@krysdolega A #Bayesian or a #Pragmaticist will agree to the position of #Neurath as stated by #Zolo. I often see this such criticism needed when sociology and #psychology turn to a pseudo-objectivism of the #Fisherian, #frequentist, kind.

A THREAD on a dead horse, #Frequentist vs #Bayesian inference, because why not?

(retro hits from the bad place, now that someone set fire to it again, and by hits I mean it got two retweets when I originally posted it four years ago, which is like a record for me)

This came out less bad than I thought #rapbattles #stats #bayesian vs #frequentist #gpt3 #farmerandthecowman #endingbeefs

Part II of my series on what to do with non-significant results is up now.

In this post, I focus on how to determine if your data is compatible with the claim of "no effect" (and why relying on p-values is wrong). It covers TOST equivalence tests and how to interpret and write up your results for publication. Link below 🔗

#statistics #frequentist #NHST #pvalue #equivalencetests #TOST #null #hypothesistesting #hypothesis

https://mzstats.blogspot.com/2023/01/what-to-do-with-null-results-part-ii.html

Ultimately this is exploratory to see if the data is worth building a principled Bayesian model for... so I told him to just run the same formula from the lm model through #brms to get a quick and dirty bayes-interpretable output. #statistics #bayes #frequentist #anova

I'm ending the year by starting a blog - Finding Suff Out - a space where I can work out statistical and methodological problems I encounter in my job (it will contain guides, tutorials, rants, etc.)

Published my first post now. It's on what to do with non-significant results when you have a small sample size. See link below.

#statistics #frequentist #NHST #pvalue #newstatistics #estimation

https://mzstats.blogspot.com/2022/12/what-to-do-with-null-results-part-i.html

I strongly agree with their final point: "...the quality of the whole study design and its execution, including its assumptions and data collection approaches, is likely more important to the inferences one can make than the analytical approach itself." #bayesian #frequentist #stats #biostat

@cd_fuller #stats #biostats #bayesian #frequentist #radonc

Everytime I read a stats paper with the words "We derive asymptotic results for (...)", I think "In the long term we're all dead."

#frequentist #bayesian

@ChristosArgyrop
Fisher was right that without randomization you cant make the assumption that things behave as if random. The biggest problem with #frequentist #statistics is that in general the usual assumption is that any old experiment is a #random sample of outcomes. People have whole careers designing random number generators and tests of randomness. Just collecting a few tens of data points in mice or some example test scores in undergrads or whatever is not #randomness

Are p-values convoluted and arcane? Are confidence intervals hopelessly confusing? No! These ideas can be challenging to teach and learn, but they represent an invaluable way of thinking about scientific results. Once they're properly understood, they are more intuitive than they get credit for. Here is an attempt at a very brief explanation of why I love the logic of null hypothesis significance testing. [1/7]
#Statistics #Frequentist #NHST #Inference

i’ve moved over from another server! but re #introduction here

i’m a stats-oriented #DataScientist working at a pediatric hospital in the clinical analytics department (ie non-research)

i love using #RStats and #SQL and #WhatsYourActualQuestion to solve clinical care problems, especially in #CriticalCare and #Neurology, and strong interest in #DataEthics and #EquityAnalytics

i use #Frequentist, #Bayesian, and #Information-Theoretic methods, as there is no single definition of probability!

hey I’m writing a (positive) thing describing a flavour of ‘frequentist’ statistical inference for fun, trying to lay out a somewhat philosophical but pragmatic approach that avoids common criticisms…so…what are your favourite criticisms of/counterexamples in frequentist inference (particularly eg confidence intervals but not limited to that)? #statistics #frequentist …and since they’ll have an interest, #bayes #bayesian 😉