mbfpval: Maximum Bayes Factor

In woraphonyamaka/MBF: Maximum Bayes Factor

Maximum Bayes Factor

Description

This function is used to do the p-value calibration

Usage

MBF(t,method)

Arguments

t	t-statistic
method	Select the calibration method i.e. "goodman", "edwards", "sellke1","sellke2","pvalue".

Details

This package introduces an alternative approaches for the p-value namely Minimum Bayes Factors (MBF), for find the evidence against a point null hypothesis under the linear regression context. MBF is the one counterpart to p-value offered by the Bayesian approach, which relies solely on the observed sample to provide direct probability statements about the parameters of interest. This approach lie in the same range as p-values, which facilitates us to make the comparison.the MBF is interpreted following the Goodman (1999) labelled intervals. As a result, a BF10 between 1-1/3 is considered weak evidence for H1 , form 1/3 – 1/10 considered moderate evidence for H1, 1/10 – 1/30 is considered substantial evidence, form 1/30 to 1/100 Strong, form 1/100 to 1/300 Very strong, and <1/300 Decisive.

Value

MBF	Maximum Bayes Factor value

Author(s)

Woraphon Yamaka

References

Goodman, S. N. (1999). Toward evidence-based medical statistics. 1: The P value fallacy. Annals of internal medicine, 130(12), 995-1004.

Held, L., & Ott, M. (2016). How the maximal evidence of p-values against point null hypotheses depends on sample size. The American Statistician, 70(4), 335-341.

Stern, H. S. (2016). A test by any other name: P values, Bayes factors, and statistical inference. Multivariate behavioral research, 51(1), 23-29.

Examples

t=2  # t-statistic
MBF(t,method="goodman")

woraphonyamaka/MBF documentation built on Aug. 16, 2022, 4:34 p.m.