I am analyzing a panel dataset with year dummies over a period of 2000-2018 and
apparently like many other Stata beginners, I came across the issue of (V_b-V_B is not positive definite) when using Hausman test to determine whether to use the FE or RE model.
I tried to follow suggestions of using xtoverid and after installing the package, I encountered the following issue:
Code:
. xtoverid
2b: operator invalid
r(198);Notes: I already tried
Code:
hausman fe re, sigmamore
hausman fe re, sigmalessCode:
** Redo HAUSMAN test to check for RE or FE model
. xtreg wROAf1 IV_CSPaggr geoentropy4rg indentropy CF_age CF_size_lnEmp CF_Levg CF_NPM CF_orgslack CC_WGI s_poptotal CC_WDI
> _PopGrowth s_GDP s_GDPpc CC_WDI_GDPPCgrowth s_fdi CC_WDI_ttUnemplRate i.yeardummy, fe
note: 17.yeardummy omitted because of collinearity
Fixed-effects (within) regression Number of obs = 18,964
Group variable: compid Number of groups = 3,780
R-sq: Obs per group:
within = 0.0346 min = 1
between = 0.0089 avg = 5.0
overall = 0.0011 max = 16
F(30,15154) = 18.13
corr(u_i, Xb) = -0.6065 Prob > F = 0.0000
-------------------------------------------------------------------------------------
wROAf1 | Coef. Std. Err. t P>|t| [95% Conf. Interval]
--------------------+----------------------------------------------------------------
IV_CSPaggr | -.0227671 .0064973 -3.50 0.000 -.0355027 -.0100316
geoentropy4rg | -.6074356 .4636818 -1.31 0.190 -1.516308 .3014366
indentropy | -.0358456 .2862778 -0.13 0.900 -.5969847 .5252934
CF_age | .1352476 .0487664 2.77 0.006 .0396596 .2308355
CF_size_lnEmp | -1.551527 .1776825 -8.73 0.000 -1.899806 -1.203248
CF_Levg | -3.375775 .6100142 -5.53 0.000 -4.571477 -2.180074
CF_NPM | .0023169 .0010765 2.15 0.031 .0002068 .0044269
CF_orgslack | -.0353077 .0529923 -0.67 0.505 -.139179 .0685636
CC_WGI | 2.715108 1.34704 2.02 0.044 .0747483 5.355469
s_poptotal | -.0184933 .0304806 -0.61 0.544 -.078239 .0412524
CC_WDI_PopGrowth | .1152938 .3522301 0.33 0.743 -.5751196 .8057072
s_GDP | .632364 .1654363 3.82 0.000 .3080889 .9566391
s_GDPpc | -1.391459 .2382413 -5.84 0.000 -1.85844 -.9244769
CC_WDI_GDPPCgrowth | .1399394 .0499854 2.80 0.005 .041962 .2379168
s_fdi | .0759093 .0944164 0.80 0.421 -.1091582 .2609769
CC_WDI_ttUnemplRate | .0317622 .0728713 0.44 0.663 -.1110744 .1745988
|
yeardummy |
2003 | 1.718398 .660478 2.60 0.009 .4237814 3.013015
2004 | 2.647522 .5736919 4.61 0.000 1.523017 3.772027
2005 | 3.015123 .5307992 5.68 0.000 1.974692 4.055553
2006 | 2.572717 .4936521 5.21 0.000 1.605099 3.540335
2007 | .1135621 .4749622 0.24 0.811 -.8174212 1.044545
2008 | -.1597079 .4313103 -0.37 0.711 -1.005128 .6857123
2009 | 2.637556 .4797226 5.50 0.000 1.697242 3.57787
2010 | 1.65895 .3939397 4.21 0.000 .8867807 2.431119
2011 | 1.438345 .3699788 3.89 0.000 .7131416 2.163548
2012 | .55647 .3401479 1.64 0.102 -.1102609 1.223201
2013 | .4664979 .3052461 1.53 0.126 -.1318213 1.064817
2014 | -1.235379 .2731461 -4.52 0.000 -1.770778 -.6999793
2015 | -.5328104 .2561052 -2.08 0.038 -1.034807 -.0308134
