Re: st: fixed effect, autocorrelation heteroskedasticity

[ghislain dutheil <gdutheil@gmail.com>]

Clive Nicholas a �crit :
> Ghislain Dutheil replied:
>
> [...]
>
>   
>> I don't how to know if there is a lots or a few CCE ?
>>     
>
> -findit xttest2-
>
>   
here my result for
xtreg y x1 X2, fe
xttest2

Correlation matrix of residuals:

__e1     __e2     __e3     __e4     __e5    __e6    __e7     __e8
__e1   1.0000
__e2   0.4354   1.0000
__e3   0.8449   0.2948   1.0000
__e4   0.6628   0.8764   0.5417   1.0000
__e5   0.8675   0.3527   0.8478   0.5885   1.0000
__e6   0.1343  -0.5371   0.1315  -0.3669  -0.0648    1.0000
__e7  -0.3547  -0.5082  -0.2219  -0.4867  -0.2920    0.4555    1.0000
__e8  -0.2355   0.1982  -0.2051   0.0071  -0.4291    0.1075    0.3012   
1.0000
__e9   0.8887   0.7226   0.7897   0.8505   0.8174    -0.1959    -0.4882  
-0.1455
__e10   0.3466  -0.2502   0.4175  -0.0682   0.3010    0.6139    0.4551  
-0.0574
__e11   0.4187   0.0301   0.5038   0.1637   0.6561    -0.2718    
-0.3045  -0.7594
__e12  -0.3787  -0.7519  -0.2388  -0.6900  -0.4225    0.8034    0.6334   
0.2224
__e13   0.8482   0.8011   0.6996   0.8726   0.7683    -0.2838    
-0.5251  -0.1061
__e14   0.5254   0.7513   0.4224   0.7461   0.5672    -0.5492    
-0.3811  -0.2019

__e9    __e10    __e11    __e12    __e13    __e14
__e9   1.0000
__e10   0.1259   1.0000
__e11   0.4186   0.1151   1.0000
__e12  -0.6329   0.4178  -0.4208   1.0000
__e13   0.9531   0.0465   0.3803  -0.7013   1.0000
__e14   0.7229  -0.0379   0.4088  -0.8348   0.7865    1.0000

Breusch-Pagan LM test of independence: chi2(91) =    1329.057,    Pr = 
0.0000
Based on 52 complete observations

So I think i have lot of ...

And I will use PCSE but David is saying that's may be it's not a good 
idea with dummies .

So if somebody knows

Thanks


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/