Step 1.4 - What terms or jargon will you define?
Write a list of technical terms, jargon, and acronyms that will be used in the course.
From a course on experimental design. This has an extensive list of statistical terms.
- Randomization, replication, blocking, Latin Square, Greco-Latin Squares, factorial, ANOVA, T-test, F-test, normality, qqplot, variance, type I/II error, null/alternative hypothesis, effect size, factor/categorical variable
From a course on clinical trials analysis. This includes both statistical terms and domain-specific terms.
- Bias, blinding, randomization, imbalance, covariates, endpoints, power, multiplicity, significance, non-inferiority, equivalence, bioequivalence.
From a course on data privacy. This in an extensive list of both statistical terms and privacy-related terms.
- Statistical Disclosure Limitation, Data Synthesis, K-Anonymity, Neighboring Databases, Randomized Response, Differential Privacy, Composition Rules, Group Privacy, Post-processing, Global Sensitivity, Histogram queries, Laplace Mechanism, Exponential Mechanism, Differential Privacy Data Synthesis
What can I assume that the students will know already?
This depends a lot upon the prerequisites for the course. For example, the introductory statistical courses have to explain what a statistical model is. For most statistical courses, you don't need to do that since they will have one of those courses are as prerequisite.
Think of synonyms
Often there are several different words for a particular concept. For example, columns in a rectangular dataset may also be referred to as fields or features or variables, depending upon context. Many students may have head one term but not the others, so it can be useful to explain synonyms to them. (Though note that once you've explained the synonyms, you should be consistent about which term you are using.)
Common problems and their solutions
I can't think of anything
Split the problem up into different areas. Are there any terms related to the code? Are there any terms related to the statistical modeling techniques? Are there any terms from the application domain? Are there any terms that might be needed to explain the dataset?
How will this be reviewed?
Your Curriculum Lead will discuss your responses to the brainstorming questions. They will not be formally reviewed (though they provide important context for reviewers).