Data collection is the systematic process of obtaining observations, measurements, or records for a defined purpose. Start with a specific question rather than gathering whatever happens to be available. A focused objective makes sufficient data easier to collect and reduces spurious findings. section 2.2 section 10.24
Before trusting collected data, check:
- Whether the observations capture important context rather than only convenient or staged moments. section 2.2
- Whether bias, incentives, inaccurate records, or selective capture could distort the conclusion. section 2.2
- Whether the measurement addresses the solution you actually need, such as testing a printer problem or evaluating product quality. section 10.24
From family photos to a golf question
A pile of family photographs cannot reliably reveal someone’s whole life: it shows curated moments and misses what was never photographed. A narrower question—whether the father is good at golf—supports more relevant observations, such as his swing, his behavior at the 18th hole, and his scorecard. Even then, context matters: a fist-pump may celebrate someone else, and a scorecard may not be genuine. section 2.2
