Tim Howes
LightNews LightNews
banner
timhowes.bsky.social
Tim Howes
@timhowes.bsky.social
410 followers 910 following 4 posts
computational biologist and data scientist
San Francisco Bay Area
biology, evolution, statistics, open source software
Posts Replies Media Videos
Reposted by Tim Howes
daryllmarie.bsky.social
And one more, there was an iguana party on Key West this morning 🦎🌿
An iguana’s upper body photographed up close. Behind it, a blurred second iguana can be seen
November 8, 2025 at 7:04 AM
Reposted by Tim Howes
fossilforager.bsky.social
gartastic
An illustration of two alligator gar on a teal background. The fish have a long alligator-like snout and are covered in armored scales. The fish are greenish-brown and have some speckled darker spots and markings on their fins and back.
September 11, 2025 at 6:25 PM
Reposted by Tim Howes
k-hermit.com
September 11, 2025 at 12:31 AM
Reposted by Tim Howes
cyrilpedia.bsky.social
'We hypothesized that cDC suppression in PDAC may further impair tumor immunity. We found that low tissue expression of Flt3L partially underlies cDC deficits. Treatment with systemic Flt3L & CD40 agonists restored cDC number & function in murine models & clinical trial samples from PDAC patients'
Combined Flt3L and CD40 agonism restores dendritic cell–driven T cell immunity in pancreatic cancer
Flt3L and CD40 agonism enhance dendritic cell immunosurveillance in human and murine pancreatic cancer and engage type I immunity.
www.science.org
September 3, 2025 at 11:33 PM
Reposted by Tim Howes
dingdingpeng.the100.ci
Ever stared at a table of regression coefficients & wondered what you're doing with your life?

Very excited to share this gentle introduction to another way of making sense of statistical models (w @vincentab.bsky.social)
Preprint: doi.org/10.31234/osf...
Website: j-rohrer.github.io/marginal-psy...
Models as Prediction Machines: How to Convert Confusing Coefficients into Clear Quantities Abstract Psychological researchers usually make sense of regression models by interpreting coefficient estimates directly. This works well enough for simple linear models, but is more challenging for more complex models with, for example, categorical variables, interactions, non-linearities, and hierarchical structures. Here, we introduce an alternative approach to making sense of statistical models. The central idea is to abstract away from the mechanics of estimation, and to treat models as “counterfactual prediction machines,” which are subsequently queried to estimate quantities and conduct tests that matter substantively. This workflow is model-agnostic; it can be applied in a consistent fashion to draw causal or descriptive inference from a wide range of models. We illustrate how to implement this workflow with the marginaleffects package, which supports over 100 different classes of models in R and Python, and present two worked examples. These examples show how the workflow can be applied across designs (e.g., observational study, randomized experiment) to answer different research questions (e.g., associations, causal effects, effect heterogeneity) while facing various challenges (e.g., controlling for confounders in a flexible manner, modelling ordinal outcomes, and interpreting non-linear models). Figure illustrating model predictions. On the X-axis the predictor, annual gross income in Euro. On the Y-axis the outcome, predicted life satisfaction. A solid line marks the curve of predictions on which individual data points are marked as model-implied outcomes at incomes of interest. Comparing two such predictions gives us a comparison. We can also fit a tangent to the line of predictions, which illustrates the slope at any given point of the curve. A figure illustrating various ways to include age as a predictor in a model. On the x-axis age (predictor), on the y-axis the outcome (model-implied importance of friends, including confidence intervals). Illustrated are 1. age as a categorical predictor, resultings in the predictions bouncing around a lot with wide confidence intervals 2. age as a linear predictor, which forces a straight line through the data points that has a very tight confidence band and 3. age splines, which lies somewhere in between as it smoothly follows the data but has more uncertainty than the straight line.
August 25, 2025 at 11:49 AM
Reposted by Tim Howes
a13x.bsky.social
DuckDB may have an adorable mascot, but this is serious DB tech! As a larger-than-memory system, data durability is critical!
avi.im v @avi.im · Aug 10
I went through DuckDB's WAL, and it does everything I was asking for in my blog post:

