1/14
The "Face" of Family: A Forensic Deep Dive 🧬📐

I’m often asked: "One is my mother, the other two are my aunts. How can you be sure?" As a data nerd, "vibes" aren't enough. I ran a multi-modal biometric analysis using Facial Anthropometry and Unsupervised Machine Learning to prove the kinship. This isn't just about looking alike; it’s about the underlying mathematical architecture of the human skull and soft tissue. Let’s look at the math. 🧵👇 #BioStats #Forensics

New blog post out!

Power analysis – A flexible simulation approach using R
https://www.nicolaromano.net/data-thoughts/power-analysis-simulation/

I go through why power matters, how to use Monte Carlo simulations to estimate it, and how this approach can be useful not only to define sample size, but also to refine experimental design.
#rstats #statistics #biostats #datascience #experimentaldesign #poweranalysis

Power analysis - A flexible simulation approach using R - Nicola Romanò

In this post we discuss how to cakcukate the statistical power of an expertiment using a Monte Carlo simulation in R. We'll see how this can help refine our choice of experimental design.

Nicola Romanò

A milestone! FDA expands accepted R file formats, resulting directly from joint work between industry and FDA through the R Consortium Submissions Working Group.

FDA expands accepted eCTD file formats for R packages

Newly accepted formats for R packages now include:
.rds, .rdb, .rdx, .rdata / .rda
.md, .rd
Expanded use of .zip and .html for delivering full R packages.

Details: https://r-consortium.org/posts/expanded-fda-ectd-file-format-support-for-r-packages

#rpharma #fda #regulatory #clinicaltrials #biostats #opensource

@arjen What's sad is that they think they'll keep their place in the #Big10 and get back into the #AAU with this cut. "We have a #biostats department at UNMC" -- well, yeah, but biostatisticians don't design ag field experiments, or specialize in data visualization (our department has 2 #datavis researchers), or teach consulting, and they probably don't have extra time to support a #datascience program.

It's very short sighted.

Wondering if I should start doing #biostats consulting work again...

I'd have to spin up a website and probably order some business cards again. More importantly, I would need to find an angle to work.

I previously focused on statistics for life science research and healthcare, basically learned everything is driven by regulatory compliance... which is fine and dandy, but I feel like there's something more I can be doing with my skills (and not working for a fucking insurance company). Hmm.

Asking for help/refs: I have observational data where some patients always get treatment T=A due to their diagnosis (D) while the rest get either T=A or T=B based on clinical judgement. It seems to me that it might be possible to get closer to causal claims for T by exploiting the (lack of) differences between the "T=A, D=1" and "T=A, D=0" groups. This seems akin to IV analysis with D as instrument. Any ideas? A bit more detail at: https://discourse.datamethods.org/t/observational-data-with-diagnosis-partially-determining-treatment-imperfect-instrumental-variable/6983 #stats #instrumentalVariable #biostats
Observational data with diagnosis partially determining treatment (imperfect instrumental variable?)

Here’s the setting - we have a retrospective dataset of patients undergoing a certain surgery. The surgery has two variants, let’s call them A and B. We are interested in comparing a set of outcomes like length of hospital stay and blood loss in each variant. The choice of variant is based on clinical judgement and thus there are inevitable selection effects biasing the comparison. If that was all, we’d have little options beyond just reporting the results descriptively. We however have an extr...

Datamethods Discussion Forum
Come help us - soil carbon, perrinial biomass and sampling frames, oh my!!! Spread the word
https://www.usda.gov/oce/energy-and-environment/climate-change-fellows-program
#soil #biostats #agroforestry
USDA Climate Change Fellows Program

Overview USDA is seeking qualified applicants for inclusion in the USDA Climate Change Fellows Program (CCFP).  Climate change presents real threats to U.S. agricultural production, forest resources, and rural economies.

#Biostatisticians play a key role in helping novel therapies get to patients faster–they help design #clinicaltrials. Discover how “PlatformDesign” can help craft multi-arm clinical trials. The software was published by Drs. Haito Pan, Xiaomeng Yuan and Jing Jing Ye. Read the blog post. http://bit.ly/3KBTflV
#Biostats #StJude #StJudeResearch
Biostatisticians are key to getting therapies to patients faster

Scientists from St. Jude created PlatformDesign a software package that clinicians can use to add study arms to a clinical trial. Read about the approach.

Stjude Blogs

Looking for #bioinformatics,#biostats, #ecology, #popgen, #fishbiology jobs or postdocs in the Calgary, AB (Canada) region. I'm well versed in popgen, genome assemblies, bioinformatics, workflow design, fish ecology, Bash, R, Python, Julia. Does anyone have or know of any leads? Thanks!

CV: https://pdimens.github.io/CV_Dimens.pdf
Website: https://pdimens.github.io

#science #jobs #postdoc #academia