Re: st: Mata, receiving conformability error in maximising the logistic log-likelihood function

[Christophe Kolodziejczyk <ck.statalist@gmail.com>]

Dear Elya

When b is a scalar b*x is comformable.
But if b is a 1 x 2 (row)vector and x is a N x 2 matrix, then
b*x is not.
try rather x*b' instead

Best
Christophe



2014-03-31 8:59 GMT+02:00 Eilya Torshizian <e.torshizian@auckland.ac.nz>:
> Dear Statalisters,
>
> I am writing a very simple mata code for maximising a logistic log-likelihood function. I aim at estimating the "y = xb" regression function, where y is a binary variable. The following code works fine if the independent variable (x) would be a single column vector, i.e. x=[.,1]:
>
>         void LOG(todo, b, y, x, LOG, g,H)
>         {
>         LOG = y:*(-ln(1:+exp(b*x))) :+ (1 :- y):*(b*x :- ln(1:+exp(b*x)))
>         }
>         p = J(1,cols(x),1)
>         i=optimize_init()
>         optimize_init_evaluator(i, &LOG())
>         optimize_init_evaluatortype(i, "gf0")
>         optimize_init_params(i,p)
>         optimize_init_technique(i,"nr")
>         optimize_init_argument(i,1,y)
>         optimize_init_argument(i,2,x)
>         optimize(i)
>
> However, if x would be [.,2] I will get a conformability error. I would appreciate your help.
>
> Thanks for your time,
> Eilya.
>
>
> *
> *   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/



-- 
Christophe Kolodziejczyk
Research Fellow

AKF, Anvendt KommunalForskning
Danish Institute of Governmental Research
Købmagergade 22
DK-1150 København K

*
*   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/