Learn R Programming

⚠️There's a newer version (1.0.14) of this package.Take me there.

rpf (version 0.3)

Response Probability Functions

Description

The purpose of this package is to factor out logic and math common to Item Response Theory fitting, diagnostics, and analysis. It is envisioned as core support code suitable for more specialized IRT packages to build upon. A version 1.0 will offer optimized, low-level functions to map parameters to response probabilities for a wide variety of dichotomous and polytomous item models.

Copy Link

Version

Install

install.packages('rpf')

Monthly Downloads

22,232

Version

0.3

License

GPL (>= 3)

Maintainer

Joshua Pritikin

Last Published

August 8th, 2012

Functions in rpf (0.3)

Compute the ordinal gamma association statistic

Class rpf.1dim.drm

Unidimensional dichotomous item models (1PL, 2PL, and 3PL).

Length of the item parameter vector

Map an item model, item parameters, and person trait score into a probability vector

Compute the sum-score EAP table

itemOutcomeBySumScore

Produce an item outcome by observed sum-score table

Write a flexMIRT PRM file

Compute EAP scores

Item derivatives with respect to the location in the latent space

Class rpf.mdim.mcm

The multiple-choice response item model (both unidimensional and multidimensional models have the same parameterization).

Class rpf.1dim.graded

The base class for 1 dimensional graded response probability functions.

ptw2011.gof.test

Compute the P value that the observed and expected tables come from the same distribution

rpf.startingParam

Initial item parameters

Class rpf.mdim.graded

The base class for multi-dimensional graded response probability functions.

sumScoreEAPTest

Conduct the sum-score EAP distribution test

rpf.1dim.moment

Calculate cell central moments

expandDataFrame

Expand summary table of patterns and frequencies

Class rpf.mdim.nrm

The nominal response item model (both unidimensional and multidimensional models have the same parameterization).

Convert an rpf item model name to an ID

Liking for Science dataset

An introduction

rpf - Response Probability Functions

Compute the S fit statistic for 1 item

Class rpf.mdim.drm

Multidimensional dichotomous item models (M1PL, M2PL, and M3PL).

Transform from [0,1] to the reals

Retrieve a description of the given parameter

Class rpf.1dim.grm

The unidimensional graded response item model.

observedSumScore

Compute the observed sum-score

Tabulate data.frame rows

Randomly sample response patterns given a list of items

Compute the S fit statistic for a set of items

The base class for multi-dimensional response probability functions.

Create a graded response model

orderCompletely

Order a data.frame by missingness and all columns

Map an item model, item parameters, and person trait score into a probability vector

Item parameter derivatives

Length of the item model vector

Class rpf.mdim.grm

The multidimensional graded response item model.

The ogive constant

Calculate item and person Rasch fit statistics

Read a flexMIRT PRM file

The base class for response probability functions.

Multinomial fit test

Convert an OpenMx MxModel object into an IFA group

omitMostMissing

Omit items with the most missing data

Find the point where an item provides mean maximum information

Create a nominal response model

rpf.1dim.stdresidual

Calculate standardized residuals

Create a multiple-choice response model

Create a dichotomous response model and associated hyperparameters.

rpf.prob wrapper2

Turn a matrix of parameters into a vector for rpf.prob.

Knox Cube Test dataset

rpf.1dim.residual

Calculate residuals

Create a similar item specification with the given number of factors

Class rpf.1dim.gpcm

The unidimensional generalized partial credit item model.

Map an item model, item parameters, and person trait score into a information vector

compressDataFrame

Compress a data frame into unique rows and frequencies

Find the point where an item provides mean maximum information

ChenThissen1997

Computes local dependence indices for all pairs of items

Monte-Carlo test for cross-tabulation tables

Rescale item parameters

rpf.setLocation

Set location related item parameters

The base class for 1 dimensional response probability functions.

rpf.getLocation

Extract location related item parameters

Generates item parameters

Log likelihood of item parameters with respect to Bayesian prior

rpf.prob wrapper1

Turn a matrix of parameters into a vector for rpf.prob.

Create a generalized partial credit model and associated hyperparameters.

Class rpf.mdim.gpcm

The multidimensional generalized partial credit item model.