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/
https://cameronpatrick.com/
this is one of my favourite observations about sample size calculations. (afaik first articulated by Miettinen in 1985)
November 25, 2025 at 10:56 AM
this is one of my favourite observations about sample size calculations. (afaik first articulated by Miettinen in 1985)
as always, xkcd has you covered
November 24, 2025 at 1:22 AM
as always, xkcd has you covered
it's always this
November 19, 2025 at 2:53 AM
it's always this
What perfect album came out the year you turned 16?
November 17, 2025 at 4:44 AM
What perfect album came out the year you turned 16?
happy 11th anniversary to this email sent to all staff at the School of Mathematics and Statistics
November 4, 2025 at 2:16 AM
happy 11th anniversary to this email sent to all staff at the School of Mathematics and Statistics
found the random seeds used in the opening scene of Rosencrantz and Guildenstern Are Dead
November 3, 2025 at 12:54 AM
found the random seeds used in the opening scene of Rosencrantz and Guildenstern Are Dead
from now on every paper needs to have a Tigure 1
October 31, 2025 at 5:58 AM
from now on every paper needs to have a Tigure 1
I'm not normally one to go in for lazy criticism of other people's attempts at stats but this one boggles me. I think Simon Bazelon has discovered a new form of curve fitting failure, hitherto unknown even to xkcd
October 28, 2025 at 12:47 AM
I'm not normally one to go in for lazy criticism of other people's attempts at stats but this one boggles me. I think Simon Bazelon has discovered a new form of curve fitting failure, hitherto unknown even to xkcd
after some cool theoretical background, I think these slides sum up Thomas Lumley's talk well
especially "resist mathematical defaults", "rank tests have stronger assumptions than the t-test" & "ordinal data is not the easy option"
a very different take from Frank Harrell's writing on the subject!
especially "resist mathematical defaults", "rank tests have stronger assumptions than the t-test" & "ordinal data is not the easy option"
a very different take from Frank Harrell's writing on the subject!
October 27, 2025 at 4:13 AM
after some cool theoretical background, I think these slides sum up Thomas Lumley's talk well
especially "resist mathematical defaults", "rank tests have stronger assumptions than the t-test" & "ordinal data is not the easy option"
a very different take from Frank Harrell's writing on the subject!
especially "resist mathematical defaults", "rank tests have stronger assumptions than the t-test" & "ordinal data is not the easy option"
a very different take from Frank Harrell's writing on the subject!
I maintain that this is generally worthwhile for a few reasons:
1. You will almost always have to do this reformatting again, life is just like that
2. You will probably learn something from writing the code
3. Coding is fun, reformatting text by hand sucks
1. You will almost always have to do this reformatting again, life is just like that
2. You will probably learn something from writing the code
3. Coding is fun, reformatting text by hand sucks
October 26, 2025 at 2:39 AM
I maintain that this is generally worthwhile for a few reasons:
1. You will almost always have to do this reformatting again, life is just like that
2. You will probably learn something from writing the code
3. Coding is fun, reformatting text by hand sucks
1. You will almost always have to do this reformatting again, life is just like that
2. You will probably learn something from writing the code
3. Coding is fun, reformatting text by hand sucks
seconding this!
my usual choice is to use the date as a random seed, which is good enough for my purposes, but more creative sources of randomness are encouraged
my usual choice is to use the date as a random seed, which is good enough for my purposes, but more creative sources of randomness are encouraged
October 23, 2025 at 5:50 AM
seconding this!
my usual choice is to use the date as a random seed, which is good enough for my purposes, but more creative sources of randomness are encouraged
my usual choice is to use the date as a random seed, which is good enough for my purposes, but more creative sources of randomness are encouraged
decided to solve a puncture on my bike by converting my wheels to tubeless and anyway this afternoon has resembled the classic xkcd. in other news my bike is still not tubeless but at least the puncture is fixed!
October 4, 2025 at 5:49 AM
decided to solve a puncture on my bike by converting my wheels to tubeless and anyway this afternoon has resembled the classic xkcd. in other news my bike is still not tubeless but at least the puncture is fixed!
the screenshot below is about aircraft maintenance and plane crashes but wow the highlighted section really applies to statistical consulting too (albeit with less severe consequences)
September 30, 2025 at 10:47 AM
the screenshot below is about aircraft maintenance and plane crashes but wow the highlighted section really applies to statistical consulting too (albeit with less severe consequences)
melbourne: alright on a spring evening
September 19, 2025 at 12:34 PM
melbourne: alright on a spring evening
There was a patio11 article about this earlier this year which is a good read (Patrick's political asides notwithstanding); it seems to be a very bad deal for retail investors, bordering on an actual scam: www.bitsaboutmoney.com/archive/chic...
September 15, 2025 at 4:28 PM
There was a patio11 article about this earlier this year which is a good read (Patrick's political asides notwithstanding); it seems to be a very bad deal for retail investors, bordering on an actual scam: www.bitsaboutmoney.com/archive/chic...
what an incredible wobsite
September 11, 2025 at 1:47 PM
what an incredible wobsite
maybe Bayes is this meme:
September 9, 2025 at 2:06 PM
maybe Bayes is this meme:
I could have sworn I created this before on our Previous Parish, but couldn't find it so made it fresh.
I present:
OUR BLESSED mixed models // THEIR BARBAROUS fixed effects
I present:
OUR BLESSED mixed models // THEIR BARBAROUS fixed effects
September 9, 2025 at 1:49 PM
I could have sworn I created this before on our Previous Parish, but couldn't find it so made it fresh.
I present:
OUR BLESSED mixed models // THEIR BARBAROUS fixed effects
I present:
OUR BLESSED mixed models // THEIR BARBAROUS fixed effects
I do love a paper that finishes with a clear conclusion
September 7, 2025 at 7:47 AM
I do love a paper that finishes with a clear conclusion
every statistician who's worked with clinical researchers has met this person:
September 3, 2025 at 3:31 PM
every statistician who's worked with clinical researchers has met this person: