hierCredibility-class function

Class "hierCredibility" of fitted hierarchical credibility models

Class "hierCredibility" of fitted hierarchical credibility models

## S3 method for class 'hierCredibility' print(x, ...) ## S3 method for class 'hierCredibility' summary(object, ...) ## S3 method for class 'hierCredibility' fitted(object, ...)

Arguments

  • x: an object of class hierCredibility
  • ...: currently ignored.
  • object: an object of class hierCredibility

Returns

The function hierCredibility returns an object of class hierCredibility, which has the following slots:

  • call: the matched call

  • type: Whether additive or multiplicative hierarchical credibility model is used.

  • Variances: The estimated variance components. s2 is the estimated variance of the individual contracts, tausq the estimate of Var(V[j])Var(V[j]) and nusq is the estimate of Var(V[jk])Var(V[jk]).

  • Means: The estimated averages at the portfolio level (intercept term μ\mu), at the first hierarchical level (bar(Y)[%.%j%.%%.%]zbar(Y)[\%.\% j \%.\% \%.\%]^z) and at the second hierarchical level (bar(Y)[%.%jk%.%]bar(Y)[\%.\% jk \%.\%]).

  • Weights: The weights at the first hierarchical level z[j%.%]z[j\%.\%] and at the second hierarchical level w[%.%jk%.%]w[\%.\%jk\%.\%].

  • Credibility: The credibility weights at the first hierarchical level q[j%.%]q[j\%.\%] and at the second hierarchical level z[jk]z[jk].

  • Premiums: The overall expectation widehat(μ)widehat(\mu), sector expectation widehat(V)[j]widehat(V)[j] and group expectation widehat(V)[jk]widehat(V)[jk].

  • Relativity: The estimated random effects widehat(U)[j]widehat(U)[j] and widehat(U)[jk]widehat(U)[jk] of the sector and group, respectively.

  • RawResults: Objects of type data.table with all intermediate results.

  • fitted.values: the fitted mean values, resulting from the model fit.

S3 methods

  • print:: Prints the call, the estimated variance parameters and the unique number of categories of the hierarchical MLF. The ... argument is currently ignored. Returns an invisible copy of the original object.
  • summary:: In addition to the output of the print.hierCredibility function, the summary function prints the random effect estimates as well. Returns an invisible copy of the original object.
  • fitted:: Returns the fitted values.

See Also

hierCredibility