ci.contr: Compute confidence interval for contrast d

In mcfanda/cpower: Power analysis for contrasts

Description

Return the confidence intervals computed by scaling the confidence intervals of the noncentrality parameter. The confidence intervals are computed based on selected function in MBESS.

Usage

ci.contr(cont, d, n, scale = "g", conf.level = 0.95)

Arguments

cont	vector of contrast weights.
d	standardized mean differences.
n	cell size (for each group)
scale	method to scale d.
conf.level	width of the confidence interval, default=.95

Details

Compute the confidence interval based on the Steiger and Fouladi (1997) method

The parameter scale controls the method used to scale the effect size d.

1. scale="g" assumes scaling by dividing 2*d by the sum of absolute coefficients

2. scale="z" assumes scaling by dividing d by the square-root of the sum of squares of the coefficients

3. numeric any constant that multiplies the unscaled d to obtain the scaled d

The confidence intervals are computed based on selected function in MBESS: in particular conf.limits.nct and ci.sc. Results are scaled to the standardized effect size required.

Value

confidence intervals of class "conf.intervals".

Author(s)

Marcello Gallucci, [e-mail]

References

Kelley, K. (2007). Confidence intervals for standardized effect sizes: Theory, application, and implementation. Journal of Statistical Software, 20 (8), 1<e2><80><93>24.

Examples

cont<-c(-3,-1,1,3)
means<-c(10,12,10,12)
d<-d.contr(cont,means = means,sd=2,scale = "g")
ci.contr(cont,d=d,scale = "g",n=100)

mcfanda/cpower documentation built on May 28, 2019, 1 p.m.