Module 2 Worksheet: Variables, Measurement, Samples, and Bias
Scenario
The dataset arrived without a data dictionary. Two people on the team already disagree about what one of the columns means.
Data
Dataset: student-study-sample.csv
| respondent_id | cohort | weekly_study_hours | preferred_resource | completed_survey | exam_score | missing_score_reason |
|---|---|---|---|---|---|---|
| S01 | A | 3 | video | yes | 62 | |
| S02 | A | 5 | practice | yes | 71 | |
| S03 | A | 2 | notes | yes | 58 | |
| S04 | A | 7 | practice | yes | 78 | |
| S05 | A | 4 | video | yes | 67 | |
| S06 | B | 6 | practice | yes | 74 |
Your Task
Mark the unit, variable types, sample, intended population, and missingness risks in the student study sample.
Questions
- What is one row, and could the same real-world thing appear twice?
- For each column, what type is it and what does that allow?
- Which column is ambiguous, and what are the two readings?
- How would each reading change the answer?
- Who is absent from this data, and would they differ?
- What summary is safe given the ambiguity?
- What one question would you send to whoever produced the file?
Write Your Conclusion
State your reading of the ambiguous column, then the conclusion that follows from it. Say what would change under the other reading.
Self-Check
- Did I state the unit of analysis explicitly?
- Did I name the ambiguity rather than picking silently?
- Did I say who is missing from the data?
- Is my conclusion conditional on the reading I chose?