On reflection, I don't think I got good at math until I realised it's just a language, like french or whatever. same is true for writing code. i think humanities people (which is how I identified myself for many years!) would be able to pick it up a lot faster with this framing.
i'm not saying everyone needs to learn math, just like not everyone needs to learn english or french or chinese or zulu or anything else -- diversity of skills within a team/department/profession/world is the only way to go.
however i will say what sets math apart is that math is the language that the universe speaks
• • •
Missing some Tweet in this thread? You can try to
force a refresh
Just finished teaching and reluctantly forced myself to open up a paper i'm slightly late in reviewing (because, pandemic) -- but got immediately drawn in by the excellent introduction! Now excited to spend my day on this. this is the thing an introduction has to accomplish.
i feel that you can really tell when a paper is written for you -- the reader -- versus being written for the author's own joy or whatever. if you want to communicat effectively, you have to think about your interlocutor! "what's my reader thinking now? what's she feeling now?"
and you have to take her seriously because you can't force her to read your paper -- you have to convince her to keep reading. all writing intended for an audience has a persuasive element to it. your reader can easily just put you down if she wants!
statistics is the most beautiful and egalitarian discipline of all of those i have studied, because when we are confused about anything in statistics we are almost always confused about the elementary, foundational concepts
in my personal experience this is not true when learning languages, history, economics, or other branches of mathematics
Example 1: sometimes very smart people suggest nonlinear regression as an alternative to quantile regression, when these address COMPLEYELY different problems. the former relaxes the linearity of the conditional mean function and the latter relaxes the focus on the mean itself.
i think we can acknowledge it's unfair that attacks on academic titles / expertise will tend to target women and minorities (& that we naturally wish to defend ourselves) while also not believing that anything on this earth is or can be earned because merit is a broken concept
not here for people whose expertise is never questioned (nor time devalued and service assumed available) pontificating about how titles are sooo silly, but definitely also not here for "i earned this"
you don't "earn" a phd with hard work, you get one by being cursed by a malevolent spirit
So some very smart folks have asked about how we would apply the AMIP metric to studies of rare events. This kicked off a discussion of what robustness checks are really for, and I want to take that set of questions seriously in this thread.
I think robustness checks mainly (ought to) function to illuminate how variation in the data is being used for inference, and we should then be able to discuss whether we think this is a reasonable situation and adjust our confidence in the results.
The problem is not that there is SOME change to which our analyses are sensitive -- of course there is, they has to be. If your results aren't affected by ANY change you make to the analysis, something has gone horribly wrong with the procedure.
Guys this paper is super important. Arnold, Hull and Dobbie are among the most careful applied econometricians we have, and the explosion of algorithmic decision making means this method -- and their finding of pervasive discrimination -- could hardly be more timely.
hey since we were discussing the other day how even just "select high contrast areas to thumbnail" is a racist decision rule given the history of photography AND since you guys only understand one language, i made this for u
"average person eats 3 spiders a year" factoid actualy just statistical error. average person eats 0 spiders per year. Spiders Georg, who lives in cave & eats over 10,000 each day, is the AMIS. we've decided to show quantiles of the spider consumption distribution instead.