Hello everyone!
I am trying to estimate the threshold above which financial development no longer has a positive effect on economic growth in high-income countries and low- and middle-income countries. For this purpose I have data for a financial development indicator called " credit to private sector divided with GDP (prcreditBI; prcreditBI2 is the quadratic term)".
For high income countries simply: 2.48x2=4.96. Then 4.39/4.96=88%
For middle and low income countries: 1) 4.39-4.96=-0.57 2) (2.48-3.46)x2=-1.96 3)-0.57/-1.96=0.29% This answer does not make sense. can somebody help with the reading of the results? Thank you!
Note DML is the dummy variable.
gen PCDML=prcreditBI*DML
gen PCDML2=prcreditBI2*DML
xtabond2 gr lgrowth prcreditBI prcreditBI2 PCDML PCDML2 log_school DML log_trade log_govsize linfl td* if period<10, gmm(L.( lgrowth PCDML2 PCDML prcreditBI2 prcreditBI log_school log_trade log_govsize linfl), lag(. 1)) iv(td*) two robust
Favoring space over speed. To switch, type or click on mata: mata set matafavor speed, perm.
td5 dropped due to collinearity
td10 dropped due to collinearity
td11 dropped due to collinearity
Warning: Number of instruments may be large relative to number of observations.
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: Country_ Number of obs = 670
Time variable : period Number of groups = 118
Number of instruments = 135 Obs per group: min = 1
Wald chi2(18) = 642.00 avg = 5.68
Prob > chi2 = 0.000 max = 9
------------------------------------------------------------------------------
| Corrected
gr | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
lgrowth | -1.042193 .8869841 -1.17 0.240 -2.78065 .6962634
prcreditBI | 4.398982 5.248081 0.84 0.402 -5.887067 14.68503
prcreditBI2 | -2.489592 2.250326 -1.11 0.269 -6.90015 1.920965
PCDML | -4.96543 13.9546 -0.36 0.722 -32.31595 22.38509
PCDML2 | 3.467936 9.394372 0.37 0.712 -14.9447 21.88057
log_school | 1.505725 2.265401 0.66 0.506 -2.934379 5.945829
DML | -1.257265 4.019629 -0.31 0.754 -9.135593 6.621064
log_trade | .9408001 .9842998 0.96 0.339 -.9883921 2.869992
log_govsize | -2.421531 3.164865 -0.77 0.444 -8.624552 3.78149
linfl | -.2981041 .5513516 -0.54 0.589 -1.378733 .7825253
td1 | 2.308894 2.605376 0.89 0.376 -2.797549 7.415337
td2 | 3.171866 2.365166 1.34 0.180 -1.463775 7.807506
td3 | 2.372238 1.642916 1.44 0.149 -.847819 5.592295
td4 | 2.137098 1.145948 1.86 0.062 -.1089182 4.383114
td6 | 1.15655 .9142448 1.27 0.206 -.6353365 2.948437
td7 | .5463423 1.010758 0.54 0.589 -1.434707 2.527392
td8 | .623756 1.377812 0.45 0.651 -2.076707 3.324219
td9 | 1.014286 1.143501 0.89 0.375 -1.226935 3.255508
_cons | 11.07957 8.93006 1.24 0.215 -6.423025 28.58217
------------------------------------------------------------------------------
Instruments for first differences equation
Standard
D.(td1 td2 td3 td4 td5 td6 td7 td8 td9 td10 td11)
GMM-type (missing=0, separate instruments for each period unless collapsed)
L.(L.lgrowth L.PCDML2 L.PCDML L.prcreditBI2 L.prcreditBI L.log_school
L.log_trade L.log_govsize L.linfl)
Instruments for levels equation
Standard
td1 td2 td3 td4 td5 td6 td7 td8 td9 td10 td11
_cons
GMM-type (missing=0, separate instruments for each period unless collapsed)
D.(L.lgrowth L.PCDML2 L.PCDML L.prcreditBI2 L.prcreditBI L.log_school
L.log_trade L.log_govsize L.linfl)
------------------------------------------------------------------------------
Arellano-Bond test for AR(1) in first differences: z = -3.47 Pr > z = 0.001
Arellano-Bond test for AR(2) in first differences: z = -1.21 Pr > z = 0.227
------------------------------------------------------------------------------
Sargan test of overid. restrictions: chi2(116) = 165.25 Prob > chi2 = 0.002
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(116) = 101.67 Prob > chi2 = 0.826
(Robust, but weakened by many instruments.)
Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(53) = 46.96 Prob > chi2 = 0.707
Difference (null H = exogenous): chi2(63) = 54.71 Prob > chi2 = 0.762
iv(td1 td2 td3 td4 td5 td6 td7 td8 td9 td10 td11)
Hansen test excluding group: chi2(108) = 99.54 Prob > chi2 = 0.707
Difference (null H = exogenous): chi2(8) = 2.13 Prob > chi2 = 0.977
I am trying to estimate the threshold above which financial development no longer has a positive effect on economic growth in high-income countries and low- and middle-income countries. For this purpose I have data for a financial development indicator called " credit to private sector divided with GDP (prcreditBI; prcreditBI2 is the quadratic term)".
