Suppose you have a confusion matrix, a matrix of values with rows corresponding to stimuli and columns to responses. Suppose further that you want to analyze the similarity between your stimuli and the bias to give one response or another … Continue reading
Since everyone’s been clamoring for more GRT, I’ve uploaded an updated draft of my paper with Robin Thomas on how GRT with an optimal response selection rule mimics decisional separability. In working through this problem, I realized recently that it … Continue reading
I’m at a loss to understand why it should be problematic to calculate false alarm rates with a Bayesian statistical model while it is acceptable to calculate statistical power with that same model. In null-hypothesis significance testing (NHST), the false … Continue reading
At Mid-Phon 17, I was talking to a colleague about mixed-effects (i.e., multilevel) modeling, and he stated very matter-of-fact-ly that when a random-intercepts-by-subjects model is estimated, there are no intercepts estimated for each individual subject. Rather, he continued, the model … Continue reading
I was amused to come across the toupée fallacy recently. According to the RationalWiki page on it, the idea is that it’s (informally) fallacious to assert that “all toupées look fake” if I am basing that conclusion solely on the “evidence” that, … Continue reading
No, not that kind of optimality theory. Though maybe I’ll write about that kind some day. No, this is about the kind of optimality theory wherein you have a mathematical model of perception (or memory, or whatever) and response selection, … Continue reading
A couple weeks ago while revising a paper (now published), I got thinking about the interplay between generality and specificity in mathematical proofs. A more general proof is better than a more specific proof, all else equal, since the former covers … Continue reading
Four or so years ago, I submitted a paper to Attention, Perception, & Psychophysics. It was very long, in large part because there was a fair amount of redundant information. The reviewers pointed this out, and I was happy to … Continue reading
I’m a little late to the game on the new paper A peculiar prevalence of p values just below .05, available to download here for free. The authors gathered 1,092 p-values from the Journal of Experimental Psychology: General, 1,760 from the … Continue reading
I’ve been working with general recognition theory (GRT) for a number of years now. I used it in a publication on complex non-speech auditory perception (pdf), my dissertation (pdf), a publication based on part of my dissertation (pdf), a second … Continue reading
