Background: Random forest based variable importance measures have become popular tools for assessing the contributions of the predictor variables in a fitted random forest. In this article we reconsider a frequently used variable importance measure, the Conditional Permutation Importance (CPI). We argue and illustrate that the CPI corresponds to a more partial quantification of variable importance and suggest several improvements in its methodology and implementation that enhance its practical value. In addition, we introduce the threshold value in the CPI algorithm as a parameter that can make the CPI more partial or more marginal. Results: By means of extensive simulations, where the original version of the CPI is used as the reference, we examine the impact of the proposed methodological improvements. The simulation results show how the improved CPI methodology increases the interpretability and stability of the computations. In addition, the newly proposed implementation decreases the computation times drastically and is more widely applicable. The improved CPI algorithm is made freely available as an add-on package to the open-source software R. Conclusion: The proposed methodology and implementation of the CPI is computationally faster and leads to more stable results. It has a beneficial impact on practical research by making random forest analyses more interpretable.

Changing the order of items between alternate test forms to prevent copying and to enhance test security is a common practice in achievement testing. However, these changes in item order may affect item and test characteristics. Several procedures have been proposed for studying these item-order effects. The present study explores the use of descriptive and explanatory models from item response theory for detecting and modeling these effects in a one-step procedure. The framework also allows for consideration of the impact of individual differences in position effect on item difficulty. A simulation was conducted to investigate the impact of a position effect on parameter recovery in a Rasch model. As an illustration, the framework was applied to a listening comprehension test for French as a foreign language and to data from the PISA 2006 assessment.

In this article, the change in examinee effort during an assessment, which we will refer to as persistence, is modeled as an effect of item position. A multilevel extension is proposed to analyze hierarchically structured data and decompose the individual differences in persistence. Data from the 2009 Program of International Student Achievement (PISA) reading assessment from N ¼ 467,819 students from 65 countries are analyzed with the proposed model, and the results are compared across countries. A decrease in examinee effort during the PISA reading assessment was found consistently across countries, with individual differences within and between schools. Both the decrease and the individual differences are more pronounced in lower performing countries. Within schools, persistence is slightly negatively correlated with reading ability; but at the school level, this correlation is positive in most countries. The results of our analyses indicate that it is important to model and control examinee effort in low-stakes assessments.