Am 15.04.2025 um 15:25 schrieb Sven Schreiber:
it looks as if regls (Lasso...) isn't checking for missings that
happen somewhere in the middle of the data. Implicitly this is
acknowledged by comments in the example code snippets in the regls
help document ("without missing values..." etc.). I just saw some
internal data errors happening because of that. I guess it would be
good if regls checked for such missings and then fails more gracefully.
Another regls (regls_multiprint) problem, although unrelated to the one
above (I think; after missings have been taken care of):
lfrac R^2 sum(|b|) df criterion
1.00000 0.0000 0.000000 0
Uneindeutiger Matrixindex # ---> ambiguous index
*** Fehler in Schleife in Funktion regls_multiprint
printf " %#10g\n", rb.crit[i]
Perhaps this is a corner case? R2=0? Does somebody have a successful
regls_multiprint invocation?
thanks
sven