1. Per record checksum
2. Explicit error on checksum failure
3. Configurable behavior
4. Partial recovery
5. Safe truncation of the WAL only when WAL contents are checkpointed
avi.im v @avi.im · Jul 24
Published a new post: "PSA: SQLite WAL checksums fail silently and may lose data"

This is a follow up to my previous posts. When SQLite encounters checksum failures in WAL, instead of raising an error, it drops all subsequent frames; even if they are not corrupt. It's not a bug
August 10, 2025 at 3:03 PM
Reposted by Tim Howes
us.theconversation.com
Where first graders watch educational media, before the impact of eliminating federal funds:
* PBS - 45%
* Nickelodeon - 14%
* YouTube - 9%
(from a 2025 study by child development researchers)
PBS accounts for nearly half of first graders’ most frequently watched educational TV and video programs
PBS KIDS produces popular age-appropriate programs. It also has a website and multiple apps with games and activities.
buff.ly
August 10, 2025 at 3:08 PM
Reposted by Tim Howes
juliasilge.com
I'm excited to speak this afternoon at #useR2025 on outgrowing your laptop with #Positron for #rstats users!

You can check out my slides at juliasilge.github.io/useR-2025/
Galaxy brain meme format outlining options for working with data: CSV file, parquet & duckdb, databases, and remote SSH sessions
August 10, 2025 at 1:33 PM
Reposted by Tim Howes
coastalpaleo.bsky.social
A couple of giant green anemones (Anthopleura xanthogrammica) in a Santa Cruz #tidepool, dwarfing a field of their smaller relative, aggregating anemones (Anthopleura elegantissima). 🦑🦀 #norcal
Two giant green anemones in a tidepool: they are large and circular with an olive green stalk and bright lime green tentacles fading to a more khaki color.
August 4, 2025 at 5:06 PM
Reposted by Tim Howes
whysharksmatter.bsky.social
Glow-in-the-dark marsupial shows off its luminous fur — July’s best science images
Glow-in-the-dark marsupial shows off its luminous fur — July’s best science images
The month’s sharpest science shots, selected by Nature’s photo team.
www.nature.com
August 4, 2025 at 5:28 PM
Reposted by Tim Howes
shteyngart.bsky.social
Had a great time on @KQED Forum.

www.kqed.org/forum/201010...
In Gary Shteyngart’s “Vera, or Faith,” A Child Navigates Family, American Dystopia | KQED
We talk to writer Gary Shteyngart about the future and families.
www.kqed.org
July 28, 2025 at 9:48 PM
Reposted by Tim Howes
eikofried.bsky.social
Psychologists & related fields: what is a big methods question that you believe remains somewhat unanswered & that you'd love to see adressed? There may be an opportunity for a large-scale meta-science project with many teams trying to figure out a question.

Any thoughts welcome! #psychscisky
July 30, 2025 at 2:03 PM
Reposted by Tim Howes
danielbolnick.bsky.social
Many attendees arrived by the Lady Rose Ferry on Sunday, sailing three and a half hours down the Alberni inlet fiord. Here’s the ferry arriving at Bamfield…
July 28, 2025 at 4:44 PM
Reposted by Tim Howes
topepo.bsky.social
Positron is definitely visually more than RStudio, and this is a helpful overview.
posit.co Posit @posit.co · Jul 28
Take a quick tour of Positron, Posit's next-generation data science IDE, built by the creators of RStudio.

Read the blog to learn more: posit.co/blog/a-quick...
A screenshot of the Positron interface, labeled with its components: "Activity bar," "Primary side bar," "Editor," "Secondary side bar," and "Panel." The text "A quick tour of Positron" is on the left.
July 28, 2025 at 4:57 PM
Reposted by Tim Howes
vincentab.bsky.social
"My First R Package"

Next week I’ll be giving a hands-on workshop on #RStats We'll start from scratch and build our very own 📦

Re-use go-to functions, boost reproducibility, and share code with colleagues.

