likCIESCRD {MBESS}R Documentation

Compute the likelihood-based confidence interval of the effect size in cluster randomized design

Description

Compute the likelihood-based confidence interval (Cheung, 2009) by running the multilevel model using the structural equation modeling with the data in wide format (Bauer, 2003). This program uses the OpenMx package (Boker et al., 2011) to run the likelihood-based confidence interval of the effect size. See further details at Pornprasertmanit and Schneider (2010, submitted).

Usage

likCIESCRD(datawide, ylab, xlab, zwlab=NULL, zblab=NULL, estype=1, 
	iccy=0.25, es=0.5, totalvar=1, covariate=FALSE, iccz=0.25, r2within=0.5, 
	r2between=0.5, totalvarz = 1, conflevel=0.95)

Arguments

datawide

The nested data in wide format

ylab

The label of the dependent variable

xlab

The label of the independent variable

zwlab

The label of the within-level covariate variables

zblab

The label of the between-level covariate variable

iccy

The intraclass correlation of the dependent variable

es

The amount of effect size

estype

The type of effect size. There are only three possible options: 0 = the effect size using total standard deviation, 1 = the effect size using the individual-level standard deviation (level 1), 2 = the effect size using the cluster-level standard deviation (level 2)

totalvar

The amount of total variance in the dependent variable

covariate

If TRUE, a single covariate is included into the model. If FALSE, the no-covariate model is used.

iccz

The intraclass correlation of the covariate (used when covariate = TRUE). If iccz = 0, the within-level covariate will be only used. If iccz = 1, the between-level covariate will be only used.

r2within

The proportion of variance explained in the within level (used when covariate = TRUE)

r2between

The proportion of variance explained in the between level (used when covariate = TRUE)

totalvarz

The total variance of the covariate (used when covariate = TRUE)

conflevel

The desired level of confidence for the confidence interval

Value

The likelihood-based confidence interval of effect size

Author(s)

Sunthud Pornprasertmanit (University of Kansas; psunthud@ku.edu)

References

Bauer, D. J. (2003). Estimating multilevel linear models as structural equation models. Journal of Educational and Behavioral Statistics, 28, 135-167.

Boker, S., M., N., Maes, H., Wilde, M., Spiegel, M., Brick, T., et al. (2011). OpenMx: An open source extended structural equation modeling framework. Psychometrika, 76, 306-317.

Cheung, M. W.-L. (2009). Constructing approximate confidence intervals for parameters with structural constructing approximate confidence intervals for parameters with structural equation models. Structural Equation Modeling, 16, 267-294.

Pornprasertmanit, S., & Schneider, W. J. (2010). Efficient sample size for power and desired accuracy in Cohen's d estimation in two-group cluster randomized design (Master Thesis). Illinois State University, Normal, IL.

Pornprasertmanit, S., & Schneider, W. J. (submitted). Accuracy in parameter estimation in two-condition cluster randomized design.

Examples

## Not run: 
datWide <- createDataCRDWide(100, 50, 5, iccy=0.25, es=0.5, estype = 0, 
	totalvar=1, covariate=FALSE)
likCIESCRD(datWide, ylab=c("y1", "y2", "y3", "y4", "y5"), xlab="x", 
	estype=0, iccy=0.25, es=0.5, totalvar=1, covariate=FALSE)

## End(Not run)
[Package MBESS version 3.3.3 Index]