phkwacker.bsky.social
Senior Lecturer in Statistics, University of Canterbury (NZ).
he/him
Bayesian stats, Applied Math, filtering & sampling
pls send me awesome vegan waffle recipes!
70 posts
125 followers
452 following
Regular Contributor
Active Commenter
comment in response to
post
Much appreciated!
comment in response to
post
I have become so accustomed to your math puns on my timeline that I was looking at your post way too long to figure out the punchline.
comment in response to
post
Good idea, this is also a strategy to make your achievements more impressive: "I did the dishes without using the axiom of choice"
comment in response to
post
Really intrigued what the going upstairs fallacy is!
comment in response to
post
Did you tell him to say "cheese"? (Also not sorry)
comment in response to
post
I hope this is on your academic CV!
comment in response to
post
Not even the worst bit, but, "in which contrasting viewpoints are aired"?
comment in response to
post
Rather, ũ
comment in response to
post
The first letter is clearly û (but one of the nails fell off, so it is slanting down a bit)
comment in response to
post
I always need to remind myself to draw additional (more than 4) arrows on rotational vector fields
comment in response to
post
Love how the bottom part of the ad suggests the three panelists are somehow championing specific perks for the audience of this show.
comment in response to
post
Also, because of exponential growth, a reduction by 50% is, like, nothing at all. This has annoyed me for a long time.
comment in response to
post
Really nice. Did you make those at Te Rua?
comment in response to
post
Post on Hackernews?
comment in response to
post
I love your absolutely feeble attempt at masking the secret word.
comment in response to
post
And in threes of you go one overlap further! Really cool!
comment in response to
post
Of course this is terribly messed up by the fact that Europeans learned about 0 too late, so the "identity translation" is called not 0 but "unison", and the next step (translation by 1) is called a "2nd" which leads to the unfortunate situation "2nd + 3rd = 4th" etc.
comment in response to
post
I can just about handle this, but I have big problems with higher numbers, e.g. increase of 162% meaning a factor of 2.62
comment in response to
post
Mettallica
comment in response to
post
Love your videos!
comment in response to
post
This is actually an amazing idea
comment in response to
post
Do you know mathscraftnz.org? This is kind of their whole deal :) (go to resources and scroll down -- I believe they have even more math-related knitting/crochet than what's there)
comment in response to
post
Don't forget connecting manuscript central to ORCID, and logging in there via your university email address!
comment in response to
post
My bad :D
comment in response to
post
More farm animal math!
comment in response to
post
Bonus image
comment in response to
post
Apparently, math conferences go like this: It's raining, everyone sits/stands in a puddle while some dude tries to convince everyone that pi=3.14, to the confusion of everyone, while notes taken dissolve in the puddle, letters and numbers floating away.
comment in response to
post
Very enjoyable talk!
comment in response to
post
Feedback more than welcome, I want to use that for my statistical learning class next year. Also, if this can be useful for you, happy to provide high-res versions of these images.
comment in response to
post
Summarising: The three different models have different bias-variance decompositions. The constant model has considerable bias (red point cloud not centered around ground truth), but it has low variance (small spread). Order 5 has minimal bias, but high variance. Quadratic seems good compromise.
comment in response to
post
And this is for 1000 independent models of polynomials, order 5.
comment in response to
post
Here the same thing for 1000 independent "quadratic" models of type f(x) = b0 + b1*x+ b2*x^2.
comment in response to
post
There's the related problem that democracies are susceptible to being destroyed from within from antidemocratic forces because (simplifying a bit) tolerance is not a good defense against hate and intolerance. Or the asymmetry between good journalism vs "flooding the zone with shit".
comment in response to
post
Maybe a good place to plug this excellent book: bookstore.ams.org/mbk-140