‹ BackHN Continuity

Thread

We do modern frequentist statistics: Using fake-data simulation

64 points · 9 comments · Tomte

Loading the complete thread in the background. This saved snapshot is available now. Refresh

  1. wodenokoto · · focus · HN ↗
    An article named “This is how we do modern frequentist statistics” is an excerpt from a book called “Bayesian workflows”

    Where is the article explaining that?

    Anyway, great article, thanks for sharing.

    1. spider-mario · · focus · HN ↗
      From your description, I thought “wait, is this going to be Andrew Gelman?”

      It is.

    2. 3abiton · · focus · HN ↗
      Wait a bayesian advocate using a frequentist approach and not having a fight over which branch is supreme. What's happening with the world. I guess all stats united against AI.
      1. Tomte · · focus · HN ↗
        Gelman (2018, and reiterated 2024): &quot;Bayesians are frequentists.&quot; (<a href="https:&#x2F;&#x2F;statmodeling.stat.columbia.edu&#x2F;2018&#x2F;06&#x2F;17&#x2F;bayesians-are-frequentists&#x2F;" rel="nofollow">https:&#x2F;&#x2F;statmodeling.stat.columbia.edu&#x2F;2018&#x2F;06&#x2F;17&#x2F;bayesians-...)
    3. beckford · · focus · HN ↗
      As mentioned in the sibling comments, Andrew Gelman has covered this elsewhere. In particular, Gelman et al have a &quot;Model Checking&quot; chapter in their Bayesian Data Analysis book <a href="https:&#x2F;&#x2F;sites.stat.columbia.edu&#x2F;gelman&#x2F;book&#x2F;BDA3.pdf" rel="nofollow">https:&#x2F;&#x2F;sites.stat.columbia.edu&#x2F;gelman&#x2F;book&#x2F;BDA3.pdf . A popular intro Bayesian book Statistical Rethinking has a similar &quot;Sampling from the Imaginary&quot; chapter (<a href="https:&#x2F;&#x2F;civil.colorado.edu&#x2F;~balajir&#x2F;CVEN6833&#x2F;bayes-resources&#x2F;RM-StatRethink-Bayes.pdf" rel="nofollow">https:&#x2F;&#x2F;civil.colorado.edu&#x2F;~balajir&#x2F;CVEN6833&#x2F;bayes-resources...). Both books introduce the topic early (the latter book deals with it in the third chapter) if you are willing to do a bit of reading.
  2. j7ake · · focus · HN ↗
    This should be automatic now in any statistical analysis given ubiquity of coding agents.
  3. SubiculumCode · · focus · HN ↗
    Where did he get the attractivess distribution, from the paper??
    1. Tomte · · focus · HN ↗
      You were just one click away from finding out:

      &quot;Figure 2. Using a sample of 2,972 respondents from the National Longitudinal Study of Adolescent Health, each of whom had been rated on a five-point scale of attractiveness […]&quot;

  4. addag · · focus · HN ↗
    This technique is very useful to gain intuition for a given sample size. Just run a few simulations with uncorrelated data and then you can get a sense of how extreme the estimators can be.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.