A fully automated, transparent, reproducible, and blind protocol for sequential analyses

Brice Beffara Bret (1, 2) , Amélie Beffara Bret (1) , Ladislas Nalborczyk (3)

1 LPPL - Laboratoire de Psychologie des Pays de la Loire
2 PSYCHO - Laboratoire de Psychologie - UFC (UR 3188)
3 Department of Experimental Clinical and Health Psychology

Despite many cultural, methodological, and technical improvements, one of the major obstacle to results reproducibility remains the pervasive low statistical power. In response to this problem, a lot of attention has recently been drawn to sequential analyses. This type of procedure has been shown to be more efficient (to require less observations and therefore less resources) than classical fixed-N procedures. However, these procedures are submitted to both intrapersonal and interpersonal biases during data collection and data analysis. In this tutorial, we explain how automation can be used to prevent these biases. We show how to synchronise open and free experiment software programs with the Open Science Framework and how to automate sequential data analyses in R. This tutorial is intended to researchers with beginner experience with R but no previous experience with sequential analyses is required.

Mots clés: Sequential analysis; Sequential testing; Sequential Bayes factor; Automation; Expectancy effects; Reproducibility; Blind analyses

Domaines: Psychologie; Psychologie; Sciences cognitives; Neurosciences; Psychologie et comportements; Sciences cognitives; Sciences du Vivant [q-bio]; Méthodologie [stat.ME]

Brice Beffara Bret, Amélie Beffara Bret, Ladislas Nalborczyk. A fully automated, transparent, reproducible, and blind protocol for sequential analyses. Meta-Psychology, 2021, 5, ⟨10.15626/MP.2018.869⟩. ⟨hal-03283796⟩