Introduction
LRMoE is a package tailor-made for actuarial applications which allows actuarial researchers and practitioners to model and analyze insurance loss frequencies and severities using the Logit-weighted Reduced Mixture-of-Experts (LRMoE) model. The flexibility of LRMoE models is theoretically justified in Fung et al. (2019), and an application of LRMoE for modelling correlated insurance claim frequencies is in Fung et al. (2019).
The package LRMoE offers several new distinctive features which are motivated by various actuarial applications and mostly cannot be achieved using existing packages for mixture models. Key features include: * A wider coverage on frequency and severity distributions and their zero inflation; * The flexibility to vary classes of distributions across components; * Parameter estimation under data censoring and truncation; * A collection of insurance rate making and reserving functions; and * Model selection and visualization tools.
While LRMoE was initially developed for actuarial application, this package also allows for customized expert functions for various modelling problems outside of the insurance context.
Package Installation and Usage
While we prepare for submitting the package to Comprehensive R Archive Network (CRAN), the package is available in this github repository. The package manual documenting all functions in the package can also be found in the current repository.
In R, the LRMoE package can be downloaded and installed by running the following code.
To get started, see here.
Issue Report and Suggestions
Issues and suggestions can be posted on https://github.com/sparktseung/LRMoE/issues.
