#statstab #515 Confounded dose-response effects of treatment adherence: fitting Bayesian instrumental variable models using brms

Thoughts: A nice tutorial on how to think about confounding, Simulating data, and making inferences

#brms #bayes #IV #guide

https://rpsychologist.com/adherence-analysis-IV-brms

You're probably familiar with git bisect, which lets you find a commit that introduces a change in behavior via binary search (`git bisect`). But what if the change in behavior is non-deterministic?

`git bayesect` is a generalization of git bisect that uses Bayesian inference to solve this problem. If your code has started gaslighting you, give it a try!

https://hauntsaninja.github.io/git_bayesect.html #git #bayes

#statstab #514 A puzzle of proportions

Thoughts: "Two popular Bayesian tests can yield dramatically different conclusions"
Model specification is important.

#bayesian #bayes #bayesfactor #nulleffects #proportions

https://doi.org/10.1002/sim.9278

🖤💙 Oh, how nice! The International Labour Organization provided the recording of my yesterday's seminar on my new forecasting system for labour market outcomes and my R package bpvars I developed for them! It's all very good 🤍

https://www.youtube.com/watch?v=ef3eXbqNbr8

#forecast #labourmarkets #Bayes #VAR #rstats #bpvars

My friend Jay Wren recommended a book yesterday at lunch:

"Thinking, Fast and Slow"
by Daniel Kahneman

https://www.amazon.com/Thinking-Fast-Slow-Daniel-Kahneman

A recommendation from Jay is an insta-buy. I got it as an audio-book (because of my commute).

It is not **at all** what I was expecting! I guess I thought maybe I was expecting something like a "self-help" book or the like. No. This is **not** a book aimed at a broad audience. This is a book aimed at people who understand (at least a bit about) probability and bias and category theory and ... What I'm saying is: it's not fluff. It's genuine knowledge aimed square at me. Jay's recommendation was on the money.

I wouldn't hand this to my MIL (it's past her at this point). I wouldn't hand it to my wife (she's certainly smart enough, but I don't think it falls in her circle of interest). I absolutely **would** recommend it to **you**, or to anyone in my circle of friends.

Go have some fun!

#Bayes #Knowledge #Psychology #Thinking

UPDATE: THIS DID NOT CONSISTENTLY WORK--some model objects still corrupted.

Went through some agony learning saveRDS() does not preserve all parts of a cmdstan_model object. The model information is corrupted upon re-importing it with readRDS(). I have to use the qs_save() from the qs2 📦 for a save that preserves the model info. #rstats #bayes #mcmc

BREAKING: Henceforth, I shall be using a new technique, “division”, to determine how much an item costs per count or unit weight.

This advance is a radical and exciting departure from the current method, counting on my fingers and toes.

🤦🏼 🤦🏼 🤦🏼

These f-ing morons.

https://www.instagram.com/reel/DTdoFw7kciA/?igsh=NTc4MTIwNjQ2YQ==

(For those unfamiliar, #Bayes was an 18th c. British #mathematician who developed an equation that has been used for centuries to calculate the probability of an event given what we already know. For example: if you get a medical test with 80% accuracy, and it returns positive, what is the chance you actually have the tested condition? Not 80%, as you may assume. The answer depends on the likelihood of developing that condition in the first place, and then applying the likelihood that the test is correct. Bayes’ theorem is pervasive in #medicine and many other disciplines, and not recently discovered by nut job RFK Jr. and his empty-headed lackeys.)

#math #science #statistics #CDC #HHS