alpha.xci: Alpha Confidence Interval

In multicon: Multivariate Constructs

Description

Computes the exact confidence interval for Cronbach's alpha if the item scores have a joint multivariate distribution, following the method outlined by Koning & Franses (2003).

Usage

alpha.xci(x, k, n, CI = 0.95)

Arguments

x	An alpha coefficient to compute a confidence interval around.
k	The number of items on which alpha was computed.
n	The number of sampling units (observations) on which alpha was computed.
CI	A numeric element between .00 and 1.00 indicating the desired confidence level.

Details

Koning & Franses (2003) describe several methods for computing confidence intervals around Cronbach's alpha coefficient. This function returns what Koning and Franses (2003) refer to as the exact confidence interval for alpha if the item scores have a joint multivariate distribution. The confidence interval is asymptomic and not necessarily symmetrical. For more info, see Koning and Franses (2003).

Value

comp1	Lower Limit of confidence interval
comp2	Upper Limit of confidence interval

Author(s)

Ryne A. Sherman

References

Koning, A. J. & Franses, P. H. (2003). Confidence Intervals for Cronbach's Alpha Coefficient values. ERIM Report Series Reference No. ERS-2003-041-MKT. Available at SSRN: http//ssrn.com/abstract=423658

See Also

alpha.aci vector.alpha

Examples

	#Compute the asymptotic CI for an observed Cronbach's alpha 
	#of .7 on 200 observaitons for a 10 item scale'
alpha.xci(.7,10,200)

multicon documentation built on May 2, 2019, 3:18 a.m.