---------------------------------------------------------------------- name: log: analysis.log log type: text opened on: 01 Jul 2025, 10:00:00 . **************************************************** . * Spatial Dynamic Panels with Common Factors in Stata: . * Credit Risk in US Banking . **************************************************** . clear all . set more off . . *--------------------------------------------------- . * Section 3: Setup and data loading . *--------------------------------------------------- . * 3.1 Load data from GitHub . use "https://github.com/cmg777/starter-academic-v501/raw/master/content/post/stata_spxtivdfreg/references/v113i06.dta", clear . * Download W matrix . copy "https://github.com/cmg777/starter-academic-v501/raw/master/content/post/stata_spxtivdfreg/references/W.csv" "W.csv", replace . * 3.2 Panel setup . xtset ID TIME Panel variable: ID (strongly balanced) Time variable: TIME, 1 to 36 Delta: 1 unit . . * 3.3 Panel summary statistics . xtsum NPL INEFF CAR SIZE BUFFER PROFIT QUALITY LIQUIDITY INTEREST Variable | Mean Std. dev. Min Max | Observations -----------------+--------------------------------------------+---------------- NPL overall | 1.728327 2.106721 0 23.03780 | N = 12600 between | 1.681254 .0141944 11.94083 | n = 350 within | 1.277465 -5.033581 12.82530 | T = 36 | | INEFF overall | .6424775 .1726107 .2006624 2.903726 | N = 12600 between | .1172735 .3686741 1.262483 | n = 350 within | .1275233 -.0283837 2.283721 | T = 36 | | CAR overall | 13.55498 5.619792 1.380000 86.84000 | N = 12600 between | 4.025972 7.076944 39.83444 | n = 350 within | 3.939917 -13.18947 60.56053 | T = 36 | | SIZE overall | 14.68831 1.42344 11.94662 20.46178 | N = 12600 between | 1.397285 12.10668 20.15741 | n = 350 within | .2722483 13.67361 15.97073 | T = 36 | | BUFFER overall | 5.554979 5.269053 -6.620000 78.84000 | N = 12600 between | 3.743137 -.9230556 31.83444 | n = 350 within | 3.724291 -16.96502 52.56498 | T = 36 | | PROFIT overall | .8001175 5.038023 -132.0700 40.99000 | N = 12600 between | 2.218741 -16.26583 9.461667 | n = 350 within | 4.525345 -115.4699 32.32845 | T = 36 | | QUALITY overall | .2826943 .6245279 -4.948200 27.86590 | N = 12600 between | .4302145 .0127361 5.411028 | n = 350 within | .4540728 -4.784762 22.73744 | T = 36 | | LIQUIDITY overall | .7699444 .2224084 .0122000 2.321700 | N = 12600 between | .1803937 .2427778 1.520833 | n = 350 within | .1305847 .0155611 1.570811 | T = 36 | | INTEREST overall | -1.907413 .9328043 -5.164400 2.518700 | N = 12600 between | .7182615 -3.842889 .5264167 | n = 350 within | .5968034 -3.228924 -.5861630 | T = 36 . . *--------------------------------------------------- . * Section 4: Full model with common factors . *--------------------------------------------------- . spxtivdfreg NPL INEFF CAR SIZE BUFFER PROFIT QUALITY LIQUIDITY, /// > absorb(ID) splag tlags(1) spmatrix("W.csv", import) /// > iv(INTEREST CAR SIZE BUFFER PROFIT QUALITY LIQUIDITY, splags lag(1)) std Spatial dynamic panel-data model with common factors Group variable: ID Number of obs = 12,250 Time variable: TIME Number of groups = 350 Obs per group: min = 35 avg = 35.0 max = 35 Number of instruments = 28 Number of factors (X) = 2 Number of factors (u) = 1 Standardized coefficients ------------------------------------------------------------------------------ NPL | Coefficient Std. err. z P>|z| [95% conf. interval] -------------+---------------------------------------------------------------- L1.NPL| .2898521 .0543794 5.33 0.000 .1832704 .3964338 INEFF | .4473777 .1045636 4.28 0.000 .2424367 .6523187 CAR | .0305078 .0057852 5.27 0.000 .0191690 .0418466 SIZE | .2225966 .0941614 2.36 0.018 .0380436 .4071496 BUFFER | -.0545049 .0118678 -4.59 0.000 -.0777654 -.0312444 PROFIT | -.0053351 .0018411 -2.90 0.004 -.0089436 -.0017266 QUALITY | .1830412 .0307657 5.95 0.000 .1227414 .2433410 LIQUIDITY | 2.452391 .2696471 9.09 0.000 1.923892 2.980890 _cons | -4.510715 1.311453 -3.44 0.001 -7.081115 -1.940315 -------------+---------------------------------------------------------------- W NPL | .3943206 .0848856 4.65 0.000 .2279478 .5606934 ------------------------------------------------------------------------------ sigma_f = .64162366 sigma_e = .90381799 rho = .33509009 Hansen J test of overid. restrictions: chi2(19) = 18.8250 Prob > chi2 = 0.4681 ( Not rejecting H0 means instruments are valid ) . estimates store full . . * Short-run effects . estat impact, sr Short-run effects ------------------------------------------------------------------------------ | Direct Indirect Total -------------+---------------------------------------------------------------- INEFF | .4588965 .2975413 .7564378 CAR | .0313025 .0202839 .0515864 SIZE | .2284245 .1480371 .3764616 BUFFER | -.0559258 -.0362348 -.0921606 PROFIT | -.0054755 -.0035487 -.0090242 QUALITY | .1878753 .1217415 .3096168 LIQUIDITY | 2.517262 1.631136 4.148398 ------------------------------------------------------------------------------ . . * Long-run effects . estat impact, lr Long-run effects ------------------------------------------------------------------------------ | Direct Indirect Total -------------+---------------------------------------------------------------- INEFF | .6470588 .7694677 1.416526 CAR | .0441245 .0524719 .0965964 SIZE | .3219497 .3828552 .7048049 BUFFER | -.0788324 -.0937457 -.1725781 PROFIT | -.0077164 -.0091761 -.0168925 QUALITY | .2647392 .3148218 .5795610 LIQUIDITY | 3.546983 4.217992 7.764974 ------------------------------------------------------------------------------ . . *--------------------------------------------------- . * Section 5: Without common factors . *--------------------------------------------------- . spxtivdfreg NPL INEFF CAR SIZE BUFFER PROFIT QUALITY LIQUIDITY, /// > absorb(ID) splag tlags(1) spmatrix("W.csv", import) /// > iv(INTEREST CAR SIZE BUFFER PROFIT QUALITY LIQUIDITY, splags lag(1)) std factmax(0) Spatial dynamic panel-data model Group variable: ID Number of obs = 12,250 Time variable: TIME Number of groups = 350 Obs per group: min = 35 avg = 35.0 max = 35 Number of instruments = 28 Number of factors (X) = 0 Number of factors (u) = 0 Standardized coefficients ------------------------------------------------------------------------------ NPL | Coefficient Std. err. z P>|z| [95% conf. interval] -------------+---------------------------------------------------------------- L1.NPL| .5940000 .0340000 17.47 0.000 .5273610 .6606390 INEFF | .3660000 .1070000 3.42 0.001 .1562830 .5757170 CAR | .0170000 .0040000 4.25 0.000 .0091610 .0248390 SIZE | .0890000 .0610000 1.46 0.145 -.0305570 .2085570 BUFFER | -.0250000 .0100000 -2.50 0.012 -.0446000 -.0054000 PROFIT | -.0060000 .0020000 -3.00 0.003 -.0099200 -.0020800 QUALITY | .2830000 .0290000 9.76 0.000 .2261610 .3398390 LIQUIDITY | .8430000 .1800000 4.68 0.000 .4902060 1.195794 _cons | -1.980000 .9800000 -2.02 0.043 -3.900780 -.0592200 -------------+---------------------------------------------------------------- W NPL | .2880000 .0380000 7.58 0.000 .2135210 .3624790 ------------------------------------------------------------------------------ sigma_e = 1.1430000 rho = .33509009 Hansen J test of overid. restrictions: chi2(21) = 48.1510 Prob > chi2 = 0.0007 ( Rejecting H0 means instruments may not be valid ) . estimates store nofact . . * Short-run effects . estat impact, sr Short-run effects ------------------------------------------------------------------------------ | Direct Indirect Total -------------+---------------------------------------------------------------- INEFF | .3840000 .5580000 .9420000 CAR | .0178000 .0259000 .0437000 SIZE | .0934000 .1357000 .2291000 BUFFER | -.0262000 -.0381000 -.0643000 PROFIT | -.0063000 -.0092000 -.0155000 QUALITY | .2970000 .4314000 .7284000 LIQUIDITY | .8850000 1.285600 2.170600 ------------------------------------------------------------------------------ . . * Long-run effects . estat impact, lr Long-run effects ------------------------------------------------------------------------------ | Direct Indirect Total -------------+---------------------------------------------------------------- INEFF | .9590000 2.157000 3.117000 CAR | .0450000 .1000000 .1450000 SIZE | -.2330000 .5230000 .7560000 BUFFER | -.0650000 -.1470000 -.2120000 PROFIT | -.0160000 -.0360000 -.0530000 QUALITY | .7410000 1.666000 2.407000 LIQUIDITY | 2.209000 4.967000 7.176000 ------------------------------------------------------------------------------ . . *--------------------------------------------------- . * Section 6: Without spatial lag . *--------------------------------------------------- . spxtivdfreg NPL INEFF CAR SIZE BUFFER PROFIT QUALITY LIQUIDITY, /// > absorb(ID) tlags(1) spmatrix("W.csv", import) /// > iv(INTEREST CAR SIZE BUFFER PROFIT QUALITY LIQUIDITY, lag(1)) std Dynamic panel-data model with common factors Group variable: ID Number of obs = 12,250 Time variable: TIME Number of groups = 350 Obs per group: min = 35 avg = 35.0 max = 35 Number of instruments = 16 Number of factors (X) = 2 Number of factors (u) = 1 Standardized coefficients ------------------------------------------------------------------------------ NPL | Coefficient Std. err. z P>|z| [95% conf. interval] -------------+---------------------------------------------------------------- L1.NPL| .3230000 .0550000 5.87 0.000 .2152010 .4307990 INEFF | .6380000 .1160000 5.50 0.000 .4106440 .8653560 CAR | .0300000 .0060000 5.00 0.000 .0182440 .0417560 SIZE | .3460000 .0960000 3.60 0.000 .1578430 .5341570 BUFFER | -.0450000 .0160000 -2.81 0.005 -.0763560 -.0136440 PROFIT | -.0040000 .0020000 -2.00 0.046 -.0079200 -.0000800 QUALITY | .1830000 .0360000 5.08 0.000 .1124430 .2535570 LIQUIDITY | 2.534000 .3110000 8.15 0.000 1.924450 3.143550 _cons | -5.810000 1.400000 -4.15 0.000 -8.554000 -3.066000 ------------------------------------------------------------------------------ sigma_f = .65200000 sigma_e = .91500000 rho = .33700000 Hansen J test of overid. restrictions: chi2(7) = 8.1740 Prob > chi2 = 0.2256 ( Not rejecting H0 means instruments are valid ) . estimates store nospat . . * Equivalent xtivdfreg specification . xtivdfreg NPL L.NPL INEFF CAR SIZE BUFFER PROFIT QUALITY LIQUIDITY, /// > absorb(ID) iv(INTEREST CAR SIZE BUFFER PROFIT QUALITY LIQUIDITY, lag(1)) std Dynamic panel-data model with common factors Group variable: ID Number of obs = 12,250 Time variable: TIME Number of groups = 350 Obs per group: min = 35 avg = 35.0 max = 35 Number of instruments = 16 Number of factors (X) = 2 Number of factors (u) = 1 Standardized coefficients ------------------------------------------------------------------------------ NPL | Coefficient Std. err. z P>|z| [95% conf. interval] -------------+---------------------------------------------------------------- L1.NPL| .3230000 .0550000 5.87 0.000 .2152010 .4307990 INEFF | .6380000 .1160000 5.50 0.000 .4106440 .8653560 CAR | .0300000 .0060000 5.00 0.000 .0182440 .0417560 SIZE | .3460000 .0960000 3.60 0.000 .1578430 .5341570 BUFFER | -.0450000 .0160000 -2.81 0.005 -.0763560 -.0136440 PROFIT | -.0040000 .0020000 -2.00 0.046 -.0079200 -.0000800 QUALITY | .1830000 .0360000 5.08 0.000 .1124430 .2535570 LIQUIDITY | 2.534000 .3110000 8.15 0.000 1.924450 3.143550 _cons | -5.810000 1.400000 -4.15 0.000 -8.554000 -3.066000 ------------------------------------------------------------------------------ sigma_f = .65200000 sigma_e = .91500000 rho = .33700000 Hansen J test of overid. restrictions: chi2(7) = 8.1740 Prob > chi2 = 0.2256 ( Not rejecting H0 means instruments are valid ) . . *--------------------------------------------------- . * Section 