There are many software packages that estimate item response theory parameters and examinee abilities. This study evaluates the accuracy of the item parameter and ability estimates generated by the open-source R package ltm. In this simulation study, item and ability estimates were compared to the true parameters under six conditions that differed in the numbers of items and examinees. After looking at the resulting bias, mean absolute deviation, and root mean square error, we concluded that item parameter and ability estimates from ltmwere estimated reasonably accurately with results similar to previous studies of established commercial software.
Sahin, Fusun and Colvin, Kimberly, "Evaluation of R Package ltm with IRT Dichotomous Models" (2015). NERA Conference Proceedings 2015. 6.