simsem: summaryConverge – R documentation

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

summaryConverge

Provide a comparison between the characteristics of convergent replications and nonconvergent replications

Description

This function provides a comparison between the characteristics of convergent replications and nonconvergent replications. The comparison includes sample size (if varying), percent missing completely at random (if varying), percent missing at random (if varying), parameter values, misspecified-parameter values (if applicable), and population misfit (if applicable).

Usage

summaryConverge(object, std = FALSE, improper = TRUE)

Arguments

`object`	`SimResult` object being described
`std`	If `TRUE`, the standardized parameter values are used instead of unstandardized parameter values.
`improper`	If TRUE, include the replications that provided improper solutions

Value

A list with the following elements:

Converged The number of convergent and nonconvergent replications
n Sample size
pmMCAR Percent missing completely at random
pmMAR Percent missing at random
paramValue Parameter values
misspecValue Misspecified-parameter values
popFit Population misfit. See details of each element at summaryMisspec.

Each element will provide the head-to-head comparison between convergent and nonconvergent replications properties.

Author(s)

Sunthud Pornprasertmanit (psunthud@gmail.com)

Examples

## Not run: 
path.BE <- matrix(0, 4, 4)
path.BE[3, 1:2] <- NA
path.BE[4, 3] <- NA
starting.BE <- matrix("", 4, 4)
starting.BE[3, 1:2] <- "runif(1, 0.3, 0.5)"
starting.BE[4, 3] <- "runif(1, 0.5, 0.7)"
mis.path.BE <- matrix(0, 4, 4)
mis.path.BE[4, 1:2] <- "runif(1, -0.1, 0.1)"
BE <- bind(path.BE, starting.BE, misspec=mis.path.BE)

residual.error <- diag(4)
residual.error[1,2] <- residual.error[2,1] <- NA
RPS <- binds(residual.error, "rnorm(1, 0.3, 0.1)")

loading <- matrix(0, 12, 4)
loading[1:3, 1] <- NA
loading[4:6, 2] <- NA
loading[7:9, 3] <- NA
loading[10:12, 4] <- NA
mis.loading <- matrix("runif(1, -0.3, 0.3)", 12, 4)
mis.loading[is.na(loading)] <- 0
LY <- bind(loading, "runif(1, 0.7, 0.9)", misspec=mis.loading)

mis.error.cor <- matrix("rnorm(1, 0, 0.1)", 12, 12)
diag(mis.error.cor) <- 0
RTE <- binds(diag(12), misspec=mis.error.cor)

SEM.Model <- model(RPS = RPS, BE = BE, LY=LY, RTE=RTE, modelType="SEM")

n1 <- list(mean = 0, sd = 0.1)
chi5 <- list(df = 5)

facDist <- bindDist(c("chisq", "chisq", "norm", "norm"), chi5, chi5, n1, n1)

# In reality, more than 50 replications are needed.
simOut <- sim(50, n=500, SEM.Model, sequential=TRUE, facDist=facDist, estimator="mlr")

# Summary the convergent and nonconvergent replications
summaryConverge(simOut)

## End(Not run)

simsem

SIMulated Structural Equation Modeling

v0.5-16

GPL (>= 2)

Authors

Sunthud Pornprasertmanit [aut], Patrick Miller [aut], Alexander Schoemann [aut] (<https://orcid.org/0000-0002-8479-8798>), Terrence D. Jorgensen [aut, cre] (<https://orcid.org/0000-0001-5111-6773>), Corbin Quick [ctb]

Initial release

2021-03-28