fisher.rskew.test: Perform a test for right skew p values between 0.00 and 0.05.

In roblanf/pcurver: Tools to analyse distributions of P-values from the published literature

Description

This function uses Fisher's test (implemented in fisher.method () function of the MADAM package) to ask whether the p values in the range 0.00 to 0.05 are more right skewed than you would expect (i.e. bunched up towards zero). This function replicates an analysis described in Simonsohn et al (2013, see references). If you use it, please cite that paper and the MADAM package (see references).

Usage

fisher.rskew.test(p)

Arguments

p	a vector of p values between 0.0 and 0.05 (inclusive)
...	additional expressions passed to fisher.method() function from the MADAM package.

Value

This method returns a data frame containing the following columns:

S	The test statistic from Fisher's test
p	The p value from Fisher's test
num.p	The number of p values used to compute the test statistic
df	The number of degrees of freedom

References

Simonsohn, Uri and Nelson, Leif D. and Simmons, Joseph P., P-Curve: A Key to the File Drawer (April 24, 2013). Journal of Experimental Psychology: General, Forthcoming. Available at SSRN: http://ssrn.com/abstract=2256237

Kugler KG, Mueller LA, Graber A: MADAM - An Open Source Toolbox for Meta-Analysis. Source Code for Biology and Medicine 2010, 5:3

See Also

binomial.all.test

Examples

p <- c(0.00001, 0.024, 0.002, 0.045, 0.00003, 0.021, 0.0001, 0.0000948, 0.0000002)
fisher.rskew.test(p)

roblanf/pcurver documentation built on May 27, 2019, 11:58 a.m.