Data Dictionary: frequentist_workflow_education.csv

Teaching dataset for the frequentist workflow page.

Use this dataset for validation, reliability, factor analysis, descriptive results, group comparisons, ANOVA, correlation, linear regression, logistic regression, and reporting practice.

Research Scenario

A district evaluates a reading support programme. The dataset follows learners across schools and records baseline reading, endline reading, attendance, socioeconomic status, engagement questionnaire items, and whether each learner reached the endline reading benchmark.

Variables

Variable Type Description
learner_id string Unique learner identifier.
school_id string School identifier.
school_context categorical School context: urban, peri_urban, or rural.
intervention binary 1 if the learner received the reading programme, 0 otherwise.
gender categorical Learner gender in the simulated data.
ses_index numeric Standardised socioeconomic-status index. Higher values indicate higher SES.
baseline_reading numeric Baseline reading score from 0 to 100.
attendance_rate numeric Attendance percentage during the study period.
engage_attention ordinal integer Engagement item from 1 to 5. Higher values indicate stronger attention.
engage_participation ordinal integer Engagement item from 1 to 5. Higher values indicate stronger participation.
engage_homework ordinal integer Engagement item from 1 to 5. Higher values indicate stronger homework effort.
engage_persistence ordinal integer Engagement item from 1 to 5. Higher values indicate stronger persistence.
endline_reading numeric Endline reading score from 0 to 100.
met_benchmark binary 1 if the learner reached the reading benchmark, 0 otherwise.

Main Questions

  • Are the data coded correctly and ready for analysis?
  • Do the engagement items form a coherent scale?
  • Do intervention and comparison learners differ in endline reading scores?
  • Do endline reading scores differ by school context?
  • Is learner engagement associated with endline reading?
  • Is the intervention associated with endline reading after adjusting for baseline reading and SES?
  • Which factors are associated with reaching the reading benchmark?