Computerized Adaptive Testing for Survey Research

Provides methods of computerized adaptive testing for survey researchers. See Montgomery and Rossiter (2020) . Includes functionality for data fit with the classic item response methods including the latent trait model, Birnbaum`s three parameter model, the graded response, and the generalized partial credit model. Additionally, includes several ability parameter estimation and item selection routines. During item selection, all calculations are done in compiled C++ code.


catSurv 1.0.3

Major Changes

  • New functions estimateThetas() and simulateThetas() allow for estimation of ability parameter for dataframe of response sets.

Minnor Changes

  • Streamlined checkStopRules().

catSurv 1.0.2

Major Changes

  • Parallelized main functionality of package --- selectItem().

Bug Fixes

  • Fixed bug in ltmCat(), tpmCat(), grmCat(), and gpcmCat() by adding the ltm package to Imports.
  • Fixed bug in KL functions, where we were integrating over a function that itself called integration.
  • Removed versioning from stats and methods imports as it caused errors in testing with r-oldrel.

catSurv 1.0.1

  • Corrected errors regarding portability of code to Solaris operating systems.

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


1.4.0 by Erin Rossiter, 4 months ago

Report a bug at

Browse source code at

Authors: Jacob Montgomery [aut] , Erin Rossiter [aut, cre]

Documentation:   PDF Manual  

GPL-3 license

Imports jsonlite, methods, stats, plyr, Rcpp, RcppParallel

Depends on ltm

Suggests catIrt, catR, testthat

Linking to BH, Rcpp, RcppArmadillo, RcppGSL, RcppParallel

System requirements: C++11, GNU make

See at CRAN