Nonpmodelcheck: An R package for nonparametric lack-of-fit testing and variable selection

Adriano Zanin Zambom, Michael G. Akritas

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

We describe the R package NonpModelCheck for hypothesis testing and variable selection in nonparametric regression. This package implements functions to perform hypothesis testing for the significance of a predictor or a group of predictors in a fully nonparametric heteroscedastic regression model using high-dimensional one-way ANOVA. Based on the p values from the test of each covariate, three different algorithms allow the user to perform variable selection using false discovery rate corrections. A function for classical local polynomial regression is implemented for the multivariate context, where the degree of the polynomial can be as large as needed and bandwidth selection strategies are built in.

Original languageEnglish (US)
Article number10
JournalJournal of Statistical Software
Volume77
Issue number1
DOIs
StatePublished - 2017

All Science Journal Classification (ASJC) codes

  • Software
  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Fingerprint Dive into the research topics of 'Nonpmodelcheck: An R package for nonparametric lack-of-fit testing and variable selection'. Together they form a unique fingerprint.

Cite this