.4963
-----------------------------------------------------------------------------------
Instruments for first differences equation
GMM-type (missing=0, separate instruments for each period unless collapsed)
L(1/7).(ihs_inigdppc_lag2 fdx_lag1 ihs_inf_lag1) collapsed
Instruments for levels equation
Standard
fdx_lag2 ihs_inf_lag2 ihs_gfcf ihs_gov ihs_trd ihs_lbor year3 year yr_1
yr_2 yr_3 yr_4 yr_5 yr_6 yr_7 yr_8
_cons
GMM-type (missing=0, separate instruments for each period unless collapsed)
D.(ihs_inigdppc_lag2 fdx_lag1 ihs_inf_lag1) collapsed
------------------------------------------------------------------------------
Arellano-Bond test for AR(1) in first differences: z = -2.85 Pr > z = 0.004
Arellano-Bond test for AR(2) in first differences: z = 0.54 Pr > z = 0.587
------------------------------------------------------------------------------
Sargan test of overid. restrictions: chi2(14) = 27.46 Prob > chi2 = 0.017
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(14) = 19.04 Prob > chi2 = 0.163
(Robust, but weakened by many instruments.)
Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(12) = 15.65 Prob > chi2 = 0.208
Difference (null H = exogenous): chi2(2) = 3.39 Prob > chi2 = 0.184
iv(fdx_lag2 ihs_inf_lag2 ihs_gfcf ihs_gov ihs_trd ihs_lbor year3 year yr_1 yr_2 yr_3 yr_4 yr_5 yr_6 yr_7 yr_8, eq(level))
Hansen test excluding group: chi2(2) = 2.64 Prob > chi2 = 0.267
Difference (null H = exogenous): chi2(12) = 16.40 Prob > chi2 = 0.174
1- how can I make the values of the coefficients less than 1, please?
2- After system GMM I want to measure the marginal effect of the variable FDX on GDP ( continuous variables) and represent it on a graph with STATA, what is the command please?
I would be very grateful for any help
Regards
Badiah
I am working on a Panel data model using system GMM, xtabond2 command.
I use the interaction terms between Financial development and inflation (fdxihs_inf), Financial development squared and inflation (fdxsqrihs_inf)
Here are the results, I am wondering if it's normal getting high coefficients values of the interaction terms Financial development and inflation (64.64) and Financial development squared and inflation (-64.30876) although they have significant p-values, also AR(2)and Hansen tests values are good!
Commands:
. reg rgdpg ihs_inigdppc fdx ihs_inf ihs_gov ihs_gfcf ihs_trd ihs_lbor
Source | SS df MS Number of obs = 344
-------------+---------------------------------- F(7, 336) = 21.41
Model | 842.761954 7 120.394565 Prob > F = 0.0000
Residual | 1889.01653 336 5.62207301 R-squared = 0.3085
-------------+---------------------------------- Adj R-squared = 0.2941
Total | 2731.77848 343 7.96436876 Root MSE = 2.3711
------------------------------------------------------------------------------
rgdpg | Coefficient Std. err. t P>|t| [95% conf. interval]
-------------+----------------------------------------------------------------
ihs_inigdppc | -.5050419 .2287499 -2.21 0.028 -.9550044 -.0550795
fdx | -2.570679 1.031912 -2.49 0.013 -4.600501 -.5408573
ihs_inf | -.2163242 .1283409 -1.69 0.093 -.4687771 .0361286
ihs_gov | -1.052389 .6752113 -1.56 0.120 -2.380563 .2757845
ihs_gfcf | 4.525075 .6973592 6.49 0.000 3.153335 5.896815
ihs_trd | .6255223 .2538116 2.46 0.014 .1262623 1.124782
ihs_lbor | 1.649964 1.507447 1.09 0.275 -1.315258 4.615187
_cons | -14.97247 8.128953 -1.84 0.066 -30.96252 1.017586
------------------------------------------------------------------------------
. estat vif
Variable | VIF 1/VIF
-------------+----------------------
ihs_inigdppc | 3.27 0.306053
fdx | 2.70 0.369795
ihs_gov | 1.55 0.644058
ihs_inf | 1.46 0.683864
ihs_trd | 1.37 0.729436
ihs_gfcf | 1.26 0.795661
ihs_lbor | 1.16 0.865620
-------------+----------------------
Mean VIF | 1.82
xtabond2 rgdpg ihs_inigdppc_lag1 fdx fdxsqr ihs_inf fdxihs_inf fdxsqrihs_inf ihs_gfcf ihs_gov ihs_trd ihs_lbor y*, gmm (ihs_inigdppc_lag2 fdx_lag1 ihs_inf_lag1 , collapse) iv(fdx_lag2 ihs_inf_lag2 ihs_gfcf ihs_gov ihs_trd ihs_lbor y*, equation(level)) twostep robust small
Favoring speed over space. To switch, type or click on mata: mata set matafavor space, perm.
year dropped due to collinearity
yr_1 dropped due to collinearity
yr_3 dropped due to collinearity
yr_8 dropped due to collinearity
Warning: Two-step estimated covariance matrix of moments is singular.