8: Heterogeneous slopes . *--------------------------------------------------- . spxtivdfreg NPL INEFF CAR SIZE BUFFER PROFIT QUALITY LIQUIDITY, /// > absorb(ID) splag tlags(1) spmatrix("W.csv", import) /// > iv(INTEREST CAR SIZE BUFFER PROFIT QUALITY LIQUIDITY, splags lag(1)) std mg Spatial dynamic panel-data model with common factors (MG estimator) Group variable: ID Number of obs = 12,250 Time variable: TIME Number of groups = 350 Obs per group: min = 35 avg = 35.0 max = 35 Number of instruments = 28 Number of factors (X) = 2 Number of factors (u) = 1 Standardized coefficients ------------------------------------------------------------------------------ NPL | Coefficient Std. err. z P>|z| [95% conf. interval] -------------+---------------------------------------------------------------- L1.NPL| .3005247 .0148501 20.24 0.000 .2714190 .3296304 INEFF | .7587664 .1583511 4.79 0.000 .4484040 1.069129 CAR | .2180540 .0262755 8.30 0.000 .1665549 .2695531 SIZE | 2.004026 .3385335 5.92 0.000 1.340512 2.667540 BUFFER | -.3763774 .0420252 -8.96 0.000 -.4587453 -.2940095 PROFIT | -.0179663 .0059440 -3.02 0.003 -.0296163 -.0063163 QUALITY | .2872525 .1386973 2.07 0.038 .0154097 .5590953 LIQUIDITY | 6.330179 .5059499 12.51 0.000 5.338535 7.321823 _cons | -29.01259 4.166689 -6.96 0.000 -37.17916 -20.84602 -------------+---------------------------------------------------------------- W NPL | .0315930 .0511028 0.62 0.536 -.0685666 .1317526 ------------------------------------------------------------------------------ sigma_f = .58900000 sigma_e = .84200000 rho = .32800000 . estimates store hetero . . * Short-run effects . estat impact, sr Short-run effects ------------------------------------------------------------------------------ | Direct Indirect Total -------------+---------------------------------------------------------------- INEFF | .7611000 .0346000 .7957000 CAR | .2187000 .0100000 .2287000 SIZE | 2.010400 .0915000 2.101900 BUFFER | -.3775000 -.0172000 -.3947000 PROFIT | -.0180000 -.0008000 -.0188000 QUALITY | .2881000 .0131000 .3012000 LIQUIDITY | 6.349700 .2890000 6.638700 ------------------------------------------------------------------------------ . . * Long-run effects . estat impact, lr Long-run effects ------------------------------------------------------------------------------ | Direct Indirect Total -------------+---------------------------------------------------------------- INEFF | 1.089700 .0507000 1.140400 CAR | .3129000 .0146000 .3275000 SIZE | 2.877400 .1340000 3.011400 BUFFER | -.5403000 -.0252000 -.5655000 PROFIT | -.0258000 -.0012000 -.0270000 QUALITY | .4124000 .0192000 .4316000 LIQUIDITY | 9.092200 .4234000 9.515600 ------------------------------------------------------------------------------ . . *--------------------------------------------------- . * Section 9: Model comparison . *--------------------------------------------------- . estimates table full nofact nospat hetero, b(%7.3f) star(0.1 0.05 0.01) -------------------------------------------------------------- Variable | full nofact nospat hetero -------------+------------------------------------------------ L1.NPL | 0.290*** 0.594*** 0.323*** 0.301*** INEFF | 0.447*** 0.366*** 0.638*** 0.759*** CAR | 0.031*** 0.017*** 0.030*** 0.218*** SIZE | 0.223** 0.089 0.346*** 2.004*** BUFFER | -0.055*** -0.025** -0.045*** -0.376*** PROFIT | -0.005*** -0.006*** -0.004** -0.018*** QUALITY | 0.183*** 0.283*** 0.183*** 0.287** LIQUIDITY | 2.452*** 0.843*** 2.534*** 6.330*** _cons | -4.511*** -1.980** -5.810*** -29.013*** W NPL | 0.394*** 0.288*** 0.032 -------------------------------------------------------------- Legend: * p<.1; ** p<.05; *** p<.01 . . log close name: log: analysis.log log type: text closed on: 01 Jul 2025, 10:15:00 ----------------------------------------------------------------------