Unit 12 of 12
Complete Statistical Investigations
- 2 lessons
- Videos 77 to 78
A statistical result means little without its question, design and limits. This unit chooses methods, reports results with their uncertainty and carries out a complete investigation.
A report starts from the estimand, the quantity the study aims to learn about, and from an analysis plan written before the results are known. It gives effects in their units with uncertainty intervals, puts each p-value in context, discloses every comparison that was made and explains missing data, sensitivity analyses and how to reproduce the work. The final lesson follows one question from design and measurement through exploration, method choice and model checking to the conclusion the analysis actually supports.
Every lesson will be one video. The videos are coming soon, and each lesson page already has the definitions and an example for every key term.
From Question to Report
Selecting Methods and Reporting Statistical Results
How to build a statistical report from its estimand, an analysis plan and preregistration, keep planned and exploratory analyses apart, avoid selective reporting, and support it with sensitivity analysis and reproducibility.
Video 77
A Complete Statistical Investigation
How a statistical investigation moves from a research question and study design through primary and secondary outcomes, exploratory data analysis, method selection and model checking to a reproducible report.
Video 78