Michael Lee's Avatar

Michael Lee

@mdlbayes.bsky.social

cognitive scientist, bayesian, fascinated by naturally occurring behavioral data, strong preference for second slip over mid off (he/him)

1,108 Followers  |  292 Following  |  11 Posts  |  Joined: 07.08.2023
Posts Following

Posts by Michael Lee (@mdlbayes.bsky.social)

Post image

A strawberry selling masterclass.

16.08.2025 23:36 β€” πŸ‘ 4    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image

So that \lipsum thing was just about contacting customer service for discounts?

05.08.2025 02:20 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Post image

In case it wasn’t already obvious, Joel Wilson is likely the worst decision maker over the last two years, based on a signal detection analysis of DRS reviews. That’s him down the bottom in the left panel. #AUSvIND

03.01.2025 00:25 β€” πŸ‘ 9    πŸ” 7    πŸ’¬ 0    πŸ“Œ 1

Norwood oval :) Go β€˜legs

23.03.2024 09:00 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Yep. And, ugh, Jarrod Berry.

30.09.2023 07:44 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

I posted hard copies of manuscripts to journals (always four copies, double spaces, single sided) for years. Well into the 2000s. This was also attributed to the dinosaurs. I guess they got that bit right :) 5/5

23.09.2023 16:19 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Mostly, it made me feel old. I’ve had to put white out on paper and realign the typewriter ball to edit. (And swap the ball repeatedly for math symbols). This was attributed as 1920s behavior. 4/n

23.09.2023 16:17 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 2    πŸ“Œ 0

The complaint about the x-axis ticks doesn’t make sense to me. Those are the legend from the histogram. That’s as far as I got in the video. I also just didn’t get the argument and am glad I’m not alone. 3/n

23.09.2023 16:14 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

My guess is the informationally redundant symmetry helps the visual and cognitive perception on the information (but I have no evidence of this β€” anyone know of any?). The vertical arrangement avoids visual overlap, unlike the histogram alternative. 2/n

23.09.2023 16:12 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 2    πŸ“Œ 0

I think aiming to showing distributions of data rather than summaries (even detailed summaries, like box plots) is generally a good goal. Smoothing relies on assumptions and will be as good as those assumptions: it’s possible to make minimal ones by binning. 1/n

23.09.2023 16:10 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

We're hiring an Assistant Professor (Tenure Track) at UC Irvine Cognitive Sciences! Focus on higher-order/causal reasoning. Due date Nov 15. Feel free to reach out to me with any questions!

www.cogsci.uci.edu/employment.php

16.09.2023 13:43 β€” πŸ‘ 32    πŸ” 33    πŸ’¬ 0    πŸ“Œ 4
Preview
Support Data Colada's Legal Defense, organized by Simine Vazire Data Colada Are Being Sued for Raising Scientific Concerns about Published Research… Simine Vazire needs your support for Support Data Colada's Legal Defense

Please consider this gofundme to support the datacolada team: https://gofund.me/70c497b1

17.08.2023 07:02 β€” πŸ‘ 8    πŸ” 1    πŸ’¬ 0    πŸ“Œ 0