2016 | .5114611 .2398972 2.13 0.033 .0412337 .9816885
2017 | 0 (omitted)
|
_cons | 15.21448 5.054748 3.01 0.003 5.306568 25.1224
--------------------+----------------------------------------------------------------
sigma_u | 13.647115
sigma_e | 7.0821539
rho | .78783095 (fraction of variance due to u_i)
-------------------------------------------------------------------------------------
F test that all u_i=0: F(3779, 15154) = 6.53 Prob > F = 0.0000
. estimate store fe
. xtreg wROAf1 IV_CSPaggr geoentropy4rg indentropy CF_age CF_size_lnEmp CF_Levg CF_NPM CF_orgslack CC_WGI s_poptotal CC_WDI
> _PopGrowth s_GDP s_GDPpc CC_WDI_GDPPCgrowth s_fdi CC_WDI_ttUnemplRate i.yeardummy, re
Random-effects GLS regression Number of obs = 18,964
Group variable: compid Number of groups = 3,780
R-sq: Obs per group:
within = 0.0190 min = 1
between = 0.0983 avg = 5.0
overall = 0.0484 max = 16
Wald chi2(31) = 642.04
corr(u_i, X) = 0 (assumed) Prob > chi2 = 0.0000
-------------------------------------------------------------------------------------
wROAf1 | Coef. Std. Err. z P>|z| [95% Conf. Interval]
--------------------+----------------------------------------------------------------
IV_CSPaggr | -.0104024 .0050298 -2.07 0.039 -.0202607 -.0005442
geoentropy4rg | .5555316 .326717 1.70 0.089 -.0848219 1.195885
indentropy | .040395 .2456707 0.16 0.869 -.4411107 .5219008
CF_age | .0183981 .0053646 3.43 0.001 .0078837 .0289125
CF_size_lnEmp | .6894453 .093907 7.34 0.000 .505391 .8734995
CF_Levg | -3.212073 .5162737 -6.22 0.000 -4.22395 -2.200195
CF_NPM | .0021792 .0004408 4.94 0.000 .0013153 .0030432
CF_orgslack | -.1645398 .0435363 -3.78 0.000 -.2498694 -.0792102
CC_WGI | -.5799745 .4522981 -1.28 0.200 -1.466462 .3065135
s_poptotal | -.0020881 .0010709 -1.95 0.051 -.0041871 .0000108
CC_WDI_PopGrowth | .1173416 .2527258 0.46 0.642 -.3779918 .612675
s_GDP | .013877 .0326286 0.43 0.671 -.0500738 .0778278
s_GDPpc | -.4957057 .1248403 -3.97 0.000 -.7403882 -.2510232
CC_WDI_GDPPCgrowth | .1474068 .0474048 3.11 0.002 .054495 .2403185
s_fdi | .1062363 .0854276 1.24 0.214 -.0611988 .2736714
CC_WDI_ttUnemplRate | .0051797 .0428637 0.12 0.904 -.0788316 .089191
|
yeardummy |
2003 | 1.641583 .6825769 2.40 0.016 .3037567 2.979409
2004 | 2.930763 .6200142 4.73 0.000 1.715558 4.145969
2005 | 3.252471 .6017448 5.41 0.000 2.073073 4.431869
2006 | 2.934455 .5998017 4.89 0.000 1.758865 4.110044
2007 | .3813269 .6038372 0.63 0.528 -.8021723 1.564826
2008 | .252396 .5885435 0.43 0.668 -.9011281 1.40592
2009 | 3.200676 .6210972 5.15 0.000 1.983348 4.418004
2010 | 2.266513 .5860811 3.87 0.000 1.117815 3.415211
2011 | 1.933953 .5919703 3.27 0.001 .7737126 3.094193
2012 | 1.211612 .5868921 2.06 0.039 .0613248 2.361899
2013 | 1.19128 .5855447 2.03 0.042 .0436333 2.338926
2014 | -.3239355 .5834149 -0.56 0.579 -1.467408 .8195367
2015 | .6538636 .5763879 1.13 0.257 -.4758358 1.783563
2016 | 1.603099 .5801637 2.76 0.006 .4659991 2.740199
2017 | 1.087371 .5918516 1.84 0.066 -.072637 2.247379
