tl;dr When your MCMC chains look a mess, you might have to manually set your initial values. If you’re a fancy pants, you can use a custom function. Context A collaborator asked me to help model some reaction-time data. One of the first steps was to decide on a reasonable likelihood function. You can see a productive Twitter thread on that process here. Although I’ve settled on the shifted-lognormal function, I also considered the exponentially modified Gaussian function (a.
