 Usage:  (gamma1, gamma2) = sssm (vectY,matX,nameX{,auto,vObs,vSel,nbslices})  
 
 Input:

  vectY                  n x 1 matrix containing the observed response variable. 
                         (The missing values are assumed to be equal to zero.) 
                         
  matX                   n x p matrix containing the observed explanatory 
                         variables. 
                         
  nameX                  p x 1 matrix containing the names of the explanatory 
                         variables. 
                         
  auto                   optional parameter, (by default, auto=1). 
                         If (auto=0), then you have to specify the vectors "vObs" 
                         and "vSel", else (auto=1) you have to specify your selection of 
                         the explanatory variables used in the outcome equation 
                         and in the selection equation during the execution of 
                         this macro in two selectitem windows. 
                         
  vObs                   optional parameter if auto=0, 
                         otherwise, p x 1 matrix containing the indicator vector of the explanatory 
                         variables used in the outcome equation. 
                         (1 if the explanatory variable is selected, 0 otherwise.) 
                         
  vSel                   optional parameter if auto=0, 
                         otherwise, p x 1 matrix containing the indicator vector of the explanatory 
                         variables used in the selection equation. 
                         (1 if the explanatory variable is selected, 0 otherwise.) 
                         
  nbslices               optional parameter, scalar which gives the number of 
                         slices (for the non missing yi observations) in the S.I.R. step. 
                         (By default, the number of slices is 5 (+ 1 slice for the 
                         missing yi cases).) 
                         
                         
 Output:

  gamma1                 estimate of the observation slope vector. 
                         
  gamma2                 estimate of the selection slope vector. 
                         
--------------------------------------------------------------
(C) MD*TECH Method and Data Technologies, 17.8.2000
