R help - Mar 2009 - Problem with dummy variables controlling for years

Hello everybody,

I'm running a panel regression with dummy variables controlling for years.
While this works fine for most of my models, in some cases I get the error
message "In sqrt(diag(object$vcov)) : NaNs wurden erzeugt" and missing
results for some or all of my year dummies:

                                  Estimate Std. Error z-value Pr(>|z|)   
year2000                     -7.48e-02         NA      NA       NA    
year2001                     -6.65e-02         NA      NA       NA    
year2002                     -6.61e-02         NA      NA       NA    
year2003                     -6.49e-02         NA      NA       NA    
year2004                     -5.95e-02         NA      NA       NA    
year2005                     -6.08e-02         NA      NA       NA    

Despite this inconsistency, the other variables as well as my R-quared look
alright.

Can anybody explain me what the reason for this problem is and how it
affects the regression? Are the results still usable in spite of the NaNs?

Thank you very much!

Best,
Johannes


-- 
View this message in context:
http://www.nabble.com/Problem-with-dummy-variables-controlling-for-years-tp22294013p22294013.html
Sent from the R help mailing list archive at Nabble.com.

Hi Johannes.
My guess is that you will get no Std. Error, if you have only 1 observation
for that year.
Could that be the case ?




On Mon, Mar 2, 2009 at 8:41 PM, Johannes Habel
<johannes.habel@gmx.de>wrote:
>
> Hello everybody,
>
> I'm running a panel regression with dummy variables controlling for
years.
> While this works fine for most of my models, in some cases I get the error
> message "In sqrt(diag(object$vcov)) : NaNs wurden erzeugt" and
missing
> results for some or all of my year dummies:
>
>                                  Estimate Std. Error z-value Pr(>|z|)
> year2000                     -7.48e-02         NA      NA       NA
> year2001                     -6.65e-02         NA      NA       NA
> year2002                     -6.61e-02         NA      NA       NA
> year2003                     -6.49e-02         NA      NA       NA
> year2004                     -5.95e-02         NA      NA       NA
> year2005                     -6.08e-02         NA      NA       NA
>
> Despite this inconsistency, the other variables as well as my R-quared look
> alright.
>
> Can anybody explain me what the reason for this problem is and how it
> affects the regression? Are the results still usable in spite of the NaNs?
>
> Thank you very much!
>
> Best,
> Johannes
>
>
> --
> View this message in context:
>
http://www.nabble.com/Problem-with-dummy-variables-controlling-for-years-tp22294013p22294013.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>


-- 
----------------------------------------------


My contact information:
Tal Galili
Phone number: 972-50-3373767
FaceBook: Tal Galili
My Blogs:
www.talgalili.com
www.biostatistics.co.il

	[[alternative HTML version deleted]]