Using a generalized inverse to calculate optimal weighting matrix for two-step estimation.
Difference-in-Sargan/Hansen statistics may be negative.
Dynamic panel-data estimation, two-step system GMM
------------------------------------------------------------------------------
Group variable: id Number of obs = 258
Time variable : year Number of groups = 43
Number of instruments = 31 Obs per group: min = 6
F(15, 42) = 26.77 avg = 6.00
Prob > F = 0.000 max = 6
-----------------------------------------------------------------------------------
| Corrected
rgdpg | Coefficient std. err. t P>|t| [95% conf. interval]
------------------+----------------------------------------------------------------
ihs_inigdppc_lag1 | 4.268642 3.15253 1.35 0.183 -2.093422 10.63071
fdx | -149.1703 57.26215 -2.61 0.013 -264.73 -33.61061
fdxsqr | 124.0305 45.2724 2.74 0.009 32.66707 215.3939
ihs_inf | -14.47922 4.504356 -3.21 0.003 -23.56938 -5.38906
fdxihs_inf | 64.64833 17.76636 3.64 0.001 28.79437 100.5023
fdxsqrihs_inf | -64.30876 16.47319 -3.90 0.000 -97.55301 -31.06452
ihs_gfcf | 6.826989 4.106349 1.66 0.104 -1.459958 15.11394
ihs_gov | -5.932954 3.309612 -1.79 0.080 -12.61202 .7461137
ihs_trd | -.6892453 1.663613 -0.41 0.681 -4.046551 2.668061
ihs_lbor | -2.684804 6.807573 -0.39 0.695 -16.42304 11.05343
year3 | .0234427 .0583441 0.40 0.690 -.0943004 .1411858
yr_2 | .401837 .5988671 0.67 0.506 -.8067257 1.6104
yr_4 | 1.507502 .5133429 2.94 0.005 .4715338 2.54347
yr_5 | -2.611209 .8814609 -2.96 0.005 -4.390069 -.8323486
yr_6 | -.5894495 .6881631 -0.86 0.397 -1.978219 .7993199
yr_7 | -.5367535 .898236 -0.60 0.553 -2.349467 1.27596
_cons | -35.58086 122.4317 -0.29 0.773 -282.658 211.4963
-----------------------------------------------------------------------------------
Instruments for first differences equation
GMM-type (missing=0, separate instruments for each period unless collapsed)
L(1/7).(ihs_inigdppc_lag2 fdx_lag1 ihs_inf_lag1) collapsed
Instruments for levels equation
Standard
fdx_lag2 ihs_inf_lag2 ihs_gfcf ihs_gov ihs_trd ihs_lbor year3 year yr_1
yr_2 yr_3 yr_4 yr_5 yr_6 yr_7 yr_8
_cons
GMM-type (missing=0, separate instruments for each period unless collapsed)
D.(ihs_inigdppc_lag2 fdx_lag1 ihs_inf_lag1) collapsed
------------------------------------------------------------------------------
Arellano-Bond test for AR(1) in first differences: z = -2.85 Pr > z = 0.004
Arellano-Bond test for AR(2) in first differences: z = 0.54 Pr > z = 0.587
------------------------------------------------------------------------------
Sargan test of overid. restrictions: chi2(14) = 27.46 Prob > chi2 = 0.017
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(14) = 19.04 Prob > chi2 = 0.163
(Robust, but weakened by many instruments.)
Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(12) = 15.65 Prob > chi2 = 0.208
Difference (null H = exogenous): chi2(2) = 3.39 Prob > chi2 = 0.184
iv(fdx_lag2 ihs_inf_lag2 ihs_gfcf ihs_gov ihs_trd ihs_lbor year3 year yr_1 yr_2 yr_3 yr_4 yr_5 yr_6 yr_7 yr_8, eq(level))
Hansen test excluding group: chi2(2) = 2.64 Prob > chi2 = 0.267
Difference (null H = exogenous): chi2(12) = 16.40 Prob > chi2 = 0.174
1- how can I make the values of the coefficients less than 1, please?
2- After system GMM I want to measure the marginal effect of the variable FDX on GDP ( continuous variables) and represent it on a graph with STATA, what is the command please?
I would be very grateful for any help
Regards
Badiah
