I find it WILDLY FRUSTRATING implementing contrast coding in Julia.
If I use ContrastCoding(), I can specify my own contrast matrices (yay!) but I can't label them. So the regression output just reuses my actual factor levels to label an actual model term that means something like, say, 'mean of levels A and B vs. mean of levels C and D'. Or whatever. To interpret my model, I must make physical notes on a piece of paper about what each term means.
If I use HypothesisCoding(), I can label everything nicely (yay!), but it insists on re-weighting my matrix for me, so if I put in the matrix I want to use, it changes it into something else. I have to put in a different matrix, with the positive term as 1 and the negative terms as fractions adding up to 1, to trick it into reweighting the matrix into what I actually want it to be.
I LEARNED HOW TO BUILD CONTRAST MATRICES
BY HAND JULIA! Don't try to do it for me. You're just breaking it!
Judging from Dave Kleinschmidt's very useful tour of it, I think possibly it was simply built for someone who learned to specify contrast matrices differently from me.
I infer this from the bit where Dave remarks that the hypothesis matrix is transformed into a contrast matrix in a way that he wouldn't be able to derive off the top of his head. To me, the contrast matrix is great! It's the hypothesis matrix that I have to puzzle over.
@ml@academicchatter I subscribe to couple of mailing lists -- Architectures and Mechanisms of Language Processing, and Human Sentence Processing Society. That keeps me up to date with job announcements, calls for conference papers, and the occasional large collaborative project.
I used to sign up for lists of new publications form key journals, but now the only time I have for reading is when I'm doing a lit review for a specific project anyway, and then I just run to Google Scholar.
Is there a #linguistic term for an interlocutor saying the last word of the previous speaker’s sentence in unison with them? Not just occasionally or when the previous speaker is having trouble recalling a word, but nearly every sentence, possibly even when that sentence is not the end of a turn? I’m looking for articles or research about this out of personal curiosity.
I made a new Mastodon bot, called "I Hope This Email Finds You.” Twice a day it proposes a novel way to conclude that sentence. (It uses phrases from Google Books that include the phrase “finds you.”) I've been having fun reading these, so I turned it into a bot because you, too, might have fun reading them. https://botsin.space/@thisemailfindsyou/112295528875440987
@bud_t@academicchatter One of my students recently finished her degree, and she's an RA on a current project. I love emailing people and adding, 'Please direct your questions to my colleague, Dr [former student], for issues relating to [project component].'
So outrage-seekers have discovered the National Trust’s scones are vegan. As a Trust member for nearly 40 years, diagnosed with cow’s milk protein intolerance over 30 years ago I can confirm dairy-free scones and cakes have been available for years. No one else ever seems to notice, and it makes solid business sense to cater for every potential customer when income from tea rooms supports the Trust’s work. (continues)
@JulietEMcKenna And even if the intolerances didn't kill children, they were still recognized among adults. I'm thinking of all the 19th century books about people with dyspepsia, or how someone who was generally lucky or healthy was described as having 'good digestion'.
Then there's poor Mr Woodhouse, in Emma, who can't stomach anything other than very thin gruel. Dietary intolerances were definitely behind at least some of that, I'm sure, even if they were described with different words.
Somersby on Dalziel Drive on the Southside of Glasgow. Designed by H.E Clifford in a Scots Baronial type style, it was build in 1902 for William T. Geddes, the Glasgow oil and produce broker.
I'm reading a book that mentions inherited #FountainPens, but also is set before railways to Inverness opened, so I'm doing a bit of research into relative timelines to see if this is even possible.
Turns out it is, just barely: First railway to Inverness opened 1854, while eyedropper fountain pens were patented in 1809. So if this takes place 1850, fountain pen is 30 years old, it's possible. (But not if pen is self-filling, patented in1832.)
@paradoxmo Yes, I remember that. It was during the writing of The Mikado, which came out in 1865, I believe, so either the writer of Topsy Turvy was a bit behind the times, or else fountain pens proper took half a century to catch on. I could believe either.