- First, I divide my full sample of countries based on the World Bank’s classification of income level.
- Second, I add a dummy variable that equals 1 if a country belongs to middle- and low-income country group and 0 otherwise to the regression.
- Third, I interact the dummy variable with both the linear and quadratic terms of financial liquidity variables.
For high income countries simply: 2.48x2=4.96. Then 4.39/4.96=88%
For middle and low income countries: 1) 4.39-4.96=-0.57 2) (2.48-3.46)x2=-1.96 3)-0.57/-1.96=0.29% This answer does not make sense. can somebody help with the reading of the results? Thank you!
Note DML is the dummy variable.
gen PCDML=prcreditBI*DML
gen PCDML2=prcreditBI2*DML
xtabond2 gr lgrowth prcreditBI prcreditBI2 PCDML PCDML2 log_school DML log_trade log_govsize linfl td* if period<10, gmm(L.( lgrowth PCDML2 PCDML prcreditBI2 prcreditBI log_school log_trade log_govsize linfl), lag(. 1)) iv(td*) two robust
Favoring space over speed. To switch, type or click on mata: mata set matafavor speed, perm.
td5 dropped due to collinearity
td10 dropped due to collinearity
td11 dropped due to collinearity
Warning: Number of instruments may be large relative to number of observations.
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: Country_ Number of obs = 670
Time variable : period Number of groups = 118
Number of instruments = 135 Obs per group: min = 1
Wald chi2(18) = 642.00 avg = 5.68
Prob > chi2 = 0.000 max = 9
------------------------------------------------------------------------------
| Corrected
gr | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
lgrowth | -1.042193 .8869841 -1.17 0.240 -2.78065 .6962634
prcreditBI | 4.398982 5.248081 0.84 0.402 -5.887067 14.68503
prcreditBI2 | -2.489592 2.250326 -1.11 0.269 -6.90015 1.920965
PCDML | -4.96543 13.9546 -0.36 0.722 -32.31595 22.38509
PCDML2 | 3.467936 9.394372 0.37 0.712 -14.9447 21.88057
log_school | 1.505725 2.265401 0.66 0.506 -2.934379 5.945829
DML | -1.257265 4.019629 -0.31 0.754 -9.135593 6.621064
log_trade | .9408001 .9842998 0.96 0.339 -.9883921 2.869992
log_govsize | -2.421531 3.164865 -0.77 0.444 -8.624552 3.78149
linfl | -.2981041 .5513516 -0.54 0.589 -1.378733 .7825253
td1 | 2.308894 2.605376 0.89 0.376 -2.797549 7.415337
td2 | 3.171866 2.365166 1.34 0.180 -1.463775 7.807506
td3 | 2.372238 1.642916 1.44 0.149 -.847819 5.592295
td4 | 2.137098 1.145948 1.86 0.062 -.1089182 4.383114
td6 | 1.15655 .9142448 1.27 0.206 -.6353365 2.948437
td7 | .5463423 1.010758 0.54 0.589 -1.434707 2.527392
td8 | .623756 1.377812 0.45 0.651 -2.076707 3.324219
td9 | 1.014286 1.143501 0.89 0.375 -1.226935 3.255508
_cons | 11.07957 8.93006 1.24 0.215 -6.423025 28.58217
------------------------------------------------------------------------------
Instruments for first differences equation
Standard
D.(td1 td2 td3 td4 td5 td6 td7 td8 td9 td10 td11)
GMM-type (missing=0, separate instruments for each period unless collapsed)
L.(L.lgrowth L.PCDML2 L.PCDML L.prcreditBI2 L.prcreditBI L.log_school
L.log_trade L.log_govsize L.linfl)
Instruments for levels equation
Standard
td1 td2 td3 td4 td5 td6 td7 td8 td9 td10 td11
_cons
GMM-type (missing=0, separate instruments for each period unless collapsed)
D.(L.lgrowth L.PCDML2 L.PCDML L.prcreditBI2 L.prcreditBI L.log_school
L.log_trade L.log_govsize L.linfl)
------------------------------------------------------------------------------
Arellano-Bond test for AR(1) in first differences: z = -3.47 Pr > z = 0.001
Arellano-Bond test for AR(2) in first differences: z = -1.21 Pr > z = 0.227
------------------------------------------------------------------------------
Sargan test of overid. restrictions: chi2(116) = 165.25 Prob > chi2 = 0.002
(Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(116) = 101.67 Prob > chi2 = 0.826
(Robust, but weakened by many instruments.)
Difference-in-Hansen tests of exogeneity of instrument subsets:
GMM instruments for levels
Hansen test excluding group: chi2(53) = 46.96 Prob > chi2 = 0.707
Difference (null H = exogenous): chi2(63) = 54.71 Prob > chi2 = 0.762
iv(td1 td2 td3 td4 td5 td6 td7 td8 td9 td10 td11)
Hansen test excluding group: chi2(108) = 99.54 Prob > chi2 = 0.707
Difference (null H = exogenous): chi2(8) = 2.13 Prob > chi2 = 0.977
