mtest: Performs an "exact" test using Monte Carlo trials for... In HWxtest: Exact Tests for Hardy-Weinberg Proportions

Description

Given a set of genotype counts, mtest examines a large number of possible outcomes with the same set of allele counts. For each table, it computes four test statistics and compares them with the observed values. It returns the total probability of all tables with test statistics as “extreme” or more so than the observed. It can also plot a histogram of one of the statitistics if histobins is greater than zero. More about these four test statistics and other information can be found in the vignette. This function will not usually be called directly by the user. Instead, call hwx.test with method set to either “auto” or “monte”.

Usage

 1 2 mtest(c, ntrials = 1e+05, statName = "LLR", histobins = 0, histobounds = c(0, 0), showCurve = T, safeSecs = 100, detail = 2)

Arguments

 c A matrix containing the genotype counts. It should be a square matrix, but only the lower-left half is used. ntrials the number of random trials to perform statName can be “LLR”, “Prob”, “U”, or “Chisq” depending on which one is to be ploted. Note that P values for all four are computed regardless of which one is specified with this parameter. histobins If 0 no histogram is plotted. If 1 or TRUE a histogram with 500 bins is plotted. If set to a number greater than 1, a histogram with histobins is plotted. histobounds A vector containing the left and right boundaries for the histogram's x axis. If you leave this as the default, c(0,0), then mtest will compute reasonable bounds to include most of the distribution. showCurve whether to show a blue curve indicating the asymptotic (chi squared) distribution. This only works for LLR and Chisq safeSecs After this many seconds the calculation will be aborted. This is a safety valve to prevent attempts to compute impossibly large sets of tables. detail Determines how much detail is printed. If it is set to 0, nothing is printed (useful if you use mtest programmatically.).

Value

mtest returns a list components

 \$ Pvalues The four computed P values corresponding to the test statistics: LLR, Prob, U and Chisq in that order. \$ tableCount placeholder \$ SE Standard errors for the P values. These come from the binomial. \$ observed The four observed statistics in the same order as above \$ ntrials The number of tables examined during the calculation \$ genotypes The input matrix of genotype counts \$ alleles The allele counts m corresponding to the input genotype counts \$ statID Which test statistic was used if a histogram was plotted \$ histobins If greater than zero, the number of bins to use for the histogram \$ histobounds The lower and upper limits of the test statistic in the histogram \$ histoData Vector of histobins values for the histogram \$ showCurve Whether the asymptotic curve should be plotted with the histogram

References

The methods are described by Engels, 2009. Genetics 183:1431.