I always a blast teaching this and am excited to meet the new group!

tinyurl.com/mv2hrd8n
July 17, 2025 at 11:25 AM
Reposted by Tim Howes
dingdingpeng.the100.ci
At this point, I might as well --
Here's an infographic showing different ways to include age as a predictor. The top shows two extremes, just as a plain old numerical predictor (imposes linear trajectory) vs. categorical predictor (imposes nothing whatsoever). And then three solutions in between!
Infographic illustrating different ways to model age. First panel shows two "extreme" cases; including age as a linear numerical predictor (df = 1) or including age as a categorical predictor (df = number of years of age minus 1). Second panel shows an intermediate solution in which age is categorized into broader bins (df = number of categories minus 1, here 5 - 1 = 4). Third panel shows an intermediate solution in which age is included with a polynomial (df = degrees of freedom of the polynomial, here 4). Fourth panel shows an intermediate solution in which age is modeled with the help of splines (df = degrees of freedom of the splines, here 4).
July 16, 2025 at 12:33 PM
Reposted by Tim Howes
fossilforager.bsky.social
A lil tribute to the kelp forests along the California coast 🌊✨
An illustration featuring a leopard shark, bat ray, and the California state marine fish: the garibaldi. They are swimming next to giant kelp and illustrated on a vibrant blue background.
July 8, 2025 at 5:11 PM
Reposted by Tim Howes
fossilforager.bsky.social
I just think sea slugs are neat 💕
A graphic-style illustration of 3 sea slugs (known as nudibranchs). Dark blue bold rounded text below the slugs reads “Nudibranch Admirer”. The slugs are vibrantly colored with hues of blue, yellow, orange, and purple and are illustrated on a saturated light blue background.
June 19, 2025 at 7:22 PM
Reposted by Tim Howes
spacecoyote.com
sometimes Louie will babble nonsense that vaguely sounds like @bobservo.bsky.social
June 12, 2025 at 8:28 PM
Reposted by Tim Howes
whysharksmatter.bsky.social
Anglerfish ancestors once roamed the seafloor. Here's how we know : Short Wave : NPR
Think anglerfish are weird? Wait until you hear how they evolved : Short Wave
There are over 200 species of deep-sea anglerfish; some are long and thin, some are squat and round, some have fins that they use to "walk" along the sea floor, and others have huge eyes set far back…
www.npr.org
June 5, 2025 at 8:16 PM
Reposted by Tim Howes
rosemarymosco.com
All proceeds from my @topa.to store in June go to the Institute for Bird Populations, @instbirdpop.bsky.social! Times are tough for nonprofits, and monitoring bird populations is more important than ever. Show your support with a tasteful print or tasteless mug. topatoco.com/collections/...
The super-talented artist and author Rosemary Mosco is donating proceeds from her shop in the month of June to IPB! There's an image of a poster of female North American birds, a yellow warbler tshirt, and a mug that says Mornings Can Kiss My Cloaca.
June 1, 2025 at 1:43 PM
Reposted by Tim Howes
jocelynanderson.bsky.social
A male Baltimore Oriole flying towards his next tree top to perch and sing his clear and sweet song.
May 27, 2025 at 10:19 PM
Reposted by Tim Howes
hrbrmstr.dev
#DuckDB DuckLake — a new lakehouse format built on pure SQL — is out!

duckdb.org/2025/05/27/d...

duckdb.org/docs/stable/...
DuckLake: SQL as a Lakehouse Format
DuckLake simplifies lakehouses by using a standard SQL database for all metadata, instead of complex file-based systems, while still storing data in open formats like Parquet. This makes it more relia...
duckdb.org
May 27, 2025 at 4:52 PM
Reposted by Tim Howes
cameronpat.bsky.social
I would say that true case-control studies are not that common in epi any more, IME odds ratios get used in clinical research mostly because you get them by pressing the "logistic regression" button and doing zero additional thought. My brain dump on ORs here: cameronpatrick.com/post/2023/07...
Cameron Patrick - You are what you ATE: Choosing an effect size measure for binary outcomes
Wherein I try to make sense of ongoing debates in the statistical community about how to analyse and report clinical trials targeting binary outcomes, and then write some R code to practice what I hes...
cameronpatrick.com
May 26, 2025 at 1:30 PM
Reposted by Tim Howes
cameron.pfiffer.org
Goodnight, sun
May 24, 2025 at 3:08 AM