Random effects GLS regression (Panel Data)

[Margaux Rensink]

Dear all,
The Wald Chi2 variable is missing. Any one got an idea on how I can fix this?
Your help is highly appreciated.

Ps: the output is in the attachment.

[Carlo Lazzaro]

Margaux:
as per FAQ, please post what you typed and what Stata gave you back via CODE delimiters.
Most listers (me too) do not open attachment due to the risk of dowloading active contents.

[Margaux Rensink]

To declare the dataset as panel data:

xtset Code year, yearly

stata gave back:

panel variable: Code (strongly balanced) time variable: year, 2004 to 2016 delta: 1 year

after I did a random effects regression:

 xtreg ROA CSR RISK SIZE, re

output stata:

Random-effects GLS regression        Number of obs     =    1,913
Group variable: Code        Number of groups  =    162

R-sq:        Obs per group:
within  = 0.0300        min =    6
between = 0.1646        avg =    11.8
overall = 0.0514        max =    13

        Wald chi2(2)      =    .
corr(u_i, X)   = 0 (assumed)        Prob > chi2       =    .

            
ROA       Coef.   Std. Err.        z    P>z     [95% Conf.    Interval]
            
CSR    .0000425   .0000239        1.78   0.075    -4.29e-06    .0000894
RISK    .0834198   .0104967        7.95   0.000     .0628467    .1039929
SIZE   -2.71e-12   7.20e-12        0.38   0.707    -1.68e-11    1.14e-11
_cons   -.0119851   .0068382        1.75   0.080    -.0253876    .0014175
            
sigma_u   .02663021
sigma_e   .07309587
rho   .11717574   (fraction    of    variance due to u_i)

Is this ok?

[Margaux Rensink]

Thank you very much for your help!

[Carlo Lazzaro]

Margaux:
what does

mat list e(V)

give you back?

[Margaux Rensink]

symmetric e(V)[4,4]
CSR        RISK    SIZE    _cons
CSR   1.280e-09
RISK  -6.461e-08   .00050086
SIZE  -9.055e-17   1.658e-14    2.456e-22
_cons  -2.643e-07  -.00011344    -2.782e-14    .00009756

[Carlo Lazzaro]

Margaux:
please take a look at -help j_robustsingular- and see if any clue to spot your problem comes alive.
See also: https://stats.stackexchange.com/ques...ssing-in-stata