|
_cons | -.2501154 1.308373 -0.19 0.848 -2.81448 2.314249
--------------------+----------------------------------------------------------------
sigma_u | 9.609396
sigma_e | 7.0821539
rho | .64801529 (fraction of variance due to u_i)
-------------------------------------------------------------------------------------
. estimate store re
. xttest0
Breusch and Pagan Lagrangian multiplier test for random effects
wROAf1[compid,t] = Xb + u[compid] + e[compid,t]
Estimated results:
| Var sd = sqrt(Var)
---------+-----------------------------
wROAf1 | 112.5129 10.60721
e | 50.1569 7.082154
u | 92.34049 9.609396
Test: Var(u) = 0
chibar2(01) = 6033.36
Prob > chibar2 = 0.0000
. xtoverid
2b: operator invalid
r(198);Code:
** Mundlak approach
egen CSPmean = mean(IV_CSPaggr)
egen Geoentmean = mean(geoentropy4rg)
egen Indentmean = mean(indentropy)
egen agemean = mean(CF_age)
egen sizemean = mean(CF_size_lnEmp)
egen levgmean = mean(CF_Levg)
egen npmmean = mean(CF_NPM)
egen orgslackmean = mean(CF_orgslack)
egen WGImean = mean(CC_WGI)
egen poptotalmean = mean(s_poptotal)
egen popgrowthmean = mean(CC_WDI_PopGrowth)
egen gdpmean = mean(s_GDP)
egen gdppcmean = mean(s_GDPpc)
egen gdppcgrowthmean = mean(CC_WDI_GDPPCgrowth)
egen fdimean = mean(s_fdi)
egen unemplmean = mean(CC_WDI_ttUnemplRate)
xtreg wROAf1 IV_CSPaggr geoentropy4rg indentropy CF_age CF_size_lnEmp CF_Levg CF_NPM CF_orgslack CC_WGI s_poptotal CC_WDI_PopGrowth s_GDP s_GDPpc CC_WDI_GDPPCgrowth s_fdi CC_WDI_ttUnemplRate CSPmean Geoentmean Indentmean agemean sizemean levgmean npmmean orgslackmean WGImean poptotalmean popgrowthmean gdpmean gdppcmean gdppcgrowthmean fdimean unemplmean i.yeardummy, re vce(robust)
note: CSPmean omitted because of collinearity
note: Geoentmean omitted because of collinearity
note: Indentmean omitted because of collinearity
note: agemean omitted because of collinearity
note: sizemean omitted because of collinearity
note: levgmean omitted because of collinearity
note: npmmean omitted because of collinearity
note: orgslackmean omitted because of collinearity
note: WGImean omitted because of collinearity
note: poptotalmean omitted because of collinearity
note: popgrowthmean omitted because of collinearity
note: gdpmean omitted because of collinearity
note: gdppcmean omitted because of collinearity
note: gdppcgrowthmean omitted because of collinearity
note: fdimean omitted because of collinearity
note: unemplmean omitted because of collinearity
Random-effects GLS regression Number of obs = 18,964
Group variable: compid Number of groups = 3,780
R-sq: Obs per group:
within = 0.0190 min = 1
between = 0.0983 avg = 5.0
overall = 0.0484 max = 16
Wald chi2(31) = 403.84
corr(u_i, X) = 0 (assumed) Prob > chi2 = 0.0000
(Std. Err. adjusted for 3,780 clusters in compid)
-------------------------------------------------------------------------------------
| Robust
wROAf1 | Coef. Std. Err. z P>|z| [95% Conf. Interval]
--------------------+----------------------------------------------------------------
