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

# st: Re: gcause

 From Christopher Baum <[email protected]> To r_sbia <[email protected]> Subject st: Re: gcause Date Wed, 2 Oct 2013 14:41:43 +0000

```I see no problem:

. ssc inst gcause
checking gcause consistency and verifying not already installed...
installation complete.

. webuse grunfeld,clear

. gcause2 invest mvalue if company==5, lags(2) regress
Granger causality test                              Sample: 1937 to 1954
obs = 18
H0: mvalue does not Granger-cause invest

F( 2, 13) =    5.53
Prob > F =   0.0183

chi2(2) =   15.32      (asymptotic)
Prob > chi2 =  0.0005      (asymptotic)

Source |       SS       df       MS              Number of obs =      18
-------------+------------------------------           F(  4,    13) =    5.12
Model |  2262.37632     4  565.594081           Prob > F      =  0.0106
Residual |  1435.08208    13  110.390929           R-squared     =  0.6119
Total |   3697.4584    17  217.497553           Root MSE      =  10.507

------------------------------------------------------------------------------
invest |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
invest |
L1. |  -.3284522   .3034551    -1.08   0.299     -.984027    .3271226
L2. |  -.3382965   .2898293    -1.17   0.264    -.9644347    .2878417
|
mvalue |
L1. |   .2019076   .0953418     2.12   0.054    -.0040658    .4078809
L2. |   .0754127   .1190404     0.63   0.537    -.1817585    .3325838
|
_cons |     41.713   14.39976     2.90   0.012     10.60422    72.82178
------------------------------------------------------------------------------

gcause2 does not have a help file because it is the same command as gcause. It just allows application to a single panel unit, which gcause does not.

Kit

Kit Baum   |   Boston College Economics & DIW Berlin   |   http://ideas.repec.org/e/pba1.html
An Introduction to Stata Programming  |   http://www.stata-press.com/books/isp.html
An Introduction to Modern Econometrics Using Stata  |   http://www.stata-press.com/books/imeus.html

On Oct 1, 2013, at 2:17 AM, r_sbia <[email protected]> wrote:

> Dear Professor,
> I hope this email finds well. I am trying to use your gcause routine.  The new version includes gcause2 command to be used for panel. However the gcause2 has no help file and when I use it iam having error message "option/required". My command line is:
> Gcause2 var1 var2 if company! =1, lag (#) regress.
> Ps: the data set is panel (invest2) and I tsset  the data.
>
>
> Sent from Samsung Mobile

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