Hi Users
I have a question about the Hadrilm test of statinarity in Panel data.
Can I use this test with unblanced panel?
With stata I have this result bellow, but I can't conclude if there's a stationnarity or no.
hadrilm D.lnPTMQ (stata command)
Hadri (2000) panel unit root test for D.lnPTMQ
with 190 observations on 6 cross-sectional units
eps Z(mu) P-value Z(tau) P-value
Homo -2.510 0.9940 -3.445 0.9997
Hetero -2.227 0.9870 -3.190 0.9993
SerDep -1.993 0.9769 -2.379 0.9913
H0: all 6 timeseries in the panel are stationary processes
Homo: homoskedastic disturbances across units
Hetero: heteroskedastic disturbances across units
SerDep: controlling for serial dependence in errors (lag trunc = 5)
hadrilm lnPTMQ (stata command)
Hadri (2000) panel unit root test for lnPTMQ
with 191 observations on 6 cross-sectional units
eps Z(mu) P-value Z(tau) P-value
Homo 67.356 0.0000 54.293 0.0000
Hetero 85.159 0.0000 82.480 0.0000
SerDep 15.167 0.0000 12.885 0.0000
H0: all 6 timeseries in the panel are stationary processes
Homo: homoskedastic disturbances across units
Hetero: heteroskedastic disturbances across units
SerDep: controlling for serial dependence in errors (lag trunc = 5)
N.B: lnPTMQ is the dependent variable in my model and D.lnPTMQ is the first difference.
Thanks in advance.
Naceur Khraief
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
