Sean Mackinnon
seanpmackinnon.bsky.social
Sean Mackinnon
@seanpmackinnon.bsky.social
Instructor at Dalhousie University. Personality, statistics, mixed methods
Ah, I often make my students do it. Did it in this paper:

psycnet.apa.org/record/2023-...

I've never like, put residual plots in a Word document supplement before, but the R code could produce them.

Word counts often mean it ends up on the cutting room floor in papers, even though I do it, tbh.
October 15, 2025 at 1:51 PM
I was using notepad in Windows 11 and somehow clicked a button to format the text with bold, italics, etc.

It's notepad, I'm using it explicitly so it won't autoformat anything.

What kind of terrible world do we live in that I need to gesture to this @dasharez0ne.bsky.social T-shirt constantly.
September 29, 2025 at 2:29 PM
Week 3 of being on strike, and the board keeps sabotaging negotiations by trying to bargain in public.

Still, hoping that a conciliator in the room on Monday will finally let us make peogress!

#keepdalstrong
September 6, 2025 at 7:16 PM
Time to start upping the meme game

#KeepDalStrong
August 28, 2025 at 2:42 PM
One week of being locked out by Dalhousie with not a single word from the board since. With the teaching term supposed to start next week, its getting a bit stressful.

Good thing we have Luna the therapy dog to keep us company, with a cute DFA branded bandanna!!

#KeepDalStrong
August 27, 2025 at 5:24 PM
Day 2 of being locked out by Dalhousie. Making history as the first U15 university to lock out their employees, but we're staying strong!

#keepdalstrong
August 21, 2025 at 12:49 PM
Could you clarify what is in the denominator of the SMD fraction when you talk about "pooled scale"?

In the paper you cited he writes this as the formula, which is a pretty standard usage of the standard deviations, so you must mean something else
August 6, 2025 at 3:46 PM
Cohen's ds (attached) is annoying arithmetic, and doesn't jive with the Welch t-test because it assumes equal variances.

Cohen's d_rm for the paired t-test requires knowing what a correlation is first, which comes later in the curriculum.

Cohen's dz, t/SQRT(N) isn't comparable to between subjects
July 31, 2025 at 2:05 PM
It's interesting that the confidence interval here contains what is predicted in Table 2 of this paper, which argues that it will tend to be the case because of how power analyses are done

www.sciencedirect.com/science/arti...
May 29, 2025 at 1:58 PM
I ended up reading a 30-year-old magazine article on shyness by Carducci & Zimbardo (1995) and it is fascinating that all the complaints of young people are basically the same as they are today.

How dare they telecommute and stay glued to their electronic hand-held video games.
May 22, 2025 at 2:24 PM
idk if this is funny when the numbers are actually true but hey here we are
March 21, 2025 at 3:06 PM
Found on a walk on the boardwalk in Halifax. A true monument to doomscrolling in the modern era.
March 15, 2025 at 3:33 PM
Lots of American boycotting in Canada 🇨🇦 today what with the tariffs and general situation, so I made a #meme to make myself feel better.

Our irrational attachment to Tims is really kinda funny
March 4, 2025 at 3:11 PM
One of my students made a cute variation of a raincloud plot using ggplot suitable for winter. The dots were changed to snowflakes! Maybe this could be a "snowflake plot"?

Code in the alt-text.
February 10, 2025 at 5:47 PM
A reviewer really wanted cross-lagged panel models I thought was inappropriate (for these data) so after 10 pages of modeling in the supplement that were basically pointless I got to get my critique of the reviewer in the published supplement, which is a pleasing mic drop moment for me.
February 5, 2025 at 2:42 PM
Just to add a little more joy to your day, seemed to me that a lot of this was AI slop and lo and behold, there's smoke. Without disclosing to the journal as required either, so naughty.

I guess that would explain why the cohen's d argument is basically a total non sequitur
January 29, 2025 at 3:11 PM
The one nice thing about winter is that my dog is at maximum fluffiness.
December 28, 2024 at 11:52 PM
I used #stats to determine the winner of my departmental chili dinner competition. After getting a LOT of wild suggestions, I eventually went with a linear mixed model.

A winner was crowned, though the difference wasn't statistically significant.

I made the data/code open for fun: osf.io/apzv8/
December 7, 2024 at 1:50 PM
Honestly it is a cool example if something with high relative consistency but poor absolute consistency, the scatterplot would have a large correlation, probably .8ish
November 24, 2024 at 1:23 PM
In a little pedagogical experiment, I tested whether in-person attendance for a workshop affects online quiz grades. Essentially, it's a dedicated time to work on stats problems with myself and TAs to answer questions.

Looks like a modest improvement, ~5% or half a letter grade.
November 11, 2024 at 1:27 PM
One of my students sent me this incredible #stats meme
October 22, 2024 at 10:59 AM
That's so cool, I didn't know that!

I once visited the Guinness brewery in Dublin, and after asking nicely they let me into the archives to look at some of the historical documents surrounding Gossett. Not nearly enough time, but my fave find was this hand-drawn distribution from him
October 19, 2024 at 12:32 PM
October 17, 2024 at 11:18 AM
I don't know of it'll help but here is a video of one in action i saw in a museum this year (which is why i could identify it)
October 6, 2024 at 7:15 PM
This is basically the truth
October 5, 2024 at 3:47 PM