semTools (version 0.5-1)

runMI: Fit a lavaan Model to Multiple Imputed Data Sets

Description

This function fits a lavaan model to a list of imputed data sets, and can also implement multiple imputation for a single data.frame with missing observations, using either the Amelia package or the mice package.

Usage

runMI(model, data, fun = "lavaan", ..., m, miArgs = list(),
  miPackage = "Amelia", seed = 12345)
lavaan.mi(model, data, ..., m, miArgs = list(), miPackage = "Amelia",
  seed = 12345)
cfa.mi(model, data, ..., m, miArgs = list(), miPackage = "Amelia",
  seed = 12345)
sem.mi(model, data, ..., m, miArgs = list(), miPackage = "Amelia",
  seed = 12345)
growth.mi(model, data, ..., m, miArgs = list(), miPackage = "Amelia",
  seed = 12345)

Arguments

model

The analysis model can be specified using lavaan model.syntax or a parameter table (as returned by parTable).

data

A data.frame with missing observations, or a list of imputed data sets (if data are imputed already). If runMI has already been called, then imputed data sets are stored in the @DataList slot, so data can also be a lavaan.mi object from which the same imputed data will be used for additional analyses.

fun

character. Name of a specific lavaan function used to fit model to data (i.e., "lavaan", "cfa", "sem", or "growth"). Only required for runMI.

…

additional arguments to pass to lavaan or lavaanList. See also lavOptions. Note that lavaanList provides parallel computing options, as well as a FUN argument so the user can extract custom output after the model is fitted to each imputed data set (see Examples). TIP: If a custom FUN is used and parallel = "snow" is requested, the user-supplied function should explicitly call library or use :: for any functions not part of the base distribution.

m

integer. Request the number of imputations. Ignored if data is already a list of imputed data sets or a lavaan.mi object.

miArgs

Addition arguments for the multiple-imputation function (miPackage). The arguments should be put in a list (see example below). Ignored if data is already a list of imputed data sets or a lavaan.mi object.

miPackage

Package to be used for imputation. Currently these functions only support "Amelia" or "mice" for imputation. Ignored if data is already a list of imputed data sets or a lavaan.mi object.

seed

integer. Random number seed to be set before imputing the data. Ignored if data is already a list of imputed data sets or a lavaan.mi object.

Value

A '>lavaan.mi object

References

Enders, C. K. (2010). Applied missing data analysis. New York, NY: Guilford.

Rubin, D. B. (1987). Multiple imputation for nonresponse in surveys. New York, NY: Wiley.

Examples

# NOT RUN {
 
# }
# NOT RUN {
## impose missing data for example
HSMiss <- HolzingerSwineford1939[ , c(paste("x", 1:9, sep = ""),
                                      "ageyr","agemo","school")]
set.seed(12345)
HSMiss$x5 <- ifelse(HSMiss$x5 <= quantile(HSMiss$x5, .3), NA, HSMiss$x5)
age <- HSMiss$ageyr + HSMiss$agemo/12
HSMiss$x9 <- ifelse(age <= quantile(age, .3), NA, HSMiss$x9)

## specify CFA model from lavaan's ?cfa help page
HS.model <- '
  visual  =~ x1 + x2 + x3
  textual =~ x4 + x5 + x6
  speed   =~ x7 + x8 + x9
'

## impute data within runMI...
out1 <- cfa.mi(HS.model, data = HSMiss, m = 20, seed = 12345,
               miArgs = list(noms = "school"))

## ... or impute missing data first
library(Amelia)
set.seed(12345)
HS.amelia <- amelia(HSMiss, m = 20, noms = "school", p2s = FALSE)
imps <- HS.amelia$imputations
out2 <- cfa.mi(HS.model, data = imps)

## same results (using the same seed results in the same imputations)
cbind(impute.within = coef(out1), impute.first = coef(out2))

summary(out1)
summary(out1, ci = FALSE, fmi = TRUE, add.attributes = FALSE)
summary(out1, ci = FALSE, stand = TRUE, rsq = TRUE)

## model fit. D3 includes information criteria
anova(out1)
## equivalently:
lavTestLRT.mi(out1)
## request D2
anova(out1, test = "D2")
## request fit indices
fitMeasures(out1)


## fit multigroup model without invariance constraints
mgfit.config <- cfa.mi(HS.model, data = imps, estimator = "mlm",
                       group = "school")
## add invariance constraints, and use previous fit as "data"
mgfit.metric <- cfa.mi(HS.model, data = mgfit1, estimator = "mlm"
                       group = "school", group.equal = "loadings")
mgfit.scalar <- cfa.mi(HS.model, data = mgfit1, estimator = "mlm"
                       group = "school",
                       group.equal = c("loadings","intercepts"))

## compare fit of 2 models to test metric invariance
## (scaled likelihood ratio test)
lavTestLRT.mi(mgfit.metric, h1 = mgfit.config)
## To compare multiple models, you must use anova()
anova(mgfit.config, mgfit.metric, mgfit.scalar)
## or compareFit(), which also includes fit indices for comparison
## (optional: name the models)
compareFit(config = mgfit.config, metric = mgfit.metric,
           scalar = mgfit.scalar,
           argsLRT = list(test = "D2", method = "satorra.bentler.2010"))

## correlation residuals to investigate local misfit
resid(mgfit.scalar, type = "cor.bentler")
## modification indices for fixed parameters, to investigate local misfit
modindices.mi(mgfit.scalar)
## or lavTestScore.mi for modification indices about equality constraints
lavTestScore.mi(mgfit.scalar)

## Wald test of whether latent means are == (fix 3 means to zero in group 2)
eq.means <- ' .p70. == 0
              .p71. == 0
              .p72. == 0 '
lavTestWald.mi(mgfit.scalar, constraints = eq.means)



## ordered-categorical data
data(datCat)
lapply(datCat, class)
## impose missing values
set.seed(123)
for (i in 1:8) datCat[sample(1:nrow(datCat), size = .1*nrow(datCat)), i] <- NA

catout <- cfa.mi(' f =~ u1 + u2 + u3 + u4 ', data = datCat,
                 m = 3, seed = 456,
                 miArgs = list(ords = paste0("u", 1:8), noms = "g"),
                 FUN = function(fit) {
                   list(wrmr = lavaan::fitMeasures(fit, "wrmr"),
                        zeroCells = lavaan::lavInspect(fit, "zero.cell.tables"))
                 })
summary(catout)
fitMeasures(catout, indices = "all") # scaled versions of indices, too

## extract custom output
sapply(catout@funList, function(x) x$wrmr) # WRMR for each imputation
catout@funList[[1]]$zeroCells # zero-cell tables for first imputation
catout@funList[[2]]$zeroCells # zero-cell tables for second imputation ...

# }
# NOT RUN {
# }