Rasmus Bååth Profile picture
Feb 2, 2023 14 tweets 5 min read Read on X
#ChatGTP knows everything about p-values and that's a problem. A short 🧵
There's a lot of non-sense written about p-values on the internet. ChatGTP has learned it all, and readily mixes correct statements with nonsense like "p < 0.05 means there is less than a 5% chance that the results are due to chance". Image
Trying out different prompts you can get better answers. I had some luck by adding on "I'm a statistics professor" which makes ChatGTP say mostly correct things about p-values. Image
But if you're a student you're out of luck and back into "It's the probability the results occurred by chance"-nonsense camp. Image
Of course, ChatGTP will readily prescript NHST and p-values if you're asking how you can *prove* that two groups are different... Image
Here's the best example of that ChatGTP has internalized ALL the nonsense people have written about p-values... Image
In 2002 Haller and Krauss wrote this sweet little paper where they show that, at their university, confusions around p-values was common among students *as well as* methodology teachers.
krigolsonteaching.com/uploads/4/3/8/… Image
Students, scientists, and methodology teachers were given the following prompt: Image
And the following questions, all of which *should* be marked as false: Image
Most students, teachers, and scientists failed on this questionnaire... Image
The amazing thing is, as chatGTP is so good, we can give it this questionnaire verbatim! Image
And it will answer! But as it's trained on people's general misconceptions of what a p-values is, it will fall into the same traps as the students and teachers. Image
Unfortunately, as long as chatGTP it's trained on what people have been writing about p-values online, it should not be used as an alternative to, say, wikipedia. Image
Some more ramblings about this in a short presentation I did at Bayes@Lund 2023:

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Rasmus Bååth

Rasmus Bååth Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @rabaath

Oct 27, 2021
The good thing when working with tidy data is that python, R and SQL code often becomes very similar.
(Makes it easier for my brain, when switching between languages 🧠👍)
Of course, then SQL had to go and get the order of statements completely wrong... well well...
Btw, this query extracts the top 10 artists that's been on Spotify's Top 200 playlist the most in Sweden. Using the "Spotify Charts" dataset: kaggle.com/dhruvildave/sp…
Read 4 tweets
Dec 5, 2020
By now you might have heard the good news that #rstats is getting a new shorthand function syntax. Soon you'll be able to write the following in R!

add <- \(x, y) x + y

But why does this new syntax use the backslash?
(A thread. 1/n)
The \(x,y) x + y syntax might look odd, but is borrowed (as far as I know) from perhaps the most functional of all programming languages - Haskell - where a similar syntax is used (with the addition of an -> arrow).
But why the backslash?
(2/n)
Modern Javascript doesn't use a backslash for shorthand function definitions and neither does python. But python gives us a clue! Why does python use the lambda keyword?
(3/n)
Read 7 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(