semTools (version 0.2-0)

runMI: 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.

Usage

runMI(data.mat,data.model, m, miPackage="Amelia", digits=3, seed=12345, 
    std.lv = FALSE, estimator = "ML", group = NULL, group.equal = "", ...)

Arguments

data.mat

Data frame with missing observations or a list of data frames where each data frame is one imputed data set (for imputed data generated outside of the function). If a list of data frames is supplied, then other options can be left at the default.

data.model

lavaan syntax for the the model to be analyzed.

m

Number of imputations wanted.

miPackage

Package to be used for imputation. Currently runMI only uses Amelia or mice for imputation.

digits

Number of digits to print in the results.

seed

Random number seed to be used in imputations.

std.lv

lavaan option. If TRUE, the metric of each latent variable is determined by fixing their variances to 1.0. If FALSE, the metric of each latent variable is determined by fixing the factor loading of the first indicator to 1.0.

estimator

lavaan option. The estimator to be used. Can be one of the following: "ML" for maximum likelihood, "GLS" for generalized least squares, "WLS" for weighted least squares (sometimes called ADF estimation), "MLM" for maximum likelihood estimation with robust

group

lavaan option. A variable name in the data frame defining the groups in a multiple group analysis.

group.equal

lavaan option. A vector of character strings. Only used in a multiple group analysis. Can be one or more of the following: "loadings", "intercepts", "means", "regressions", "residuals", "residual.covariances", "lv.variances" or "lv.covariances", specifyin

...

Other arguments to be passed to the imputation package

Value

• runMI returns a list with pooled fit indices, estimates, standard errors and fraction missing information.
• fit
  Pooled fit information. The first set of fit information are simply averaged across imputations and are not trustworthy. The second set of fit information, is a pooled Chi-square statistic based on Li, Meng, Raghunathan, & Rubin (1991)
• parameters
  Pooled parameter estimates and standard errors. Wald statistics and p values are computed from the pooled estimates and standard errors. Also contains two estimates of Fraction of Missing Information (FMI). The first estimate of FMI (FMI.1) is asymptotic FMI and the second estimate of FMI (FMI.2) is corrected for small numbers of imputation

References

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. 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 <- runMI(HSMiss, HS.model, m = 3)

HSMiss2 <- cbind(HSMiss, school = HolzingerSwineford1939[,"school"])
out2 <- runMI(HSMiss2, HS.model, m = 3, group="school", noms="school")

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(datsimMI$imputations, mod, group="group")