The RELIABILITY Procedure
- Overview
-
Getting Started
Analysis of Right-Censored Data from a Single PopulationWeibull Analysis Comparing Groups of DataAnalysis of Accelerated Life Test DataWeibull Analysis of Interval Data with Common Inspection ScheduleLognormal Analysis with Arbitrary CensoringRegression ModelingRegression Model with Nonconstant ScaleRegression Model with Two Independent VariablesWeibull Probability Plot for Two Combined Failure ModesAnalysis of Recurrence Data on RepairsComparison of Two Samples of Repair DataAnalysis of Interval Age Recurrence DataAnalysis of Binomial DataThree-Parameter WeibullParametric Model for Recurrent Events DataParametric Model for Interval Recurrent Events Data -
SyntaxPrimary StatementsSecondary StatementsGraphical Enhancement StatementsPROC RELIABILITY StatementANALYZE StatementBY StatementCLASS StatementDISTRIBUTION StatementEFFECTPLOT StatementESTIMATE StatementFMODE StatementFREQ StatementINSET StatementLOGSCALE StatementLSMEANS StatementLSMESTIMATE StatementMAKE StatementMCFPLOT StatementMODEL StatementNENTER StatementNLOPTIONS StatementPROBPLOT StatementRELATIONPLOT StatementSLICE StatementSTORE StatementTEST StatementUNITID Statement
-
DetailsAbbreviations and NotationTypes of Lifetime DataProbability DistributionsProbability PlottingNonparametric Confidence Intervals for Cumulative Failure ProbabilitiesParameter Estimation and Confidence IntervalsRegression Model Statistics Computed for Each Observation for Lifetime DataRegression Model Statistics Computed for Each Observation for Recurrent Events DataRecurrence Data from Repairable SystemsODS Table NamesODS Graphics
- References
The FREQ statement specifies a variable that provides frequency counts for each observation in the input data set. If n is the value of the FREQ variable in the input data set for an observation, then that observation is weighted by n. The log-likelihood function for maximum likelihood estimation is multiplied by n. If n is not an integer, the integer part of n is used in creating probability plots.
You can also use the FREQ statement in conjunction with the NENTER statement to specify interval-censored data having a special structure; these data are called readout data. The FREQ statement specifies a variable in the input data set that determines the number of units failing in each interval. See the section Weibull Analysis of Interval Data with Common Inspection Schedule for an example that uses the FREQ statement with readout data.
You can also use the FREQ statement in conjunction with the NENTER statement to specify recurrent events data when the event times are grouped into intervals, rather than being observed exactly. The FREQ statement specifies a variable in the input data set that determines the number of events in each interval.
You can use the FREQ statement with the MCFPLOT and MODEL statements for exact age data to provide frequency counts for entire recurrence histories. If n is the value of the FREQ variable at a censor time, the history of recurrences for the corresponding system is replicated independently n times. Values of the FREQ variable at times other than censor times are not used; they can be any value or missing without affecting the analysis.