Alternative HCT Procedure to Choose P-Value Threshold Based on Beta Distribution of P-Values.

Share:

Description

This procedure chooses the p-value threshold for feature selection in a similar fashion to hct_empirical. However, it is based on the Beta distribution of the p-values. Only the features whose p-values are less than the thresold will be included in the classifier.

Usage

1
hct_beta(pvalue, p, n)

Arguments

pvalue

A vector containing the p*alpha_0 smallest p-values; typically alpha_0=0.10

p

The number of the features in total.

n

The total sample size for the two groups.

Details

Refer to Sanchez, et al (2016), Section 3 and supplementary materials.

Value

The p-value threshold for feature selection. Only the features whose p-values are less than the threshold will be included in the classifier.

Author(s)

Meihua Wu <meihuawu@umich.edu> Brisa N. Sanchez <brisa@umich.edu> Peter X.K. Song <pxsong@umich.edu> Raymond Luu <raluu@umich.edu> Wen Wang <wangwen@umich.edu>

References

Sanchez, B.N., Wu, M., Song, P.X.K., and Wang W. (2016). "Study design in high-dimensional classification analysis." Biostatistics, in press.

Examples

1
2
hct_beta(pvalue=0.10,p=500,n=80)
# 0.1