Search Results for “parameters” – Page 14

How To Do Predictive Statistics: Part III New (Free) Software Regression 2

Mandatory! Read Part I, Part II. I will ignore all comments already answered in Parts I & II. Download the code: mcmc.pred.R, mcmc.pred.examples.R. If you downloaded before, download again. This…

Class Statistics

How To Do Predictive Statistics: Part II New (Free) Software Regression 1

Mandatory! Read Part I. I will ignore all comments already answered in Part I. Download the code: mcmc.pred.R, mcmc.pred.examples.R. Update If you downloaded before, download again. This is version 0.2!…

Class Statistics

How To Do Predictive Statistics: Part I New (Free) Software Introduction

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: …

Class Statistics

There Is No Prior? What’s A Bayesian To Do? Relax, There’s No Model, Either

I saw colleague Deborah Mayo casting, or rather trying to cast, aspersions on Bayesian philosophy by saying there is "no prior". Bayesians might not agree, but it's true. Mayo's right.…

Statistics

The Epidemiologist Fallacy Strikes Again: Premature Birth Rate Edition

Hypothesis testing leads to more scientific nonsense than any other practice, including fraud. Hypothesis testing, as regular readers know, cannot identify cause. It conflates decision with probability and leads to…

Class Statistics

Lovely Example of Statistics Gone Bad

The graph above (biggified version here) was touted by Simon Kuestenmacher (who posts many beautiful maps). He said "This plot shows the objects that were found to be 'the most…

Other Practical Books On Par With <em>Uncertainty</em>? Reader Question

Fun Statistics

Other Practical Books On Par With Uncertainty? Reader Question

Got this email from VD. I've edited to remove any personal information and to add blog-standard style and links. I answered, and I remind all readers of the on-going claassre,…

Class Statistics

Choose Predictive Over Parametric Every Time

Gaze and wonder at picture which heads this article, which I lifted from John Haman's nifty R package ciTools. The numbers in the plot are made up whole cloth to…

Briggs on Class 70: Most Claims Of “Controlled For” Are Wrong: The Right WayNovember 8, 2025
Darin, There is no interval around a probability (with esoteric exceptions not of interest to us). All your evidence is…
Darin Johnson on Class 70: Most Claims Of “Controlled For” Are Wrong: The Right WayNovember 8, 2025
I'm struggling to extrapolate this to the case when the thing I'm estimating is a probability. Let's say I observe…
hudbwu on Changes Are Coming: Our Return to 1970sNovember 7, 2025
I didn't come here for ~two months. Then I come back and ... *shit's gotten weird, son.* o.O At least…
Northbrae on Diversity Patrol Scanning Citations For VictimsNovember 7, 2025
Cheers from Florida, land of the ugly beasts known as womanatees. Meritocracy is now Ancient Herstory. Sheesh.
RANDOM TIDS & BITS- Thu 3/20/24- – WAXX on The Sports Illustrated curse and regression to the meanNovember 6, 2025
[…] Illustrated” once determined that their cover is a JINX 37% of the time. So about two out of every five…