Topic

Data analysis

Working with real datasets: what they recorded, what they omit, and what can be concluded from them.

About

Team

The accountable lead for work this practice takes on, and the scope that one person sets.

Data

How datasets are sourced, documented, and made legible to the people they describe.
Research

How questions are framed, evidence is gathered, and uncertainty is reported.
Visualization

How charts are chosen and tested so the encoding carries the finding rather than decorating it.

U.S. Bureau of Labor Statistics

The federal source for employment and wage series used in the local economic resilience work.
U.S. Census Bureau

The federal statistical agency behind the population and economic estimates several projects here depend on.

Charts that survive without color

An independent demonstration of chart encodings that do not rely on hue.
Reading a recommender notebook in the open

A published Jupyter notebook comparing three recommendation approaches, rendered as readable prose rather than a download.
Taste Profile play counts

The play-count data behind the recommender comparison: what a row of it actually records, and why the extract that was modelled is the dense middle of a distribution rather than the whole of one.
The popularity baseline was harder to beat than expected

What the recommender notebook actually showed. Tuned collaborative filtering improved on recommending the most-played titles by less than the evaluation's own noise.
What a good statistical brief does in four pages

A close reading of an NCHS mortality brief, embedded in full, as an example of publishing a document without making the reader download it blind.
What collaborative filtering assumes about people

A written-up account of how user-user and item-item recommendation differ, and what each one quietly assumes about the people it is describing.