But don't forget at first to sort the data--on an ascending order--by the variable supposed to be the cause of heteroskedasticity... ;-)  (by clicking on Data/Sort data)

artur


Sven Schreiber a écrit :
It seems to me that this is a good candidate for a packaged function, no?

cheers,
sven

Ignacio Diaz-Emparanza schrieb:
  
On Miércoles, 24 de Junio de 2009 22:12:57 Jav escribió:
    
Hi everyone. I've been using Gretl for almost two months and I think is a
really great software for econometric analysis. I want to request another
test for Heteroskedasticity, I see there's some tests already in Gretl, but
I don't see the Goldfeld-Quandt contrast and since I'm not that good on
Gretl's commands I'm having a hard time trying to do that test.

Well, that's pretty much my request... thanks to all.
      
You have an example on how to do the Goldfeld-Quandt test in /File/script 
files/user file/Practice file/Ramanathan/ps8-3

It is not very long so I include it here:

<script>
# PS8.3, for Example 8.4, Goldfeld-Quandt test
open data8-1 
genr LNSALARY=ln(SALARY)
genr YRS2 = YEARS*YEARS
# estimate log quadratic model for first 75 observations 
smpl 1 75
ols LNSALARY const YEARS YRS2 
genr var1 = $sigma*$sigma
genr df1 = $df
# estimate log quadratic model for last 75 observations 
smpl 148 222
ols LNSALARY const YEARS YRS2 
genr var2 = $sigma*$sigma
genr df2 = $df
# compute F-statistic and pvalue for test 
smpl 1 222
genr Fc = var2/var1
pvalue F df1 df2 Fc 
</script>

    


_______________________________________________
Gretl-users mailing list
Gretl-users@lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users