A Reproducible Data Analysis Workflow

In this tutorial, we describe a workflow to ensure long-term reproducibility of R-based data analyses. The workflow leverages established tools and practices from software engineering. It combines the benefits of various open-source software tools including R Markdown, Git, Make, and Docker, whose interplay ensures seamless integration of version management, dynamic report generation conforming to various journal styles, and full cross-platform and long-term computational reproducibility. The workflow ensures meeting the primary goals that 1) the reporting of statistical results is consistent with the actual statistical results (dynamic report generation), 2) the analysis exactly reproduces at a later point in time even if the computing platform or software is changed (computational reproducibility), and 3) changes at any time (during development and post-publication) are tracked, tagged, and documented while earlier versions of both data and code remain accessible. While the research community increasingly recognizes dynamic document generation and version management as tools to ensure reproducibility, we demonstrate with practical examples that these alone are not sufficient to ensure long-term computational reproducibility. Combining containerization, dependence management, version management, and dynamic document generation, the proposed workflow increases scientific productivity by facilitating later reproducibility and reuse of code and data.

A note on a computationally efficient implementation of the EM algorithm in item response models

This note sketches two computational shortcuts for estimating unidimensional item response models and multidimensional item response models with between-item dimensionality utilizing an expectation-maximization (EM) algorithm that relies on numerical integration with fixed quadrature points. It is shown that the number of operations required in the E-step can be reduced in situations of many cases and many items by appropriate shortcuts. Consequently, software implementations of a modified E-step in the EM algorithm could benefit from gains in computation time.

A tutorial for joint modeling of longitudinal and time-to-event data in R

In biostatistics and medical research, longitudinal data are often composed of repeated assessments of a variable and dichotomous indicators to mark an event of interest. Consequently, joint modeling of longitudinal and time-to-event data has generated much interest in these disciplines over the previous decade. In behavioural sciences, too, often we are interested in relating individual trajectories and discrete events. Yet, joint modeling is rarely applied in behavioural sciences more generally. This tutorial presents an overview and general framework for joint modeling of longitudinal and time-to-event data, and fully illustrates its application in the context of a behavioral study with the JMbayes R package. In particular, the tutorial discusses practical topics, such as model selection and comparison, choice of joint modeling parameterization and interpretation of model parameters. In the end, this tutorial aims at introducing didactically the theory related to joint modeling and to introduce novice analysts to the use of the JMbayes package.