Dear Statalist members:
Could somebody help me to interpretate the result of -nnest- test?.
There is not much about this test and I don't know which model is
better:
. nnest iitt lpdit ltarifa lavgdp ldkl ldcap ldedu ltc lrydcost
lroyalsale (ltarifa lavgdp ldcap ldedu ltc lrydcost lroyalsale
lavgestb ldpcgdp ladvsale)
<>
M1 : Y = a + Xb with X = [lpdit ltarifa lavgdp ldkl ldcap ldedu ltc
lrydcost lroyalsale]
M2 : Y = a + Zg with Z = [ltarifa lavgdp ldcap ldedu ltc lrydcost
lroyalsale lavgestb ldpcgdp ladvsales]
<>J test for non-nested models <>
H0 : M1 t(880) 7.39163
H1 : M2 p-val 0.00000 <>
H0 : M2 t(879) 0.72921
H1 : M1 p-val 0.46606 <>
Cox-Pesaran test for non-nested models <>
H0 : M1 N(0,1) -26.60836
H1 : M2 p-val 0.00000 <>
H0 : M2 N(0,1) -0.78036
H1 : M1 p-val 0.21759
What I understand is that the model 2 is superior to model 1 because
in both tests, J and Cox-Pesaran the p-val is significant. Is that
correct?
Thanks
Maritza
__________________________________________________
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
http://mail.yahoo.com
*
* 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/
