back
user profile
apwheele
1,887karma·374submissions·November 10, 2021
about
Data scientist. Former academic in criminal justice field.
Personal blog at https://andrewpwheeler.com/
Consulting at https://crimede-coder.com/
Large Language Models for Mortals: A Practical Guide for Analysts (book), https://crimede-coder.com/blogposts/2026/LLMsForMortals
recent activity (374 total)
comment
I create my own classes for this. (Essentially to do the same thing as sklearn pipelines, but I like creating my own classes just for this debugging/slowly expand functionality reason.) Something…
comment
I don't see a conflict, unions would still be obligated to represent officers. It is just criminal behavior investigations would be shifted entirely to the DAs office (to prevent Joe from investi…
comment
IMO I don't think unions are the fundamental issue -- many PDs internal affairs leave something to be desired (and police need unions for the same reason everyone else needs a union). So I thin…
comment
Not about randomness - but about curve fitting. It is actually very difficult to verify non-linear effects -- or maybe I should say the opposite. The statistical tools we use to identify non-lineariti…
comment
Like most science reporting, the headline is a bit over-the-top, but the article is pretty straightforward. You need to consider here the control/counter-factual -- [time fasting + restricted cal…
comment
I've always taken part of my job as a data scientist is to articulate when data is not sufficient to meet a particular a goal (and to outline what data would be necessary). For some goals doing s…
comment
I struggle with this (kiddo is at the stage will be applying in a few years, so have thought about it), as it essentially relies on network effects with a large/unknown variance. (Is the MBA netw…
comment
As a researcher who has (and continues to) use the publicly available census data, I agree with this. IMO it makes more sense to have higher quality micro level data products that are only available i…
comment
This doesn't work as a reasonable objective measure of population mental health disorders for several reasons. 1) The oversampling of the training set makes it uncalibrated when applied to the ge…
comment
I wonder what the 40% who wouldn't eat food fertilized by urine think about the fact that urea is a common cow feed supplement.
comment
I think a more basic problem is people don't even know how to formulate meaningful probability hypothetical/counterfactuals to begin with (let alone update them). For Covid stuff pretty much…
comment
I prefer Gigerenzer’s idea of natural frequencies over the Venn diagrams. https://www.researchgate.net/figure/Gigerenzer-Hoffrage-Natu... …
comment
While I really love Tufte's books, for more direct advice I recommend Albert Cairo's The Functional Art . I don't remember discussion of fonts offhand, but everything else in your list…