MODEL Subcommand (SURVREG AFT command)

MODEL is an optional subcommand to specify the model options and settings. It could optionally followed by model effects and initial values. If no model effects are specified, all the variables specified after SURVREG AFT BY and WITH will be used as main effects. If specified, the variable(s) must be contained in the factors specified after SURVREG AFT BY or the covariates specified after SURVREG AFT WITH. A factor effect could optionally be followed by multiple numeric values specified within brackets. If specified, the adjacent values could be separated by a comma, a blank space, or blank spaces. Each one will be used as the initial value for the estimation of the corresponding coefficient of the category. A default value, denoted by DEFAULT, could be specified at a given position to and assigned to a certain category. The values specified within brackets cannot be all DEFAULT. If the number of values (including the default values) does not match the one of the categories (including the reference category), the procedure will ignore all the values specified for the factor and assign default values to all the categories. A covariate effect could optionally be followed by a single numeric value specified within brackets. If specified, it will be used as the initial value for the estimation of the corresponding coefficient. Specifying DEFAULT within brackets is not allowed for a covariate.

DISTRIBUTION

An optional parameter to specify the distribution of the survival time. WEIBULL is the setting by default, which will specify Weibull distribution. EXPONENTIAL will specify exponential distribution. LOG_NORMAL will specify log-normal distribution. LOG_LOGISTIC will specify log-logistic distribution.

LEFTTRUNCATE

An optional parameter to specify the variable for left truncation. If specified, it must be a single and numeric variable, and cannot be the same as the dependent variable(s), covariates, or factors. The process will be ignored if two dependent variables are specified.

SIGMA

An optional parameter to control the setting of the scale parameter. SE is the setting by default, which will use the standard error of the corresponding ordinary least squares regression as the initial value. INV_SE will use the reciprocal of the standard error. If a single numeric value is specified, the value will be used as the initial value. If specified, it must be greater than 0.

INTERCEPT

An optional parameter to specify the initial value of the intercept term. If specified, it must be a single numeric value, and cannot be 0.