PsiMLE
Psychophysical Scaling with Maximum-Likelihood Estimation
PsiMLE provides reseachers with a simple and intuitive way of using the maximum-likelihood estimation method to quickly, efficiently, and reliably estimate individual diffenrences in psychophysical scaling (e.g., slopes, power-law exponents, etc.) and variability (e.g., coefficients of variance).You can use PsiMLE in two ways: either through our user-friendly program R-PsiMLE on Windows or Mac OS (download here), or by using it within R directly (simply install the psimle package within R). Both of these come with complete manuals and help files for additional information. The forum above can also be used for additional assistance.
PsiMLE holds numerous advantages over traditional methods, including that it can be used in experiments where each target value is only presented once (these situations prevent calculations of coefficients of variance). Additionally, the method allows for model comparison and for testing of non-standard models, including testing whether observers counted, or if estimation variability is different for low- vs. high-intensity ranges. This software is a companion to our work and available upon request (Odic, Im, Eisinger, Ly, & Halberda (2015) PsiMLE: a maximum-likelihood approach to estimating psychophysical scaling and variability more reliably, efficiently, and flexibly).
