Make defensible data decisions by defining populations, measuring uncertainty and planning experiments before reading results.
Learning path
- Population, estimand and sampling frame: name the quantity before calculating
- Distribution summaries: report tails and define the outlier policy
- Standard error and cluster bootstrap: resample the independent unit
- Confidence intervals: interpret coverage and precision honestly
- Hypothesis tests: pair the decision rule with an effect size
- Experiment design: assign the right unit and guard against interference
- Multiple comparisons and peeking: protect a predeclared decision rule
- Project: evaluate a receipt-review workflow without changing the question midstream
Connected foundations
Use the earlier data and model boundaries as prerequisites.
Practice
Continue into another subject: Causal Inference Tutorial.
Continue into another subject: Online Experimentation Tutorial.
Continue into another subject: Data Annotation & Label Quality Tutorial.