xttest0 (BP-LM test) results invalid?

[Martin Dite]

Dear colleagues,

I am working on my panel data, trying to determine which method is optimal. After running the hausman test, I concluded that it should be either random effect or pooled OLS, but when I run the BP-LM test the result is suspicious as it tells me that is it pooled OLS with Prob > chibar2 = 1.0

xttest0

Breusch and Pagan Lagrangian multiplier test for random effects

dT1[bankno,t] = Xb + u[bankno] + e[bankno,t]

Estimated results:
| Var sd = sqrt(Var)
---------+-----------------------------
dT1 | 1.87812 1.370445
e | 1.955134 1.398261
u | 0 0

Test: Var(u) = 0
chibar2(01) = 0.00
Prob > chibar2 = 1.0000

Could anyone give me a hint on what could be the problem?

Thank you!

[Martin Dite]

For future reference- in the end the issue was in the fact that my RE model degenerated to pooled OLS model and explanation with solution can be found here:

http://www.statalist.org/forums/foru...he-same-as-ols

[amira elshal]

Dear Martin,

As in your case, I ran the Breusch and Pagan Lagrangian multiplier test for random effects to test for random effects. I got the results below although I did not difference my data. Prob > chibar2 = 1.0000 because u = 0. Please advise on how I shall proceed.

Breusch and Pagan Lagrangian multiplier test for random effects

childmort[id,t] = Xb + u[id] + e[id,t]

Estimated results:
Var sd = sqrt(Var)
---------+-----------------------------
childmort 17.83105 4.222683
e 17.64855 4.201018
u 0 0

Test: Var(u) = 0
chibar2(01) = 0.00
Prob > chibar2 = 1.0000

Thank you.

Kind regards,
Amira

[Carlo Lazzaro]

Amira double posted #3 at http://www.statalist.org/forums/foru...chibar2-1-0000