Using AB Designs With Nonoverlap Effect Size Measures to Support Clinical Decision-Making: A Monte Carlo Validation.

Single-case experimental designs often require extended baselines or the withdrawal of treatment, which may not be feasible or ethical in some practical settings. The quasi-experimental AB design is a potential alternative, but more research is needed on its validity. The purpose of our study was to examine the validity of using nonoverlap measures of effect size to detect changes in AB designs using simulated data. In our analyses, we determined thresholds for three effect size measures beyond which the type I error rate would remain below 0.05 and then examined whether using these thresholds would provide sufficient power. Overall, our analyses show that some effect size measures may provide adequate control over type I error rate and sufficient power when analyzing data from AB designs. In sum, our results suggest that practitioners may use quasi-experimental AB designs in combination with effect size to rigorously assess progress in practice.

Correction to: Machine Learning to Analyze Single-Case Data: A Proof of Concept.

[This corrects the article DOI: 10.1007/s40614-020-00244-0.].

Machine Learning to Analyze Single-Case Data: A Proof of Concept.

Visual analysis is the most commonly used method for interpreting data from single-case designs, but levels of interrater agreement remain a concern. Although structured aids to visual analysis such as the dual-criteria (DC) method may increase interrater agreement, the accuracy of the analyses may still benefit from improvements. Thus, the purpose of our study was to (a) examine correspondence between visual analysis and models derived from different machine learning algorithms, and (b) compare the accuracy, Type I error rate and power of each of our models with those produced by the DC method. We trained our models on a previously published dataset and then conducted analyses on both nonsimulated and simulated graphs. All our models derived from machine learning algorithms matched the interpretation of the visual analysts more frequently than the DC method. Furthermore, the machine learning algorithms outperformed the DC method on accuracy, Type I error rate, and power. Our results support the somewhat unorthodox proposition that behavior analysts may use machine learning algorithms to supplement their visual analysis of single-case data, but more research is needed to examine the potential benefits and drawbacks of such an approach.

Evaluation of Manualized Instruction to Train Staff to Implement a Token Economy.

All components of behavioral skills training may not be necessary to effectively train staff to implement behavior-analytic technologies with children with disabilities. This study evaluated manualized instruction to train inexperienced staff to implement a token economy with a confederate and collect data on learner responding. A nonconcurrent multiple-baseline design across staff trainees was used to evaluate the effectiveness of manualized instruction to increase the staff trainees' accurate implementation of a token economy. Additionally, a modified general case analysis was conducted to identify potential child behaviors. Multiple-exemplar training of these behaviors was presented in random order during sessions. Following the use of the manualized instruction, staff trainees' accurate implementation of a token economy and data collection on confederate responding increased, the skills generalized from a confederate to a child with autism spectrum disorder, and the skills maintained 1 month following training.

Differential reinforcement of high rates of behaviour to increase work productivity in adults with intellectual disability.

BACKGROUND: Due to deficits in adaptive and cognitive functioning, productivity may pose challenges for individuals with intellectual disability in the workplace. METHOD: Using a changing-criterion embedded in a multiple baseline across participants design, we examined the effects of differential reinforcement of high rates of behaviour (DRH) on the rate of data entry (i.e., productivity) in four adults with intellectual disability. RESULTS: Although the DRH procedure increased the rate of correct data entry in all four participants, none of the participants achieved the criterion that we set with novice undergraduate students. CONCLUSIONS: Our results indicate that DRH is an effective intervention to increase rate of correct responding in individuals with intellectual disability, but that achieving the same productivity as workers without disability may not always be possible.

Teaching installation and use of child passenger safety restraints.

Correctly installed child passenger safety restraints may reduce the risk of child injury and death during accidents. The present study evaluated behavioral skills training and self-monitoring to teach correct installation and use of a child passenger safety restraint in the rear-facing position. Extension probes were conducted with untrained installations and harnessing positions. Training was successful in teaching participants all installation methods and harnessing positions.

Using Video Modeling with Voiceover Instruction Plus Feedback to Train Staff to Implement Direct Teaching Procedures.

Direct teaching procedures are often an important part of early intensive behavioral intervention for consumers with autism spectrum disorder. In the present study, a video model with voiceover (VMVO) instruction plus feedback was evaluated to train three staff trainees to implement a most-to-least direct (MTL) teaching procedure. Probes for generalization were conducted with untrained direct teaching procedures (i.e., least-to-most, prompt delay) and with an actual consumer. The results indicated that VMVO plus feedback was effective in training the staff trainees to implement the MTL procedure. Although additional feedback was required for the staff trainees to show mastery of the untrained direct teaching procedures (i.e., least-to-most and prompt delay) and with an actual consumer, moderate to high levels of generalization were observed.