| Title: | Uses Brown's method to combine p-values from dependent tests |
|---|---|
| Description: | Combining P-values from multiple statistical tests is common in bioinformatics. However, this procedure is non-trivial for dependent P-values. This package implements an empirical adaptation of Brown’s Method (an extension of Fisher’s Method) for combining dependent P-values which is appropriate for highly correlated data sets found in high-throughput biological experiments. |
| Authors: | William Poole |
| Maintainer: | David Gibbs <[email protected]> |
| License: | MIT + file LICENSE |
| Version: | 1.35.0 |
| Built: | 2024-11-29 05:24:10 UTC |
| Source: | https://github.com/bioc/EmpiricalBrownsMethod |
This data is used in the unit tests and usage examples. There are four items:
allPvals, dat, pathways, and randData. allPvals is a data.frame of p-values for the spearman correlation between CHD4 and each of the 45 genes.
dat is the gene expression data corresponding to genes in allPvals.
pathways is a data.frame listing gene membership for 3 biochemical pathways.
randData is a gaussian generated data set, emphasizing dependence among variables. Independent Var [line 1] are 25 samples from a unit normal distribution. Depedent Var 1-10 [line 2-11] are each 25 samples drawn from a 10 dimensional normal distribution centered at the origin with off diagonal terms a=0.25. The P values from a pearson correlation between the independent var and each dependent var are combined.
data(ebmTestData)data(ebmTestData)
Rdata object
data objects in the environment
GEO and generated.
Combining P-values from multiple statistical tests is common in bioinformatics. However, this procedure is non-trivial for dependent P-values. This package provides an empirical adaptation of Brown’s Method (an extension of Fisher’s Method) for combining dependent P-values which is appropriate for highly correlated data sets, like those found in high-throughput biological experiments.
empiricalBrownsMethod(data_matrix, p_values, extra_info)empiricalBrownsMethod(data_matrix, p_values, extra_info)
data_matrix |
An m x n numeric matrix with m variables in rows and n samples in columns. |
p_values |
A numeric vector of p-values with length m. |
extra_info |
boolean, TRUE additionally returns the p-value from Fisher's method, the scale factor c, and the new degrees of freedom from Brown's Method |
The output is a list containing list(P_Brown=p_brown, P_Fisher=p_fisher, Scale_Factor_C=c, DF_Brown=df_brown)
P_test |
p-value for Brown's method |
P_Fisher |
p-value for Fisher's method |
Scale_Factor |
the scale factor c |
DF |
the degrees of freedom used in Brown's method |
## restore the saved values to the current environment data(ebmTestData) glypGenes <- pathways$gene[pathways$pathway == "GLYPICAN 3 NETWORK"] glypPvals <- allPvals$pvalue.with.CHD4[match(glypGenes, allPvals$gene)]; glypDat <- dat[match(glypGenes, dat$V1), 2:ncol(dat)]; empiricalBrownsMethod(data_matrix=glypDat, p_values=glypPvals, extra_info=TRUE);## restore the saved values to the current environment data(ebmTestData) glypGenes <- pathways$gene[pathways$pathway == "GLYPICAN 3 NETWORK"] glypPvals <- allPvals$pvalue.with.CHD4[match(glypGenes, allPvals$gene)]; glypDat <- dat[match(glypGenes, dat$V1), 2:ncol(dat)]; empiricalBrownsMethod(data_matrix=glypDat, p_values=glypPvals, extra_info=TRUE);
Combining P-values from multiple statistical tests is common in bioinformatics. However, this procedure is non-trivial for dependent P-values. This package provides an implementation of Kost's Method for combining dependent P-values which is appropriate for highly correlated data sets, like those found in high-throughput biological experiments.
kostsMethod(data_matrix, p_values, extra_info)kostsMethod(data_matrix, p_values, extra_info)
data_matrix |
An m x n numeric matrix with m variables in rows and n samples in columns. |
p_values |
A numeric vector of p-values with length m. |
extra_info |
boolean, TRUE additionally returns the p-value from Fisher's method, the scale factor c, and the new degrees of freedom from Brown's Method |
The output is a list containing list(P_test=p_brown, P_Fisher=p_fisher, Scale_Factor_C=c, DF=df)
P_test |
p-value for Kost's method |
P_Fisher |
p-value for Fisher's method |
Scale_Factor |
the scale factor c |
DF |
the degrees of freedom |
## restore the saved values to the current environment data(ebmTestData) glypGenes <- pathways$gene[pathways$pathway == "GLYPICAN 3 NETWORK"] glypPvals <- allPvals$pvalue.with.CHD4[match(glypGenes, allPvals$gene)] glypDat <- as.matrix(dat[match(glypGenes, dat$V1), 2:ncol(dat)]) kostsMethod(data_matrix=glypDat, p_values=glypPvals, extra_info=TRUE);## restore the saved values to the current environment data(ebmTestData) glypGenes <- pathways$gene[pathways$pathway == "GLYPICAN 3 NETWORK"] glypPvals <- allPvals$pvalue.with.CHD4[match(glypGenes, allPvals$gene)] glypDat <- as.matrix(dat[match(glypGenes, dat$V1), 2:ncol(dat)]) kostsMethod(data_matrix=glypDat, p_values=glypPvals, extra_info=TRUE);