[Gretl-devel] Another quantile regression bug

[Allin Cottrell]

On Thu, 15 May 2008, andreas.rosenblad at ltv.se wrote:

> I have found another bug for the quantile regression function 
> (again using the Windows snapshot from 2008-05-14):
> 
> 1. Using the GUI, open the Ramanathan data file "data 4-1".
> 2. Choose Model > Robust estimation > Quantile regression...
> 3. Set price as dependent and srft, bedrms, baths as independent
> 4. .1 .2 .3 .4 .5 .6 .7 .8 .9 as desired quantiles
> 
> Output...
> 
>       VARIABLE      TAU    COEFFICIENT      LOWER        UPPER
> 
>   const              0.1      1.13915     -1.#IND0     -1.#IND0
>                      0.2    -0.856990     -1.#IND0      296.952

Hmm, for tau = .10, R reports the confidence intervals as 
(-1.797693e+308, 1.797693e+308) for all coefficients.  There is a 
certain lack of error checking in the underlying Fortran code.

I think this is now fixed in CVS and a new snapshot.  Thanks for
testing!

Allin.