Statistics for Psychophysics, using R

Kenneth Knoblauch, PhD. , Université Claude Bernard, Lyon 1, Inserm U 1208, Stem-cell and Brain Research Institute, Building the cerebral cortex:  Connectomics, Bron, France and Faculty of Health and Social Sciences, Department of Optometry, Radiography and Lighting Design, University Southeastern Norway, Oslo, Norway

This workshop will focus on statistical tools to analyze and to model psychophysical experiments within the framework of Signal Detection Theory.  This includes choice experiments (detection, discrimination, identification, etc.), fitting psychometric functions and rating scale experiments with ROC analyses.  In many cases, the decision rule underlying these paradigms is linear, thereby permitting the analyses to be facilitated by using a Generalized Linear Model (GLM).  Rating scales, similarly, are analyzed by using ordinal regression models with cumulative link functions.  With these approaches, we can define straight-forward procedures to fit the data, to test hypotheses about them, to obtain confidence intervals, etc.  Most off-the-shelf software packages now include tools for performing GLMs, thus, making it easy to implement these tests and procedures.  Examples will be shown using the R programming environment and language (https://www.r-project.org).  Finally, an example will be shown of this approach with a paradigm for measuring appearance, i.e., scaling. Background reading includes the books "Modeling Psychophysical Data in R", K. Knoblauch & L. T. Maloney, 2012, Springer, (for R users) and "Psychophysics: A Practical Introduction, 2^nd Edition", F. A. A. Kingdom & N. Prins, 2016, Academic Press (for matlab users). R packages used in tutorial that can be installed ahead of time from CRAN - please see Center for Integrative Neuroscience for links.  Packages should be installed with dependencies, e.g., from within an R session 

Data sets used during the workshop will be made available ahead of time.