Tutorial: Artificial Neural Networks to Analyze Single-Case Experimental Designs

Translational Abstract Applied researchers often use single-case experimental designs to examine the effects of interventions and treatments. However, current practices to analyze the results obtained with single-case experimental designs may produce unacceptably high error rates, which may limit their applicability. One potential solution to this issue is to use artificial neural networks to develop decision-making models for single-case designs. The purpose of this article is to teach researchers how to develop decision-making models based on artificial neural network architecture. To this end, we provide step-by-step procedures to develop novel decision-making models with Python, a common programming language. Concurrently, our analyses show how neural networks may outperform common rules when applied to multiple baseline designs. The tutorial should support researchers in extending this line of research, which could not only improve the analysis of data from single-case designs in research, but also lead to better decision-making in practice. Since the start of the 21st century, few advances have had as far-reaching impact in science as the widespread adoption of artificial neural networks in fields as diverse as fundamental physics, clinical medicine, and psychology. In research methods, one promising area for the adoption of artificial neural networks involves the analysis of single-case experimental designs. Given that these types of networks are not generally part of training in the psychological sciences, the purpose of our article is to provide a step-by-step introduction to using artificial neural networks to analyze single-case designs. To this end, we trained a new model using data from a Monte Carlo simulation to analyze multiple baseline graphs and compared its outcomes with traditional methods of analysis. In addition to showing that artificial neural networks may produce less error than other methods, this tutorial provides information to facilitate the replication and extension of this line of work to other designs and datasets.