The term predictive statistics is used to describe a focus on observables, and not on any invisible model-based parameters as is found in estimation and null hypothesis significance testing. It isn’t sticking, […]
We are finally at the most crucial part of the modeling process: proving if the damned thing works. Not “works” in the sense that we get good unobservable parameter estimates, but works […]
Query: now that I’m a video master, would people like videos of these lessons? I don’t see how they’d help much, but who knows. Let me know below or via email. Next […]
Review! We’re doing logistic and beta regression this time. These aren’t far apart, because the observable for both lives between 0 and 1; for logistic it is 0 or 1; for beta, […]
Review! You must at least review the first lessons—all class material is on one page for ease. I’ll have more words about the mysticism of simulation, but I’ve said it all before […]
Introduction Here’s what we always want, but never get, using the old ways of doing statistics: The probability that some proposition Y is true given certain assumptions. Like this: (1) Pr(Y […]
RELEVANT ARTICLES New Paper! Reality-Based Probability & Statistics: Solving the Evidential Crisis (link) New Paper! Everything Wrong With P-values Under One Roof (link) New Paper! The Replacement For Hypothesis Testing (link) Randomization […]
What is the purpose of modeling? There can be only two. The first is to say what happened, to explain. But in order to do this one must first assume what one […]
Recent Comments