The Work Disability Functional Assessment Battery (WD-FAB) is a multidimensional item response theory (IRT) instrument designed for assessing work-related mental and physical function based on responses to an item bank. In prior iterations it was developed using traditional means -- linear factorization, followed by statistical testing for item selection, and finally, calibration of disjoint unidimensional IRT models. As a result, the WD-FAB, like many other IRT instruments, is a posthoc model. In this manuscript, we derive an interpretable probabilistic autoencoder architecture that embeds as the decoder a Bayesian hierarchical model for self-consistently performing the following simultaneous tasks: scale factorization, item selection, parameter identification, and response scoring. This method obviates the linear factorization and null hypothesis statistical tests that are usually required for developing multidimensional IRT models, so that partitioning is consistent with the ultimate nonlinear factor model. We use the method on WD-FAB item responses and compare the resulting item discriminations to those obtained using the traditional method.

使用贝叶斯分层模型和变分推理的方法，自洽地实现了多维项目反应模型的尺度因子化、项目选择、参数辨识和响应评分，并以使用 Work Disability Functional Assessment Battery 项目反应数据为例，证明了该方法在项区分度和测量效度方面的优越性。

基于自编码稀疏贝叶斯的IRT因子分解、校准和摊销推理在工作伤残功能评估电池中的应用