ideal_pcc: Determine the Ideal PCC

In HDDesign: Sample Size Calculation for High Dimensional Classification Study

Description

Determine the probability of correct classification (PCC) for a study employing the ideal classifier. The ideal classifier is constructed assuming we know exactly the important features and their effect size. The ideal PCC is the uppper bound of the PCC of any linear classifiers.

Usage

ideal_pcc(mu0, m, p1 = 0.5)

Arguments

mu0	The effect size of the important features.
m	The number of the important features.
p1	The prevalence of the group 1 in the population, default to 0.5.

Value

The PCC of the ideal classifier.

Author(s)

Meihua Wu <[e-mail]> Brisa N. Sanchez <[e-mail]> Peter X.K. Song <[e-mail]> Raymond Luu <[e-mail]> Wen Wang <[e-mail]>

References

Dobbin, Kevin K., and Richard M. Simon. 2007. "Sample Size Planning for Developing Classifiers Using High-dimensional DNA Microarray Data." Biostatistics 8 (1) (January 1): 101-117.

Examples

ideal_pcc(mu0=0.4, m=10, p1 = 0.6) 
#return: 0.8999055

Example output

[1] 0.8999055

HDDesign documentation built on May 2, 2019, 6:41 a.m.