Blog, page 52

Field notes — one a day since May 2023. Things we shipped, things we broke, and numbers we went and checked.

2026 2025 2024 2023

1,244 posts. , or browse by year and tag below.

May 16, 2023

What solar_mw actually contains in grid-energy-load

8,760 rows, 3,538 distinct values, and the one fact about solar_mw that changes how you query it.

quality practice Data quality

May 15, 2023

The overall average hides 8 different numbers

Real group means for one column across 8 segments, and what the pooled average conceals.

statistics practice Analytics practice

May 14, 2023

r = 1.00 between seats_now and mrr_usd

A measured correlation of 1.00 between two columns, what its square says, and the diagnostic that costs one line.

statistics Statistics

May 13, 2023

Five minutes with dep_delay_min in flight-delays

8,000 rows, 251 distinct values, and the one fact about dep_delay_min that changes how you query it.

quality practice Data quality

May 12, 2023

The overall average hides 8 different numbers

Real group means for one column across 8 segments, and what the pooled average conceals.

statistics practice Analytics practice

May 11, 2023

r = 0.46 between pm25 and no2_ppb

A measured correlation of 0.46 between two columns, what its square says, and the diagnostic that costs one line.

statistics Statistics

May 10, 2023

What salary_min_usd actually contains in data-job-postings

3,500 rows, 436 distinct values, and the one fact about salary_min_usd that changes how you query it.

quality practice Data quality

May 9, 2023

The overall average hides 6 different numbers

Real group means for one column across 6 segments, and what the pooled average conceals.

statistics practice Analytics practice

May 8, 2023

A essentially none correlation, and what it is not

A measured correlation of -0.08 between two columns, what its square says, and the diagnostic that costs one line.

statistics Statistics

May 7, 2023

Reading country before trusting it in world-indicators

720 rows, 30 distinct values, and the one fact about country that changes how you query it.

quality practice Data quality

May 6, 2023

Reader question — Describing a column without lying

The mean is the default summary and it is frequently the wrong one. Knowing when — and what to reach for instead — is most of applied statistics in this job.

practice Statistics

May 5, 2023

A essentially none correlation, and what it is not

A measured correlation of -0.01 between two columns, what its square says, and the diagnostic that costs one line.

statistics Statistics

May 4, 2023

Reading converted before trusting it in ab-test-checkout

6,000 rows, 2 distinct values, and the one fact about converted that changes how you query it.

quality practice Data quality

May 3, 2023

unit_price_usd by category: a 1,012% spread

Real group means for one column across 6 segments, and what the pooled average conceals.

statistics practice Analytics practice

May 2, 2023

A moderate correlation, and what it is not

A measured correlation of -0.40 between two columns, what its square says, and the diagnostic that costs one line.

statistics Statistics

May 1, 2023

What first_response_min actually contains in support-tickets

4,000 rows, 622 distinct values, and the one fact about first_response_min that changes how you query it.

quality practice Data quality

Apr 25, 2023

The notebook that only ran once

Hidden state, a board number, and why "restart and run all" became a rule.

practice engineering Machine learning

Mar 14, 2023

We saved $2,100 a month by typing more

A columnar storage lesson learned from a bill, not a book.

performance warehousing Data platform

Feb 21, 2023

The join that doubled revenue for six weeks

A fan-out bug, the four controls that failed to catch it, and the one-line test we now put on every model.

quality sql Data quality

Jan 17, 2023

Why we started writing this down

Nine people, one group chat, and three years of answering the same questions. This is the first post.

practice Analytics practice