LOGSCALE
effect-list < /options > ;
You use the LOGSCALE statement to model the logarithm of the distribution scale parameter as a function of explanatory variables. A MODEL statement must also be present to specify the model for the distribution location parameter. effect-list is a list of variables in the input data set representing the values of the independent variables in the model for each observation, and combinations of variables representing interaction terms. It can contain any variables or combination of variables in the input data set. It can contain the same variables as the MODEL statement, or it can contain different variables. The variables in the effect-list can be any combination of indicator variables named in a CLASS statement and continuous variables. The coefficients of the explanatory variables are estimated by maximum likelihood.
Table 16.18 lists the options available for the LOGSCALE statement.
Table 16.18: LOGSCALE Statement Options
Option |
Option Description |
---|---|
INITIAL=number-list |
Specifies initial values for log-scale regression parameters other than the intercept term. |
INTERCEPT=number <INTINIT> |
Specifies an initial or fixed value of the intercept parameter, depending on whether INTINIT is present. |