IV_CSPaggr | -.0104024 .005792 -1.80 0.072 -.0217545 .0009497
geoentropy4rg | .5555316 .4246757 1.31 0.191 -.2768174 1.387881
indentropy | .040395 .2513858 0.16 0.872 -.452312 .5331021
CF_age | .0183981 .0037449 4.91 0.000 .0110582 .025738
CF_size_lnEmp | .6894453 .1634117 4.22 0.000 .3691641 1.009726
CF_Levg | -3.212073 1.113767 -2.88 0.004 -5.395016 -1.029129
CF_NPM | .0021792 .0011534 1.89 0.059 -.0000814 .0044399
CF_orgslack | -.1645398 .0894728 -1.84 0.066 -.3399033 .0108237
CC_WGI | -.5799745 .4286284 -1.35 0.176 -1.420071 .2601217
s_poptotal | -.0020881 .0008452 -2.47 0.013 -.0037447 -.0004315
CC_WDI_PopGrowth | .1173416 .2156586 0.54 0.586 -.3053415 .5400247
s_GDP | .013877 .0344897 0.40 0.687 -.0537215 .0814755
s_GDPpc | -.4957057 .1313103 -3.78 0.000 -.7530691 -.2383423
CC_WDI_GDPPCgrowth | .1474068 .0596172 2.47 0.013 .0305592 .2642544
s_fdi | .1062363 .0843957 1.26 0.208 -.0591762 .2716489
CC_WDI_ttUnemplRate | .0051797 .0422669 0.12 0.902 -.077662 .0880214
CSPmean | 0 (omitted)
Geoentmean | 0 (omitted)
Indentmean | 0 (omitted)
agemean | 0 (omitted)
sizemean | 0 (omitted)
levgmean | 0 (omitted)
npmmean | 0 (omitted)
orgslackmean | 0 (omitted)
WGImean | 0 (omitted)
poptotalmean | 0 (omitted)
popgrowthmean | 0 (omitted)
gdpmean | 0 (omitted)
gdppcmean | 0 (omitted)
gdppcgrowthmean | 0 (omitted)
fdimean | 0 (omitted)
unemplmean | 0 (omitted)
|
yeardummy |
2003 | 1.641583 .4706248 3.49 0.000 .7191752 2.56399
2004 | 2.930763 .580364 5.05 0.000 1.793271 4.068256
2005 | 3.252471 .5911194 5.50 0.000 2.093898 4.411043
2006 | 2.934455 .6290839 4.66 0.000 1.701473 4.167436
2007 | .3813269 .6928329 0.55 0.582 -.9766007 1.739254
2008 | .252396 .5860639 0.43 0.667 -.896268 1.40106
2009 | 3.200676 .6079538 5.26 0.000 2.009109 4.392244
2010 | 2.266513 .6160047 3.68 0.000 1.059166 3.47386
2011 | 1.933953 .6155617 3.14 0.002 .7274743 3.140432
2012 | 1.211612 .5967539 2.03 0.042 .041996 2.381228
2013 | 1.19128 .5951258 2.00 0.045 .0248547 2.357705
2014 | -.3239355 .605627 -0.53 0.593 -1.510943 .8630717
2015 | .6538636 .5871039 1.11 0.265 -.4968388 1.804566
2016 | 1.603099 .580165 2.76 0.006 .4659965 2.740202
2017 | 1.087371 .6118433 1.78 0.076 -.11182 2.286562
|
_cons | -.2501154 1.708782 -0.15 0.884 -3.599267 3.099036
--------------------+----------------------------------------------------------------
sigma_u | 9.609396
sigma_e | 7.0821539
rho | .64801529 (fraction of variance due to u_i)
-------------------------------------------------------------------------------------
estimates store mundlak
testparm CSPmean Geoentmean Indentmean agemean sizemean levgmean npmmean orgslackmean WGImean poptotalmean popgrowthmean gdpmean gdppcmean gdppcgrowthmean fdimean unemplmean
no such variables;
the specified varlist does not identify any testable coefficients
r(111);Kind regards,
Jennifer
0 Response to xtreg, fe robust: xtoverid error(2b) operator invalid when correcting Hausman test (V_b-V_B is not positive definite) due to year dummies
Post a Comment