Reproducibility and provenance
Someone should be able to understand where your data came from and run your analysis again from the beginning.
The analysis lifecycle is iterative: frame, acquire, understand and clean, explore, model if needed, evaluate, communicate, and monitor. A discovery can send you back to an earlier stage.
A data dictionary records names, meaning, type, units, allowed values and missingness rules. Provenance records source, collection context, dates, permissions where relevant, and transformations. A reproducible notebook combines purpose, code, output and interpretation. Restart and run all; hidden state and execution order can otherwise make a correct-looking notebook impossible to reproduce.
Sources: W1 PDF pp. 3, 13-17, 22-30, 32-53, 57-60; L1 Parts 1-5.
The lecture's claim ladder becomes a written answer: report the comparison, explain its limits and identify a useful next check.
The lecture's audit trail becomes a final report. Structural checks verify stated rules, while source accuracy and broader claims still need separate evidence.
Practice problems
Supplementary study questions on the lecture concepts — not verbatim exam questions. Each answer counts toward spaced review.
1. Conceptual understanding
Definitions and distinctions.
What makes a notebook reproducible?
What belongs in a data dictionary?
2. Application
Apply the concept to a case or calculation.
Why avoid overwriting the only raw export?
Why restart and run all notebook cells?
3. Interpretation and limitations
Evaluate assumptions and justify conclusions.
Which rule belongs in the data dictionary?
Two runs use the same seed but a changed sequence of random draws. Must all outputs match?
Explain it in writing
Self-checked, not marked. Write a few sentences, then compare with the example answer. Your writing is saved as you type.
Show an example answer
It lets you compare changes, correct mistakes and explain how the final data were produced. It also preserves the original evidence for unresolved values.
Check: did you answer the question, use evidence or working, and avoid claiming more than the evidence supports?
Show an example answer
With the same algorithm and sequence of draws, it helps reproduce the random example. It does not guarantee accuracy, representative sampling or good model performance.
Check: did you answer the question, use evidence or working, and avoid claiming more than the evidence supports?