Multiply impute and analyze data using lavaan

Description

This function takes data with missing observations, multiple imputes the data, runs a SEM using lavaan and combines the results using Rubin's rules. Note that parameter estimates and standard errors are pooled by the Rubin's (1987) rule. The chi-square statistics and the related fit indices are pooled by the method described in "chi" argument. SRMR is calculated based on the average model-implied means and covariance matrices across imputations.

Usage

runMI(model, data, m, miArgs=list(), chi="all", miPackage="Amelia", 
	seed=12345, fun, nullModel = NULL, includeImproper = FALSE, ...) 
cfa.mi(model, data, m, miArgs=list(), miPackage="Amelia", chi="all", 
	seed=12345, nullModel = NULL, includeImproper = FALSE, ...)
sem.mi(model, data, m, miArgs=list(), miPackage="Amelia", chi="all",  
	seed=12345, nullModel = NULL, includeImproper = FALSE, ...)
growth.mi(model, data, m, miArgs=list(), miPackage="Amelia", chi="all", 
	seed=12345, nullModel = NULL, includeImproper = FALSE, ...)
lavaan.mi(model, data, m, miArgs=list(), miPackage="Amelia", chi="all", 
	seed=12345, nullModel = NULL, includeImproper = FALSE, ...)

Arguments

Value

The lavaanStar object which contains the original lavaan object (where the appropriate parameter estimates, appropriate standard errors, and chi-squares are filled), the additional fit-index values of the null model, which need to be adjusted to multiple datasets, and the information from pooling multiple results.

Author(s)

Alexander M. Schoemann (East Carolina University; schoemanna@ecu.edu) Patrick Miller (University of Notre Dame; pmille13@nd.edu) Sunthud Pornprasertmanit (psunthud@gmail.com) Mijke Rhemtulla (University of Amsterdam; M.T.Rhemtulla@uva.nl) Alexander Robitzsch (Federal Institute for Education Research, Innovation, and Development of the Austrian School System, Salzburg, Austria; a.robitzsch@bifie.at) Craig Enders (Arizona State University; Craig.Enders@asu.edu) Mauricio Garnier Villarreal (University of Kansas; mgv@ku.edu) Yves Rosseel (Ghent University; Yves.Rosseel@UGent.be)

References

Asparouhov T. & Muthen B. (2010).Chi-Square Statistics with Multiple Imputation. Technical Report. www.statmodel.com.

Li, K.H., Meng, X.-L., Raghunathan, T.E. and Rubin, D.B. (1991). Significance Levels From Repeated p-values with Multiply-Imputed Data. Statistica Sinica, 1, 65-92.

Meng, X.L. & Rubin, D.B. (1992). Performing likelihood ratio tests with multiply-imputed data sets. Biometrika, 79, 103 - 111.

Rubin, D.B. (1987) Multiple Imputation for Nonresponse in Surveys. J. Wiley & Sons, New York.

Examples

library(lavaan)

HS.model <- ' visual  =~ x1 + x2 + x3
              textual =~ x4 + x5 + x6
              speed   =~ x7 + x8 + x9 '

HSMiss <- HolzingerSwineford1939[,paste("x", 1:9, sep="")]
randomMiss <- rbinom(prod(dim(HSMiss)), 1, 0.1)
randomMiss <- matrix(as.logical(randomMiss), nrow=nrow(HSMiss))
HSMiss[randomMiss] <- NA

out <- cfa.mi(HS.model, data=HSMiss, m = 3, chi="all")
summary(out)
inspect(out, "fit")
inspect(out, "impute")

## Not run: 
##Multiple group example
HSMiss2 <- cbind(HSMiss, school = HolzingerSwineford1939[,"school"])
out2 <- cfa.mi(HS.model, data=HSMiss2, m = 3, miArgs=list(noms="school"), chi="MR", group="school")
summary(out2)
inspect(out2, "fit")
inspect(out2, "impute")

##Example using previously imputed data with runMI
library(Amelia)

modsim <- '
f1 =~ 0.7*y1+0.7*y2+0.7*y3
f2 =~ 0.7*y4+0.7*y5+0.7*y6
f3 =~ 0.7*y7+0.7*y8+0.7*y9'

mod <- '
f1 =~ y1+y2+y3
f2 =~ y4+y5+y6
f3 =~ y7+y8+y9'

datsim <- simulateData(modsim,model.type="cfa", meanstructure=TRUE, 
	std.lv=TRUE, sample.nobs=c(200,200))
randomMiss2 <- rbinom(prod(dim(datsim)), 1, 0.1)
randomMiss2 <- matrix(as.logical(randomMiss2), nrow=nrow(datsim))
datsim[randomMiss2] <- NA
datsimMI <- amelia(datsim,m=3, noms="group")

out3 <- runMI(mod, data=datsimMI$imputations, chi="LMRR", group="group", fun="cfa")
summary(out3)
inspect(out3, "fit")
inspect(out3, "impute")

# Categorical variables
popModel <- "
f1 =~ 0.6*y1 + 0.6*y2 + 0.6*y3 + 0.6*y4
y1 ~*~ 1*y1
y2 ~*~ 1*y2
y3 ~*~ 1*y3
y4 ~*~ 1*y4
f1 ~~ 1*f1
y1 | 0.5*t1
y2 | 0.25*t1
y3 | 0*t1
y4 | -0.5*t1
"
analyzeModel <- "
f1 =~ y1 + y2 + y3 + y4
y1 ~*~ 1*y1
y2 ~*~ 1*y2
y3 ~*~ 1*y3
y4 ~*~ 1*y4
"
dat <- simulateData(popModel, sample.nobs  = 200L)
miss.pat <- matrix(as.logical(rbinom(prod(dim(dat)), 1, 0.2)), nrow(dat), ncol(dat))
dat[miss.pat] <- NA
out5 <- cfa.mi(analyzeModel, data=dat, ordered=paste0("y", 1:4), m = 3, 
	miArgs=list(ords = c("y1", "y2", "y3", "y4")))
summary(out5)
inspect(out5, "fit")
inspect(out5, "impute")


## End(Not run)

Results