Learn R Programming

selectMeta (version 1.0.8)

DearBeggMonotonePvalSelection: Compute simulation-based p-value to assess null hypothesis of no selection

Description

This function computes a simulation-based $p$-value to assess the null hypothesis of no selection. For details we refer to Rufibach (2011, Section 6).

Usage

DearBeggMonotonePvalSelection(y, u, theta0, sigma0, lam = 2, M = 1000, maxiter = 1000, test.stat = function(x){return(min(x))})

Arguments

y
Normally distributed effect sizes.
u
Associated standard errors.
theta0
Initial estimate for $\theta$.
sigma0
Initial estimate for $\sigma$.
lam
Weight of the first entry of $w$ in the likelihood function. Should be the same as used to generate res.
M
Number of runs to compute $p$-value.
maxiter
Maximum number of iterations of differential evolution algorithm. Increase this number to get higher accuracy.
test.stat
A function that takes as argument a vector and returns a number. Defines the test statistic to be used on the estimated selection function $w$.

Value

pval
The computed $p$-value.
res.mono
The monotone estimates for each simulation run.
mono0
The monotone estimates for the original data.
Ti
The test statistics for each simulation run.
T0
The test statistic for the original data.
ran.num
Matrix that contains the generated $p$-values.

References

Rufibach, K. (2011). Selection Models with Monotone Weight Functions in Meta-Analysis. Biom. J., 53(4), 689--704.

See Also

This function is illustrated in the help file for DearBegg.