Overview (QUANTILE REGRESSION command)
QUANTILE REGRESSION dependent_varname [BY factor_list] [WITH covariate_list] is
a required command to invoke the quantile regression procedure. A single numeric dependent variable
is required. BY and WITH are followed by an optional list of
factors and covariates, respectively. Note that either the intercept term or at least one predictor
is required to run the analysis.
Options
- Analysis options
- You can specify the regression percentile, the estimation method, numerical method settings, post-estimation attributes, and the significance level for computing credible intervals.
- Model design
- You can specify the model design for the analysis, which includes target variables, factor variables, covariates, regression weights, and model effects.
- Display settings
- You can specify which estimates to output, as well as plot and tabulation output options for the effects, prediction lines and tables.
- Save settings
- You can specify to save the predicted value of responses, residuals, and the lower/upper bound of prediction intervals.
- Export options
- You can specify to export the covariance and correlation matrices for parameter estimates, and specify a target file to generate the PMML file.
Basic specification
QUANTILE REGRESSION dependent_varname [BY factor_list] [WITH covariate_list]is a required command to invoke the quantile regression procedure.
Subcommand order
- The subcommands can be named in any order.
Syntax rules
- In cases where duplicated values are specified, only unique values are used, and a warning message is generated to indicate that all duplicated values are excluded from the analysis.
- Either the intercept term or at least one predictor is required to run the analysis.