 Usage:  ll = glmll(code,mu,y{,opt})  
 
 Input:

  code                   text string, the short code for the model (e.g. 
                         "bilo" for logit or "noid" for ordinary OLS). 
                         
  mu                     n x 1, n x 2 or n x 3 matrix, either the response 
                         function, or sums of response function in the first 
                         column. 
                         In second and third column expressions needed for 
                         computation of deviance (typically sums of 
                         mu^2 or log(mu)). 
                         
  y                      n x 1, n x 2 or n x 3 matrix, either the response 
                         values, or sums of response values in the first 
                         column. 
                         In second and third column expressions needed for 
                         computation of deviance (typically sums of 
                         y^2 or log(y)). 
                         
  opt                    optional, a list with optional input. The macro 
                         "glmopt" can be used to set up this parameter. 
                         
  opt.phi                nuisance parameter, usually the dispersion 
                         parameter. If not given, only those parts of the 
                         log-likelihood are computed, which depend on the 
                         parameter of interest. 
                         
  opt.nbk                scalar, extra parameter k for negative binomial 
                         distribution. If not given, set to 1 (geometric 
                         distribution). 
                         
 Output:

  ll                     n x 1 matrix, log-likelihood. 
                         
--------------------------------------------------------------
(C) MD*TECH Method and Data Technologies, 17.8.2000
