Learn R Programming

⚠️There's a newer version (0.5-17) of this package.Take me there.

simsem (version 0.5-14)

SIMulated Structural Equation Modeling

Description

Provides an easy framework for Monte Carlo simulation in structural equation modeling, which can be used for various purposes, such as such as model fit evaluation, power analysis, or missing data handling and planning.

Copy Link

Version

Install

install.packages('simsem')

Monthly Downloads

789

Version

0.5-14

License

GPL (>= 2)

Maintainer

Terry Jorgensen

Last Published

June 3rd, 2018

Functions in simsem (0.5-14)

Data analysis using the model specification

Extract parameter estimates from a simulation result

findIndIntercept

Find indicator intercepts from factor loading matrix, total factor mean, and indicator mean.

Find coverage rate of model parameters

Find confidence interval width

Find indicator total means from factor loading matrix, total factor mean, and indicator intercept.

continuousPower

Find power of model parameters when simulations have randomly varying parameters

Find power in rejecting alternative models based on fit indices criteria

continuousCoverage

Find coverage rate of model parameters when simulations have randomly varying parameters

findFactorResidualVar

Find factor residual variances from regression coefficient matrix, factor (residual) correlations, and total factor variances

Extract the data generation population model underlying a result object

Find power of model parameters

Combine result objects

findFactorTotalVar

Find factor total variances from regression coefficient matrix, factor (residual) correlations, and factor residual variances

findFactorTotalCov

Find factor total covariance from regression coefficient matrix, factor residual covariance

getCutoffNonNested

Find fit indices cutoff for non-nested model comparison given a priori alpha level

Find p-values (1 - percentile) for a nested model comparison

Find p-values (1 - percentile) by comparing a single analysis output from the result object

Find the likelihood ratio (or Bayes factor) based on the bivariate distribution of fit indices

Extract information from a simulation result

Get extra outputs from the result of simulation

Build the data generation template and analysis template from the lavaan result

multipleAllEqual

Test whether all objects are equal

plotCutoffNonNested

Plot sampling distributions of the differences in fit indices between non-nested models with fit indices cutoffs

Provide summary of the population misfit and misspecified-parameter values across replications

plotCutoffNested

Plot sampling distributions of the differences in fit indices between nested models with fit indices cutoffs

Provide summary of parameter estimates and standard error across replications

Draw values from vector or matrix objects

Find population misfit by sufficient statistics

plotPowerFitNonNested

Plot power of rejecting a non-nested model based on a difference in fit index

getPowerFitNested

Find power in rejecting nested models based on the differences in fit indices

Find fit indices cutoff given a priori alpha level

getCutoffNested

Find fit indices cutoff for nested model comparison given a priori alpha level

Impose MAR, MCAR, planned missingness, or attrition on a data set

getPowerFitNonNested

Find power in rejecting non-nested models based on the differences in fit indices

Make a plot of confidence interval coverage rates

findIndTotalVar

Find indicator total variances from factor loading matrix, total factor covariance, and indicator residual variances.

pValueNonNested

Find p-values (1 - percentile) for a non-nested model comparison

Plot sampling distributions of fit indices with fit indices cutoffs

Plot the population misfit in the result object

Plot a confidence interval width of a target parameter

Set the data generation population model underlying an object

Find the discrepancy value between two means and covariance matrices

Provide summary of model fit across replications

Make a power plot of a parameter given varying parameters

summaryConverge

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

Run a monte carlo simulation with a structural equation model.

Provide short summary of an object.

Find a value of independent variables that provides a given value of coverage rate

findFactorIntercept

Find factor intercept from regression coefficient matrix and factor total means

Specify matrices for Monte Carlo simulation of structural equation models

Create a data distribution object.

findPossibleFactorCor

Find the appropriate position for freely estimated correlation (or covariance) given a regression coefficient matrix

Find a value of independent variables that provides a given value of power.

findRecursiveSet

Group variables regarding the position in mediation chain

Generate data using SimSem template

Specifying the missing template to impose on a dataset

Plot a distribution of a data distribution object

Data generation template and analysis template for simulation.

Visualize the missing proportion when the logistic regression method is used.

plotPowerFitNested

Plot power of rejecting a nested model in a nested model comparison by each fit index

Plot sampling distributions of fit indices that visualize power of rejecting datasets underlying misspecified models

summaryPopulation

Summarize the population model used for data generation underlying a result object

Summary of a seed number

Provide a comparison of nested models and nonnested models across replications

SimMatrix-class

Matrix object: Random parameters matrix

SimMissing-class

Class "SimMissing"

SimResult-class

Class "SimResult": Simulation Result Object

SimVector-class

Vector object: Random parameters vector

Draw parameters from a '>SimSem object.

SimDataDist-class

Class "SimDataDist": Data distribution object

Class "SimSem"

Create data from a set of drawn parameters.

Shortcut for data analysis template for simulation.

Export data sets for analysis with outside SEM program.

Find factor total means from regression coefficient matrix and factor intercept

findIndResidualVar

Find indicator residual variances from factor loading matrix, total factor covariance, and total indicator variances.