Ratings provided on visual analog scales (VAS), or slider scales, are unlikely to be normally distributed. Nevertheless, researchers typically use the normal distribution to analyze analog scale ratings, such as when they perform ANOVAs, t-tests, and correlations. A potentially better model of analog ratings, which are typically skewed and have lower and upper limits, is the so called zero-one-inflated beta model. In this post, I explain this model, illustrate its use with simulated and data, and compare its performance to t-tests in comparing two groups slider ratings.
(This post is part 4 of a series of blog posts discussing Bayesian estimation of Signal Detection models.) In this blog post, I describe how to estimate the unequal variances Gaussian signal detection (UVSDT) model for confidence rating responses, for multiple participants simultaneously. I provide software code for the hierarchical Bayesian model in R.
(This post is part 3 in a series of blog posts discussing Bayesian estimation of Signal Detection models.) In this post, we extend the EVSDT model to confidence rating responses, and estimate the resulting model as an ordinal probit regression. I also describe how to estimate the unequal variance Gaussian SDT model for a single participant. I provide a software implementation in R.
This is a part of a series of blog posts discussing Bayesian estimation of Signal Detection models. In this post, I describe how to estimate the equal variance Gaussian SDT model's parameters for multiple participants simultaneously, using Bayesian generalized linear and nonlinear hierarchical models. I provide a software implementation in R.
Signal Detection Theory (SDT) is a common framework for modeling memory and perception. Calculating point estimates of equal variance Gaussian SDT parameters is easy using widely known formulas. More complex SDT models, such as the unequal variance SDT model, require more complicated modeling techniques. These models can be estimated using Bayesian (nonlinear and/or hierarchical) regression methods, which are sometimes difficult to implement in practice. In this post, I describe how to estimate the equal variance Gaussian SDT model's parameters for a single participant with a Generalized Linear Model, and a nonlinear model. I describe the software implementation in R.
Exploring SIPS Tweets with R.
Assessing the correlations between psychological variabless, such as abilities and improvements, is one essential goal of psychological science. However, psychological variables are usually only available to the researcher as estimated parameters in mathematical and statistical models. The parameters are often estimated from small samples of observations for each research participant, which results in uncertainty (aka sampling error) about the participant-specific parameters. Ignoring the resulting uncertainty can lead to suboptimal inferences, such as asserting findings with too much confidence. Hierarchical models alleviate this problem by accounting for each parameter's uncertainty at the person- and average levels. However, common maximum likelihood estimation methods can have difficulties converging and finding appropriate values for parameters that describe the person-level parameters' spread and correlation. In this post, I discuss how Bayesian hierarchical models solve this problem, and advocate their use in estimating psychological variables and their correlations.
Last spring, at The Science of Consciousness conference in Tucson (previously known as Toward a Science of Consciousness), I was fortunate to be asked to participate in a discussion panel on Consciousness and Free Will. I only now found out that they have uploaded the videos from all the plenary talks and panels on YouTube.
The plenary talk before the panel was given by Aaron Schurger, on a computational model of the controversial results from Benjamin Libet’s experiments (a really great talk about a very nice paper, I might add).
What happens when the eye is passively dislocated? Well, it turns out that the research on that is out (or rather has been out since 1960), and the answer is very strange indeed.
Brindley and Merton, writing in 1960 in the Journal of Physiology reported that when the human eye is moved passively with a special contact lens, while the muscles usually responsible of the movement of the eye are anaesthetized, that people were unaware that their eye has moved.
I recently wrote a piece for Scientific American’s mind matters section. I wanted to call it “Why you won’t believe me”, but the editors thought otherwise. The post was about some cool research about how your name might influence how other people perceive your claims. It turns out that people are more likely to agree with people whose names they find easier to pronounce.
Anyway, I enjoyed writing for them, so hopefully you’ll enjoy reading the piece: