discrete

discrete —

Synopsis




MODEL       logit_probit                    (const int *list,
                                             double ***pZ,
                                             DATAINFO *pdinfo,
                                             int ci,
                                             gretlopt opt,
                                             PRN *prn);
MODEL       logistic_model                  (const int *list,
                                             double ***pZ,
                                             DATAINFO *pdinfo,
                                             const char *param);
int         logistic_ymax_lmax              (const double *y,
                                             const DATAINFO *pdinfo,
                                             double *ymax,
                                             double *lmax);

Description

Details

logit_probit ()

MODEL       logit_probit                    (const int *list,
                                             double ***pZ,
                                             DATAINFO *pdinfo,
                                             int ci,
                                             gretlopt opt,
                                             PRN *prn);

Computes estimates of the discrete model specified by list, using an estimator determined by the value of ci. In the binary case, uses the BRMR auxiliary regression; see Davidson and MacKinnon. If the dependent variable is not binary but is discrete and has a minimum value of 0, we do ordered logit/probit.

`list` :	dependent variable plus list of regressors.
`pZ` :	pointer to data matrix.
`pdinfo` :	information on the data set.
`ci` :	command index: if = `LOGIT`, perform logit regression, otherwise perform probit regression.
`opt` :	if includes `OPT_R` form robust (QML) estimates of standard errors and covariance matrix, in binary case.
`prn` :	printing struct in case additional information is wanted (`OPT_V`).
Returns :	a MODEL struct, containing the estimates.

logistic_model ()

MODEL       logistic_model                  (const int *list,
                                             double ***pZ,
                                             DATAINFO *pdinfo,
                                             const char *param);

Estimate the model given in list using the logistic transformation of the dependent variable.

`list` :	dependent variable plus list of regressors.
`pZ` :	pointer to data matrix.
`pdinfo` :	information on the data set.
`param` :	may contain "ymax=value" for user setting of the asymptotic maximum of the dependent variable.
Returns :	a MODEL struct, containing the estimates.

logistic_ymax_lmax ()

int         logistic_ymax_lmax              (const double *y,
                                             const DATAINFO *pdinfo,
                                             double *ymax,
                                             double *lmax);

`y` :
`pdinfo` :
`ymax` :
`lmax` :
Returns :