oolax: oolax: Objected-orientated Loglikelihood Adjustment for...

In RuoqingYin/oolax: Object-orientated Loglikelihood Adjustment for Extreme Value Models

Description

Provides functions for loglikelihood adjustment for fitting extreme value models. The fitted object is from the package 'evd' and 'ismev' for extreme value analysis. The 'chandwich' package <https://cran.r-project.org/web/packages/chandwich/index.html> is used to construct the adjustment given the clustered data. The 'sandwich' package <https://cran.r-project.org/web/packages/sandwich/index.html> is used to adjust the robust covariance matrix estimators.

Details

The main function in the oolax package is alogLik, which provides loglikelihood adjustment for fitting Generalised Extreme Value (GEV) model and Threshold Modelling using generalised Pareto distribution (GPD). The adjustment is based on package evd and ismev. The user can make adjustment towards fitted obejcts such as fgev and fgev from the package evd, and gev.fit and gpd.fit from the package ismev. The metholdology is develped based on sandwich and chandwich.

See vignette("oolax-vignette", package = "oolax") for an overview and detailed examples about the package.

References

Chandler, R. E. and Bate, S. (2007). Inference for clustered data using the independence loglikelihood. Biometrika, 94(1), 167-183. http://dx.doi.org/10.1093/biomet/asm015

RuoqingYin/oolax documentation built on May 28, 2019, 12:20 p.m.