Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

# st: Re: Normality and Granger Causality in Panel Data

 From "D. Demetriou" To statalist@hsphsun2.harvard.edu Subject st: Re: Normality and Granger Causality in Panel Data Date 03 Apr 2012 17:43:39 +0100

```Kit and Nick,

```
Thank you for all your comments and suggestion on how to deal with normality and granger causality in Panel Data stractures.
```
```
Chrostopher in his last email suggested that because my panel is short(T=10 and N=9) I should't use a cluster-robust estimator. However, STATA does implemented onw automatically as you can see below the heading just above the estimation table. is there any way to disable this??
```

```
. xi: xtreg publicprov1 hownership incvars popabove60 ILO regsegr primsector i.wave
```, fe vce(robust)
```
```note: w10 omitted because of collinearity

```
Fixed-effects (within) regression Number of obs = 80 Group variable: region Number of groups = 9
```
R-sq: within = 0.9154 Obs per group: min = 8
between = 0.1848 avg = 8.9
overall = 0.2093 max = 9

```
F(8,8) = . corr(u_i, Xb) = -0.9213 Prob > F = .
```
```
(Std. Err. adjusted for 9 clusters in region) ------------------------------------------------------------------------------
```            |               Robust
```
publicprov1 | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+----------------------------------------------------------------
``` hownership | -.1460149 .041091 -3.55 0.007 -.2407709 -.0512588
incvars | -.0324381 .025144 -1.29 0.233 -.0904203 .0255441
popabove60 | .0431907 .0277384 1.56 0.158 -.0207741 .1071556
ILO | .00225 .026478 0.08 0.934 -.0588084 .0633083
regsegr | .0564663 .0228579 2.47 0.039 .0037559 .1091768
primsector | -.0458808 .0555693 -0.83 0.433 -.1740238 .0822621

Yours,

DD
*
*   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/
```