Lightnews — Scholar-powered news

Uriel Cohen Priva @urielcohenpriva.bsky.social · Jul 15

They're not "the same", and they are usually off by some linear operation, but the fact that they are not normally distributed simply doesn't matter

Uriel Cohen Priva @urielcohenpriva.bsky.social · Jul 15

Linguists seem to believe that modeling an effect using random effects causes the estimation to be very different than using fixed effects, because random effects are assumed to be normally distributed. Usually, the estimates are (almost) identical, regardless of the actual distribution.

The R code shown is:
g <- 1:200 |> as.character()
g.x <- 2**rnorm(length(g))
n <- 10**4
y <- rnorm(n) + g.x
d <- data.frame(y, g)
m.lmer <- lmer(y ~ 0 + (1 | g), d)
m.lm <- lm(y ~ 0 + g, d)
cor(coefficients(m.lm), ranef(m.lmer)$g[,1])

and the result is 1 (the two perfectly match)

The following R code:

g <- 1:200 |> as.character()
g.x <- runif(length(g))
n <- 10**4
y <- rnorm(n) + g.x
d <- data.frame(y, g)
m.lmer <- lmer(y ~ 0 + (1 | g), d)
m.lm <- lm(y ~ 0 + g, d)
cor(coefficients(m.lm), ranef(m.lmer)$g[,1])

The result is again 1

R code:

g <- 1:200 |> as.character()
g.x <- c(runif(length(g)/2, 1000, 1100), runif(length(g)/2, 0, 100))
n <- 10**4
y <- rnorm(n) + g.x
d <- data.frame(y, g)
m.lmer <- lmer(y ~ 0 + (1 | g), d)
m.lm <- lm(y ~ 0 + g, d)
cor(coefficients(m.lm), ranef(m.lmer)$g[,1])

Again, the correlation is 1, despite the very non-normal distribution

1

Reposted by Uriel Cohen Priva

Charles B. Chang @cbchang.bsky.social · Feb 6

So sad to hear of Ian Maddieson's passing. He was an amazing linguist but also an inspiring instructor and a big part of why I went into phonetics. I've always been in awe of the depth and breadth of his knowledge of the most obscure languages and will miss his kindness and wit. RIP, Ian~ 🐦🐦

Ian Maddieson at Berkeley Linguistics' commencement, with Rebecca Cover and Charles Chang

5 30

Reposted by Uriel Cohen Priva

Christian DiCanio @cdicanio.bsky.social · Jan 30

New #labphon publication out today. I was happy to help this one along.

www.journal-labphon.org/article/id/1...

Contrastive vowel length and segment duration in production and perception in Djambarrpuyŋu

This paper deals with segment duration and phonological length in production and perception in the Australian language Djambarrpuyŋu. It provides an acoustic phonetic account of vowel and consonant du...

www.journal-labphon.org

1 7

Uriel Cohen Priva @urielcohenpriva.bsky.social · Jan 14

🪬🪬🪬 that's early!

1

Uriel Cohen Priva @urielcohenpriva.bsky.social · Jan 9

Her 8yo bilingualness:

/hameil oʊnli χosemz et hakor/
'the-coat only blocks+z ACC the-cold'

That's a double decker code switch

2

Uriel Cohen Priva @urielcohenpriva.bsky.social · Dec 21

זה קרה בפלורנטין ואת משת"פית של לוינסון?

1 1

Uriel Cohen Priva @urielcohenpriva.bsky.social · Dec 18

Thanks for revitalizing it, it's really a must read material for everyone, not just linguists. I just told my kids about it this morning. They were very impressed.

1

Uriel Cohen Priva @urielcohenpriva.bsky.social · Dec 18

I will assign the bunny paper next time I teach intro. Thanks for that!

May his memory be a blessing (evidently it already is)

1 8

Uriel Cohen Priva @urielcohenpriva.bsky.social · Dec 12

You can now share our Linguist List post as well!

Open area Visiting Assistant Professor at Brown, deadline February first

linguistlist.org/issues/35-35...

Uriel Cohen Priva @urielcohenpriva.bsky.social · Dec 11

Brown's Program in Linguistics (that us!) is searching for a Visiting Assistant Professor (open field). One year appointment, possibly renewable, 2:2 teaching load, February 1st deadline

Please apply / retweet / forward

Email me if you have any questions

apply.interfolio.com/160337

Apply - Interfolio {{$ctrl.$state.data.pageTitle}} - Apply - Interfolio

apply.interfolio.com

10 13

Reposted by Uriel Cohen Priva

andriescoetzee.bsky.social @andriescoetzee.bsky.social · Dec 6

The search for new (co-)editor of Language has started! Please circulate widely. And do reach out if you have questions and/or are interested in applying. I did this job for six years — it was hard work, but also very rewarding.

Journal Language Seeks Next Co-Editor

mailchi.mp