pvalHist: Plot histogram of log p-values in table

Description Usage Arguments Details See Also Examples

View source: R/pHist.R

Description

Graphical exploration of extreme p-values from quartet hypothesis tests, to aid in choosing critical values for hypothesis tests. Log base 10 of p-values exceeding some minimum are plotted, to explore gaps in the tail of the distribution.

Usage

1
pvalHist(pTable, model, pmin = 0)

Arguments

pTable

a quartet table with p-values, such as from NANUQ, quartetTreeTestInd, or quartetStarTestInd

model

one of "T1", "T3", or "star", where pTable contains a column p_model of p-values

pmin

include only p-values above pmin in the histogram

Details

Since logarithms are plotted, p-values close to 0 will appear as negative numbers of large magnitude, putting the tail of the distribution to the left in the histogram.

When exploring possible critical values for the hypothesis tests in the NANUQ algorithm, use model= "T3" to choose values for alpha which distinguish treelikeness from hybridization, and model= "star" to choose values for beta which distinguish polytomies from resolved trees. In general, alpha should be chosen to be small and beta to be large so that most quartets are interpreted as resolved trees.

See Also

NANUQ, NANUQdist

Examples

1
2
3
pTable=NANUQ(system.file("extdata","dataYeastRokas",package="MSCquartets"), 
       alpha=0.05, beta=.95, outfile = file.path(tempdir(), "NANUQdist"))
pvalHist(pTable,"T3")

MSCquartets documentation built on Jan. 8, 2021, 2:10 a.m.