prop_stronger_sign {MetaUtility}

Return sign test point estimate of proportion of effects above or below threshold.

Description

Internal function not intended for user to call. Uses an extension of the sign test method of Wang et al. (2010) to estimate the proportion of true (i.e., population parameter) effect sizes in a meta-analysis that are above or below a specified threshold of scientific importance. See important caveats in the Details section of the documentation for the function prop_stronger.

Usage

prop_stronger_sign(
  q,
  yi,
  vi,
  ci.level = 0.95,
  tail = NA,
  R = 2000,
  return.vectors = FALSE
)

Arguments

q

Population effect size that is the threshold for "scientific importance"

yi

Study-level point estimates

vi

study-level variances

ci.level

Confidence level as a proportion

tail

above for the proportion of effects above q; below for the proportion of effects below q.

R

Number of simulation iterates to estimate null distribution of sign test statistic

return.vectors

Should all percents and p-values from the grid search be returned?

References

Wang R, Tian L, Cai T, & Wei LJ (2010). Nonparametric inference procedure for percentiles of the random effects distribution in meta-analysis. Annals of Applied Statistics.