CVST: constructCVSTModel – R documentation

Pricing

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

Get Started for Free

Documentation

CVST

constructCVSTModel

Setup for a CVST Run.

Description

This is an helper object of type CVST.setup conatining all necessary parameters for a CVST run.

Usage

constructCVSTModel(steps = 10, beta = 0.1, alpha = 0.01,
similaritySignificance = 0.05, earlyStoppingSignificance = 0.05,
earlyStoppingWindow = 3, regressionSimilarityViaOutliers = FALSE)

Arguments

`steps`	Number of steps CVST should run
`beta`	Significance level for H0.
`alpha`	Significance level for H1.
`similaritySignificance`	Significance level of the similarity test.
`earlyStoppingSignificance`	Significance level of the early stopping test.
`earlyStoppingWindow`	Size of the early stopping window.
`regressionSimilarityViaOutliers`	Should the less strict outlier-based similarity measure for regression tasks be used.

Value

A CVST.setup object suitable for fastCV.

Author(s)

Tammo Krueger <tammokrueger@googlemail.com>

References

Tammo Krueger, Danny Panknin, and Mikio Braun. Fast cross-validation via sequential testing. Journal of Machine Learning Research 16 (2015) 1103-1155. URL http://jmlr.org/papers/volume16/krueger15a/krueger15a.pdf.