calcCliffdTestStatistics {reproducer}

calcCliffdTestStatistics

Description

This function is a helper function for meta-analysis of experiments using Cliff's d as an effect size. It returns the 100*(1-alpha/2)

Usage

calcCliffdTestStatistics(
  d.value,
  d.variance,
  d.df = 0,
  alpha = 0.05,
  alternative = "two.sided"
)

Arguments

d.value

The overall estimate of Cliff's d from a group of effect sizes to be meta-analysed

d.variance

The estimate of the variance of the overall estimate of Cliff's d

d.df

The total degrees of freedom for the set of effect sizes. If d.df>0, the pvalues and significance test use the t-distribution probability values. If d.df=0 (default) the pvalues and significance test use the normal distribution probability values. The confidence intervals are always based on the normal probability values.

alpha

The significance level used to control the significance tests and calculation of confidence limits (default 0.05).

alternative

Specifies the type of significance test and can take the values "two.sided", "less" or "greater" (default "two.sided").

Value

d.tvalue The value of the t-statistic

d.pvalue The p-value of the t-test if the parameter d.df>0, or the normal probability value if d.df=0

d.ci.lower The lower 100*(1-alpha/2)

d.ci.upper The upper 100*(1-alpha/2)

d.sig The significance of the statistical test of the d.tvalue return value at the alpha level for one sided tests and aplha/2 for two sided tests as specified by the input parameter alternative

Author(s)

Barbara Kitchenham and Lech Madeyski

Examples

aveCliffd=mean(c(0.84,0.2,-0.04,0.44,0.76))
aveCliffdvar=sum(c(0.04,0.18,0.21,0.15,0.06))/25
df=45
calcCliffdTestStatistics(d.value=aveCliffd,d.variance=aveCliffdvar,d.df=df)
# A tibble: 1 x 5
#   d.tvalue d.pvalue d.ci.lower d.ci.upper d.sig
#      <dbl>    <dbl>      <dbl>      <dbl> <lgl>
# 1     2.75  0.00855     0.0923      0.692 TRUE