I am using Stata 13 and run xtabond2. When running xtabond2 with nocons option, no Wald Chi 2 result is produced. If a constant is included, a Wald Chi 2 statistic is included in the output.
After reading the Stata help, the paper How to do Xtabond2: An Introduction to Difference and System GMM in Stata, Roodman (2009) (https://journals.sagepub.com/doi/10....867X0900900106) and using the search function, I understood that it might be related to the number of coefficients and clusters in my model.
However, I do not understand why adding a constant solves the problem. Can anyone help me to understand the problem and how to proceed? I'd prefer to use the model without a constant. Please find the regression outputs including command below. Please also let me know if I should add any additional information or if I did not correctly paste my results into the post. I am new to Statalist and read the FAQs but I am not sure if I posted correctly.
1) with constant
Code:
xtabond2 SNL5YSR L.SNL5YSR CET1R VSTOXX YSOV ONR LLRGCL ROE WFTA , gmm(SNL5YSR, lag(2 2) coll eq(diff)) gmm(SNL5YSR, lag(1 1) coll eq(level)) gmm(CET1R LLRGCL ROE WFTA, lag (1 1) eq(diff) coll) gmm(CET1R LLRGCL ROE WFTA, lag (0 0) eq(level) coll) iv(VSTOXX YSOV ONR) twostep robust Favoring speed over space. To switch, type or click on mata: mata set matafavor space, perm. Dynamic panel-data estimation, two-step system GMM ------------------------------------------------------------------------------ Group variable: SP_ENTITY_ID Number of obs = 503 Time variable : TimeID Number of groups = 22 Number of instruments = 14 Obs per group: min = 21 Wald chi2(8) = 7769.91 avg = 22.86 Prob > chi2 = 0.000 max = 24 ------------------------------------------------------------------------------ | Corrected SNL5YSR | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- SNL5YSR | L1. | .7236356 .1245733 5.81 0.000 .4794765 .9677947 | CET1R | -2.7957 1.132513 -2.47 0.014 -5.015384 -.576016 VSTOXX | 1.760592 .2525506 6.97 0.000 1.265602 2.255582 YSOV | .2334796 .0893604 2.61 0.009 .0583365 .4086227 ONR | -2.589678 2.239863 -1.16 0.248 -6.979729 1.800373 LLRGCL | -5.618255 3.577531 -1.57 0.116 -12.63009 1.393576 ROE | -.4537094 .4546517 -1.00 0.318 -1.34481 .4373916 WFTA | -.3023635 .3822196 -0.79 0.429 -1.0515 .4467731 _cons | 44.18907 21.5631 2.05 0.040 1.92617 86.45197 ------------------------------------------------------------------------------ Instruments for first differences equation Standard D.(VSTOXX YSOV ONR) GMM-type (missing=0, separate instruments for each period unless collapsed) L.(CET1R LLRGCL ROE WFTA) collapsed L2.SNL5YSR collapsed Instruments for levels equation Standard VSTOXX YSOV ONR _cons GMM-type (missing=0, separate instruments for each period unless collapsed) D.(CET1R LLRGCL ROE WFTA) collapsed DL.SNL5YSR collapsed ------------------------------------------------------------------------------ Arellano-Bond test for AR(1) in first differences: z = -1.97 Pr > z = 0.049 Arellano-Bond test for AR(2) in first differences: z = 1.20 Pr > z = 0.228 ------------------------------------------------------------------------------ Sargan test of overid. restrictions: chi2(5) = 19.63 Prob > chi2 = 0.001 (Not robust, but not weakened by many instruments.) Hansen test of overid. restrictions: chi2(5) = 9.00 Prob > chi2 = 0.109 (Robust, but weakened by many instruments.) Difference-in-Hansen tests of exogeneity of instrument subsets: GMM instruments for levels Hansen test excluding group: chi2(0) = 0.00 Prob > chi2 = . Difference (null H = exogenous): chi2(5) = 9.00 Prob > chi2 = 0.109 gmm(SNL5YSR, collapse eq(diff) lag(2 2)) Hansen test excluding group: chi2(4) = 8.99 Prob > chi2 = 0.061 Difference (null H = exogenous): chi2(1) = 0.01 Prob > chi2 = 0.928 gmm(SNL5YSR, collapse eq(level) lag(1 1)) Hansen test excluding group: chi2(4) = 8.70 Prob > chi2 = 0.069 Difference (null H = exogenous): chi2(1) = 0.30 Prob > chi2 = 0.585 gmm(CET1R LLRGCL ROE WFTA, collapse eq(diff) lag(1 1)) Hansen test excluding group: chi2(1) = 1.09 Prob > chi2 = 0.297 Difference (null H = exogenous): chi2(4) = 7.91 Prob > chi2 = 0.095 gmm(CET1R LLRGCL ROE WFTA, collapse eq(level) lag(0 0)) Hansen test excluding group: chi2(1) = 7.66 Prob > chi2 = 0.006 Difference (null H = exogenous): chi2(4) = 1.34 Prob > chi2 = 0.855 iv(VSTOXX YSOV ONR) Hansen test excluding group: chi2(2) = 2.11 Prob > chi2 = 0.349 Difference (null H = exogenous): chi2(3) = 6.89 Prob > chi2 = 0.075
2) without constant
Code:
