Cameron Patrick
banner
cameronpat.bsky.social
Cameron Patrick
@cameronpat.bsky.social
biostatistician @ University of Melbourne Statistical Consulting Centre. enjoyer of multiple imputation, RCTs, and DAGs. always graph your data. also runs, bikes, hikes, etc. he/him #BiInSci 🏳️‍🌈

https://cameronpatrick.com/
(I'm completely with you over their behaviour over the last few years! just trying not to be completely doomerist about the future of the USA)
February 5, 2026 at 3:06 AM
their actual letter is a lot better than that NYT screenshot above suggests. I mean it's still "pretty please start following the law" but it's a also a bunch of clear points that should be the bare minimum for a police force in a democratic country:
bsky.app/profile/sahi...
Schumer & Jeffries lay out the Democratic demands for a DHS funding deal in a letter to the top Republican leaders
February 5, 2026 at 3:02 AM
there is also a trade-off between cost, space and location! if, for a given cost, you can either have a city apartment where you can walk to work, or a big house in car-dependent suburbia an hour's drive from the city, different people may make different choices, & it's good to have options
February 5, 2026 at 2:00 AM
{ordbetareg} master race!
February 5, 2026 at 1:32 AM
this distribution is triggering my general anxiety disordinal
February 5, 2026 at 1:12 AM
agreed but I feel that's a more advanced level of understanding
February 4, 2026 at 11:19 AM
yes - in my mind there's nothing that implies a fixed effect has to be categorical. (and e.g. if you have a look at the summary() output from lme4 or glmmTMB it'll show continuous variables in the fixed effects table too)
February 4, 2026 at 7:19 AM
yeah this is why biostats and econ people end up talking past each other about this
February 4, 2026 at 7:00 AM
also! I will be teaching an online short course on Mixed Models in R next week. places still available! scc.ms.unimelb.edu.au/statistics-c...
Mixed Models in R
Mixed Models in R
scc.ms.unimelb.edu.au
February 4, 2026 at 6:24 AM
exactly, although that feels a bit redundant to state? but this is where I struggle with the econ terminology because to me "fixed effects model" just means any regression that doesn't include random effects
February 4, 2026 at 6:22 AM
the idea of Julia is to solve the two-language problem (high level languages like R and Python that need a lower level language like Fortran or C++ for anything that needs to go fast) with One Language To Rule Them All ... love the idea though haven't used it enough to be really won over
February 4, 2026 at 5:50 AM
Reposted by Cameron Patrick
There's more than one way to do it: Perl, R, Stan
There's exactly one way to do it: Python, BUGS
There's at most one way to do it: SPSS, SAS
February 4, 2026 at 5:21 AM
we're definitely a cult
February 4, 2026 at 5:20 AM
this clearly calls for integer-inflated ordered beta regression
February 3, 2026 at 11:45 PM
Reposted by Cameron Patrick
yeah for most of us absorbing the chaos void isn't very healthy. i'm fine obviously, i don't have a chaos void problem... but almost none of us should be doing this. anyone up for void summoning later?
February 3, 2026 at 3:47 AM