MCPerm (version 1.1.4)

chisq.TradPerm: A permutation test for multiple chisq.test correction in case/control association study

Description

A permutation test for multiple chisq.test correction in case/control association study.

Usage

chisq.TradPerm(genotypeLine, affectionLine, fromCol, naString, sep, repeatNum = 1000)

Arguments

genotypeLine

a matrix with one row containing information of specified snp: basic information(e.g. SNP ID number,chromo,position) and genotype of observed individuals. See below for details.

affectionLine

a matrix having the same dimension with parameter 'genotypeLine' contain the affection status (case or control) of each individual and other information. The affection status must be in same columns with the genotypes in parameter 'genotypeLine'. See below for details.

fromCol

a positive integer, the start column of genotype data in parameter 'genotypeLine'.

naString

a character string for NA values of genotype.

sep

character separator used to divide genotype between alleles "Allele1Allele2".

repeatNum

an integer(default 1000) specifying the number of replicates for permutation test.

Value

pValue

the p value for the test.

obsStatistic

the value of the chi-squared test statistic for the true data.

obsP

the p value of the chisq.test for the true data.

permStatistic

a matrix with one row and 'repeatNum' columns, the value of the chi-squared test statistic for permutation data.

permP

a matrix with one row and 'repeatNum' columns, the p value of the chisq.test for permutation data.

Details

For case/control association study for snps, the permutation test proceeds as follows:

1) Combine the observations from all the samples;

2) Shuffle them and rearrangements of the labels(case/control) on the observed data;

3) Record the genotype frequency of case and control samples, respectively;

4) Calculate the statistic of interest;

5) Repeat many times(at least 1000) to obtain the distribution of the statistic;

6) Determine how often the resampled statistic of interest is as extreme as the observed value of the same statistic.

The basic information of sepcified snp for 'genotypeLine' and the other information of individuals for 'affectionLine' must be located in the matrix of previous columns; and also can not be included,thus fromCol=1.

The genotypes of the specified snp, the stored alleles is considered to be ordered, i.e. "C/T" is unequivalent to "T/C".

The affection status can be character string or numeric, but the symbol for control must be in advantageous alphabetical order (e.g. control=0,case=1).

References

William S Noble(Nat Biotechnol.2009): How does multiple testing correction work?

Edgington. E.S.(1995): Randomization tests, 3rd ed.

See Also

OR, OR.TradPerm, OR.MCPerm, Armitage, Armitage.TradPerm, Armitage.MCPerm, chisq.test, chisq.MCPerm, fisher.test, fisher.TradPerm, fisher.MCPerm, meta, meta.TradPerm, meta.MCPerm, permuteGenotype, rhyper, permuteGenotypeCount, genotypeStat

Examples

## import example data
#data(genotypeData)
## get the first line: affection state for samples
# data1=genotypeData[1,,drop=FALSE]
# get the second line: genotype data for a sepcifed snp
# data2=genotypeData[2,,drop=FALSE]
# chisq.TradPerm(data2,data1,fromCol=2,naString="?_?",sep="_",repeatNum=5)

## matrix
# genotypeLine=matrix(c("rs12","AA","TT","TA","AA","TT","AA","AA"),nrow=1)
# affectionLine=matrix(c("Affection",1,1,1,0,0,0,0),nrow=1)
# chisq.TradPerm(genotypeLine,affectionLine,fromCol=2,naString="NN",sep="",repeatNum=5)

## connect file
# datafile=file("F:/data.txt","r")
## get the affection status for samples, read the first line from "data.txt"
# dataLine1=readLins(datafile,n=1)
# dataLine1=t(unlist(strsplit(dataLine1,sep="")))
## get the genotype line for samples, read the second line form "data.txt"
# dataLine2=readLines(datafile,n=1)
# dataLine2=t(unlist(strsplit(dataLine2,sep="")))
# chisq.TradPerm(dataLine2,dataLine1,fromCol=2,naString="NN",sep="",repeatNum=1000)