Hello!
I am using STATA/SE 15.1 and doing panel data analysis involving 100 countries and 12 years of time period. Panel is unbalanced and I have 600 obervations in total. I have read literature and few number of obervations and panel data analysis is the norm in this field. However, when I conduct the hausman test, it runs fine until I add Years and Country effects i.e. dummy variables of these i.year and i.countrynum.Now I have read previous posts about hausman test but I didn't get the answer. Maybe I overlooked something. This error (displayed below) comes when I run with year and country effects (Adding dummy variables to the regression equation).
Hoping to hear from the experts.
I am using STATA/SE 15.1 and doing panel data analysis involving 100 countries and 12 years of time period. Panel is unbalanced and I have 600 obervations in total. I have read literature and few number of obervations and panel data analysis is the norm in this field. However, when I conduct the hausman test, it runs fine until I add Years and Country effects i.e. dummy variables of these i.year and i.countrynum.Now I have read previous posts about hausman test but I didn't get the answer. Maybe I overlooked something. This error (displayed below) comes when I run with year and country effects (Adding dummy variables to the regression equation).
Code:
Note: the rank of the differenced variance matrix (16) does not equal the number of coefficients being
tested (17); be sure this is what you expect, or there may be problems computing the test.
Examine the output of your estimators for anything unexpected and possibly consider scaling your
variables so that the coefficients are on a similar scale.
---- Coefficients ----
| (b) (B) (b-B) sqrt(diag(V_b-V_B))
| fe re Difference S.E.
-------------+----------------------------------------------------------------
totalterro~s | -.0003332 -.0003332 6.66e-16 .
ControlofC~n | .3944104 .3944104 4.51e-12 .
SavingsCur~g | .5122627 .5122627 -9.89e-12 .
Inflationwin | .0189139 .0189139 -1.00e-13 .
creditwins~g | .006928 .006928 -1.02e-12 .
Year |
2007 | .4605182 .4605182 1.98e-12 .
2008 | -.0723403 -.0723403 2.76e-12 .
2009 | -.0857283 -.0857283 8.63e-13 .
2010 | -.203764 -.203764 2.60e-12 .
2011 | -.1459416 -.1459416 4.59e-12 .
2012 | .1909434 .1909434 4.45e-12 .
2013 | .1695522 .1695522 4.52e-12 .
2014 | .2844599 .2844599 4.79e-12 .
2015 | .5150472 .5150472 3.58e-12 .
2016 | .7817107 .7817107 3.49e-12 .
2017 | .8225087 .8225087 4.54e-12 .
2018 | .9736898 .9736898 5.40e-12 .
------------------------------------------------------------------------------
b = consistent under Ho and Ha; obtained from xtreg
B = inconsistent under Ha, efficient under Ho; obtained from xtreg
Test: Ho: difference in coefficients not systematic
chi2(16) = (b-B)'[(V_b-V_B)^(-1)](b-B)
= -0.00 chi2<0 ==> model fitted on these
data fails to meet the asymptotic
assumptions of the Hausman test;
see suest for a generalized test
Hoping to hear from the experts.
Comment