On a signal detection approach to m-alternative forced choice with bias, with maximum likelihood, Bayesian approaches to estimation

摘要

The standard signal detection theory (SDT) approach to m-alternative forced choice uses the proportion correct as the outcome variable, assumes that there is no response bias. The assumption of no bias is not made for theoretical reasons, but rather because it simplifies the model, estimation of its parameters. The SDT model for mAFC with bias is presented, with the cases of two, three, four alternatives considered in detail. Two approaches to fitting the model are noted: maximum likelihood estimation with Gaussian quadrature, Bayesian estimation with Markov chain Monte Carlo. Both approaches are examined in simulations. SAS, OpenBUGS programs to fit the models are provided, an application to real-world data is presented.