. xtabond2 SNL5YSR L.SNL5YSR CET1R VSTOXX YSOV ONR LLRGCL ROE WFTA , gmm(SNL5YSR, lag(2 2) coll eq(diff)) gmm(SNL5YSR, lag(1 1) coll eq(level)) gmm(CET1R LLRGCL ROE WFTA, lag (1 1) eq > (diff) coll) gmm(CET1R LLRGCL ROE WFTA, lag (0 0) eq(level) coll) iv(VSTOXX YSOV ONR) twostep robust nocons Favoring speed over space. To switch, type or click on mata: mata set matafavor space, perm. Dynamic panel-data estimation, two-step system GMM ------------------------------------------------------------------------------ Group variable: SP_ENTITY_ID Number of obs = 503 Time variable : TimeID Number of groups = 22 Number of instruments = 13 Obs per group: min = 21 Wald chi2(0) = . avg = 22.86 Prob > chi2 = . max = 24 ------------------------------------------------------------------------------ | Corrected SNL5YSR | Coef. Std. Err. z P>|z| [95% Conf. Interval] -------------+---------------------------------------------------------------- SNL5YSR | L1. | .749729 .1454875 5.15 0.000 .4645788 1.034879 | CET1R | -3.331046 1.410676 -2.36 0.018 -6.09592 -.5661716 VSTOXX | 2.901118 .7974796 3.64 0.000 1.338086 4.464149 YSOV | .1807601 .0801348 2.26 0.024 .0236987 .3378214 ONR | -15.24867 10.87028 -1.40 0.161 -36.55404 6.056697 LLRGCL | -3.283477 2.566796 -1.28 0.201 -8.314305 1.747351 ROE | -.2305399 .3018184 -0.76 0.445 -.8220931 .3610133 WFTA | .2303409 .2724232 0.85 0.398 -.3035987 .7642806 ------------------------------------------------------------------------------ Instruments for first differences equation Standard D.(VSTOXX YSOV ONR) GMM-type (missing=0, separate instruments for each period unless collapsed) L.(CET1R LLRGCL ROE WFTA) collapsed L2.SNL5YSR collapsed Instruments for levels equation Standard VSTOXX YSOV ONR GMM-type (missing=0, separate instruments for each period unless collapsed) D.(CET1R LLRGCL ROE WFTA) collapsed DL.SNL5YSR collapsed ------------------------------------------------------------------------------ Arellano-Bond test for AR(1) in first differences: z = -2.09 Pr > z = 0.036 Arellano-Bond test for AR(2) in first differences: z = 0.94 Pr > z = 0.346 ------------------------------------------------------------------------------ Sargan test of overid. restrictions: chi2(5) = 9.94 Prob > chi2 = 0.077 (Not robust, but not weakened by many instruments.) Hansen test of overid. restrictions: chi2(5) = 7.77 Prob > chi2 = 0.169 (Robust, but weakened by many instruments.) Difference-in-Hansen tests of exogeneity of instrument subsets: GMM instruments for levels Hansen test excluding group: chi2(0) = 0.00 Prob > chi2 = . Difference (null H = exogenous): chi2(5) = 7.77 Prob > chi2 = 0.169 gmm(SNL5YSR, collapse eq(diff) lag(2 2)) Hansen test excluding group: chi2(4) = 7.27 Prob > chi2 = 0.122 Difference (null H = exogenous): chi2(1) = 0.50 Prob > chi2 = 0.479 gmm(SNL5YSR, collapse eq(level) lag(1 1)) Hansen test excluding group: chi2(4) = 7.72 Prob > chi2 = 0.102 Difference (null H = exogenous): chi2(1) = 0.05 Prob > chi2 = 0.816 gmm(CET1R LLRGCL ROE WFTA, collapse eq(diff) lag(1 1)) Hansen test excluding group: chi2(1) = 0.00 Prob > chi2 = 0.986 Difference (null H = exogenous): chi2(4) = 7.77 Prob > chi2 = 0.100 gmm(CET1R LLRGCL ROE WFTA, collapse eq(level) lag(0 0)) Hansen test excluding group: chi2(1) = 4.68 Prob > chi2 = 0.031 Difference (null H = exogenous): chi2(4) = 3.09 Prob > chi2 = 0.542 iv(VSTOXX YSOV ONR) Hansen test excluding group: chi2(2) = 0.97 Prob > chi2 = 0.616 Difference (null H = exogenous): chi2(3) = 6.80 Prob > chi2 = 0.078
dataex SNL5YSR CET1R VSTOXX YSOV ONR LLRGCL ROE WFTA, count(10)
Code:
* Example generated by -dataex-. To install: ssc install dataex clear input double SNL5YSR float CET1R double(VSTOXX YSOV ONR) float LLRGCL double ROE float WFTA 111.62393939393941 . 16.9061 55.91924242424243 .12007812499999998 4.4316688 . . 97.85031249999999 10.9 18.6417 52.44968750000002 .1821746031746032 4.4926686 1.7693218833284 . 82.05261538461538 10.9 15.9833 43.87292307692308 .19156451612903225 4.5539865 5.14868005482391 43.37068 76.44727272727275 11.1 16.8353 42.17227272727272 .022969696969696973 4.3474116 6.69158714103523 41.57645 80.86666666666666 10.914593 21.5048 50.39424242424242 -.015109375000000012 4.1446137 5.31285262542873 38.25728 82.59453125000002 10.5 22.6771 44.57796875000002 -.045888888888888896 4.0511775 6.41991374492188 35.974506 80.8106153846154 11.006385 23.1731 34.94323076923077 -.10019354838709676 3.962838 8.05379174411497 38.81546 85.8978787878788 11.1 26.6899 33.29984848484849 -.12483333333333332 3.806642 8.1975740861538 38.23668 74.91257575757577 11.419175 23.4128 28.50075757575758 -.15786153846153836 3.653196 7.23794858915584 37.924942 89.8449230769231 11.5 28.611 31.730923076923073 -.2558709677419355 3.603081 6.51920838183935 38.76804 end Listed 10 out of 604 observations
Niklas
0 Response to xtabond2 - missing Wald Chi2 under nocons option
Post a Comment