The SEVERITY Procedure
- Overview
-
Getting Started
-
Syntax
-
DetailsPredefined DistributionsCensoring and TruncationParameter Estimation MethodParameter InitializationEstimating Regression EffectsLevelization of Classification VariablesSpecification and Parameterization of Model EffectsEmpirical Distribution Function Estimation MethodsStatistics of FitDefining a Severity Distribution Model with the FCMP ProcedurePredefined Utility FunctionsScoring FunctionsCustom Objective FunctionsMultithreaded ComputationInput Data SetsOutput Data SetsDisplayed OutputODS Graphics
-
ExamplesDefining a Model for Gaussian DistributionDefining a Model for the Gaussian Distribution with a Scale ParameterDefining a Model for Mixed-Tail DistributionsEstimating Parameters Using Cramér-von Mises EstimatorFitting a Scaled Tweedie Model with RegressorsFitting Distributions to Interval-Censored DataDefining a Finite Mixture Model That Has a Scale ParameterPredicting Mean and Value-at-Risk by Using Scoring FunctionsScale Regression with Rich Regression Effects
- References
The WEIGHT statement specifies the name of a variable whose values represent the weight of each observation. PROC SEVERITY associates a weight of w to each observation, where w is the value of the WEIGHT variable for the observation. If the weight value is missing or less than or equal to 0, then the observation is ignored and a warning is written to the SAS log. When you do not specify the WEIGHT statement, each observation is assigned a weight of 1. If you specify more than one WEIGHT statement, then the last statement is used.
The weights are normalized so that they add up to the actual sample size. In particular, the weight of each observation is
multiplied by 
, where N is the sample size.