Sean Pinkney
@spinkney.bsky.social
I mostly post about probabilistic programming stuff, statistics, and R/Julia/Python (in that order). I'm a volunteer Stan developer and citizen scientist (papers on arxiv). Currently my day job is doing marketing analytics.
I checked for n>=3. For n = 3, the max is 4 which must be true.
November 6, 2025 at 1:11 AM
I checked for n>=3. For n = 3, the max is 4 which must be true.
Ah yep, just working under duress (kids)
November 6, 2025 at 1:05 AM
Ah yep, just working under duress (kids)
I didn't prove max but I'm not sure it can be bigger. Let me know what's right!
November 6, 2025 at 12:36 AM
I didn't prove max but I'm not sure it can be bigger. Let me know what's right!
2 cases bc of median. Max element is then
Even: n + n / 2
Odd: 2 n - (n + 1) / 2
Assuming positive integers for all n. The formula isn't too hard to work out afterward for the entire sequence
Even: n + n / 2
Odd: 2 n - (n + 1) / 2
Assuming positive integers for all n. The formula isn't too hard to work out afterward for the entire sequence
November 6, 2025 at 12:31 AM
2 cases bc of median. Max element is then
Even: n + n / 2
Odd: 2 n - (n + 1) / 2
Assuming positive integers for all n. The formula isn't too hard to work out afterward for the entire sequence
Even: n + n / 2
Odd: 2 n - (n + 1) / 2
Assuming positive integers for all n. The formula isn't too hard to work out afterward for the entire sequence
Wonderful apotropaic marks!
October 30, 2025 at 2:16 PM
Wonderful apotropaic marks!
Parallel processing in R
computing.stat.berkeley.edu
October 20, 2025 at 8:55 PM
I'll take one if you have any left
June 23, 2025 at 12:55 PM
I'll take one if you have any left
Which base measure are we in?
June 4, 2025 at 2:03 PM
Which base measure are we in?
So go re-run your models with simplex and report back with your results!
June 4, 2025 at 12:45 PM
So go re-run your models with simplex and report back with your results!
and to be comparable, if not a bit better, in all other cases.
What has changed is that we use the sum-to-zero vector transform and then softmax it. There are still n-1 free variables but the over/underflow for finite precision computing is less likely. 2/
What has changed is that we use the sum-to-zero vector transform and then softmax it. There are still n-1 free variables but the over/underflow for finite precision computing is less likely. 2/
June 4, 2025 at 12:45 PM
and to be comparable, if not a bit better, in all other cases.
What has changed is that we use the sum-to-zero vector transform and then softmax it. There are still n-1 free variables but the over/underflow for finite precision computing is less likely. 2/
What has changed is that we use the sum-to-zero vector transform and then softmax it. There are still n-1 free variables but the over/underflow for finite precision computing is less likely. 2/
This is the pre-pre-print of the meta-meta-analysis
May 24, 2025 at 6:41 PM
This is the pre-pre-print of the meta-meta-analysis
Oh I first read this as the water cycle is changing as a good thing rather than a permanent thing
March 29, 2025 at 10:00 PM
Oh I first read this as the water cycle is changing as a good thing rather than a permanent thing
Hi I don't know you, you don't know me but I have the same feels. Come say hi sometime to me
February 23, 2025 at 1:30 AM
Hi I don't know you, you don't know me but I have the same feels. Come say hi sometime to me
Please let me know! I'd love to see timing and ESS comparisons
February 20, 2025 at 2:52 PM
Please let me know! I'd love to see timing and ESS comparisons