Learn R Programming

⚠️There's a newer version (2.17.1) of this package.Take me there.

SimDesign (version 2.2)

Structure for Organizing Monte Carlo Simulation Designs

Description

Provides tools to help safely and efficiently organize Monte Carlo simulations in R. The package controls the structure and back-end of Monte Carlo simulations by utilizing a general generate-analyse-summarise strategy. The functions provided control common simulation issues such as re-simulating non-convergent results, support parallel back-end and MPI distributed computations, save and restore temporary files, aggregate results across independent nodes, and provide native support for debugging. For a pedagogical introduction to the package refer to Sigal and Chalmers (2016) , and for an in-depth overview of the package and its design philosophy see Chalmers and Adkins (2020) .

Copy Link

Version

Install

install.packages('SimDesign')

Monthly Downloads

7,206

Version

2.2

License

GPL (>= 2)

Issues

Pull Requests

Stars

Forks

Repository

https://github.com/philchalmers/SimDesign

Homepage

https://github.com/philchalmers/SimDesign/wiki

Maintainer

Last Published

November 7th, 2020

Functions in SimDesign (2.2)

Compute the mean absolute error

Compute the empirical detection rate for Type I errors and Power

Compute the integrated root mean-square error

Compute estimates and statistics

Attach the simulation conditions for easier reference

Compute empirical coverage rates

Compute congruence coefficient

Function for decomposing the simulation into ANOVA-based effect sizes

Structure for Organizing Monte Carlo Simulation Designs

Compute the (normalized) root mean square error

Empirical detection robustness method suggested by Serlin (2000)

Suppress function messages and Concatenate and Print (cat)

Compute the relative absolute bias of multiple estimators

Compute the relative performance behavior of collections of standard errors

Create the simulation Design object

Function to extract extra information from SimDesign objects

Add missing values to a vector given a MCAR, MAR, or MNAR scheme

aggregate_simulations

Collapse separate simulation files into a single result

Generate a basic Monte Carlo simulation GUI template

Summarise simulated data using various population comparison statistics

Removes/cleans files and folders that have been saved

Generate data with the inverse Wishart distribution

Generate integer values within specified range

rejectionSampling

Rejection sampling (i.e., accept-reject method) to draw samples from difficult probability density functions

Generate data with the multivariate normal (i.e., Gaussian) distribution

Generate data with the multivariate t distribution

Generate data with the multivariate g-and-h distribution

Run a summarise step for results that have been saved to the hard drive

Compute prediction estimates for the replication size using bootstrap MSE estimates

rbind.SimDesign

Combine two separate SimDesign objects by row

Generate a random set of values within a truncated range

Compute (relative/standardized) bias summary statistic

Run a Monte Carlo simulation given a data.frame of conditions and simulation functions

Template-based generation of the Generate-Analyse-Summarise functions

Function to read in saved simulation results

Compute the relative efficiency of multiple estimators

Compute the relative difference

Generate non-normal data with Headrick's (2002) method

Generate non-normal data with Vale & Maurelli's (1983) method

Example simulation from Brown and Forsythe (1974)

BF_sim_alternative

(Alternative) Example simulation from Brown and Forsythe (1974)