Notes

Course-voice weekly lesson pages for the 15-week Intro to Statistics spine. Each weekly page is the main reading for that week — a short textbook-depth read that teaches the concepts end-to-end, with outbound links to OpenIntro IMS and ISLBS for an alternate voice.

The weekly cadence is Monday concept / Wednesday application / Friday accountability. Monday and Wednesday public-safe exit tickets are linked from each weekly page. Friday quizzes and the biweekly homework are handled through Blackboard or in class as directed.

Available

  • Week 1 — Data, evidence, and statistics — what counts as data, cases and variables, variable types (numerical vs categorical, continuous vs discrete, nominal vs ordinal), response vs explanatory variables, and reading a small dataset honestly.
  • Week 2 — Study design, bias, and causality — populations and samples, parameters vs statistics, sampling and representativeness, observational studies vs experiments, random assignment, bias, confounding, and what each design can support.
  • Week 3 — One-variable summaries — describing a single variable: frequency tables and bar plots for categorical data; histograms, boxplots, and the center–spread–shape vocabulary for numerical data; choosing the right summary.
  • Week 4 — Comparing groups — comparing two or more groups: contingency tables and conditional proportions; differences in proportions and differences in means; choosing displays that answer the comparison question.
  • Week 5 — Association — scatterplots and the direction / form / strength / unusual points reading; correlation as a single descriptive number for the linear part of the relationship; why a near-zero correlation can still hide a strong relationship; association vs causation in headlines.
  • Week 6 — Confounding and multivariable thinking — the associated with both definition of a confounder; comparing within strata as a fairer descriptive move; Simpson’s paradox; the plain-English alone / after accounting for language as the honest-reporting habit.
  • Week 7 — First-half synthesis and midterm — the Units 1–6 walkthrough as one connecting case (cases and variables → design and scope → describe → compare → associate → ask what else explains it); a midterm-prep checklist and a single bounded forward-pointer to next week’s regression line.
  • Week 8 — Simple regression — fitting a line to a scatterplot and reading it honestly: slope and intercept in real units, residuals and the residual-plot reading, least squares as the rule for choosing one line, R² as descriptive strength of fit, the extrapolation caveat, and a light look at outliers and leverage.
  • Week 9 — Multiple and logistic regression, by interpretation — adding predictors to a model; the holding the other variables constant coefficient reading; adjusted vs unadjusted coefficients as the formal engine for the Week 6 confounding lesson; categorical predictors and reference levels; adjusted R² as a reading; and an interpretation-only look at logistic regression (reading a yes/no model by direction and predicted probability).
  • Week 10 — Probability as risk and diagnosis — probability as long-run risk; conditional probability as among the subgroup; why P(A | B) is not P(B | A); diagnostic two-way tables; sensitivity and specificity, false positives and false negatives, positive and negative predictive value; and why a positive test for a rare condition can still be probably wrong (the base-rate effect).
  • Week 11 — Simulation-based inference — could this be due to chance, and what values are plausible? The logic of a randomization test (chance model, observed statistic, null distribution, and the simulated p-value as evidence); bootstrapping and the percentile confidence interval as a range of plausible values; reading StatKey-style output; and reading p-values and intervals honestly.
  • Week 12 — Classical hypothesis testing — the classical formula as a shortcut to the Week 11 simulation: null and alternative hypotheses, the test statistic as (estimate − null) / SE, the p-value from a normal/t model, the confidence interval as estimate ± margin of error, reading one-proportion z and one- and two-mean t output, and Type I / Type II errors with significance level and power.

Planned

Notes are added a few weeks at a time as the course is built. The sequence follows the 15-week course spine.

Probability and inference (Week 13)

  • Week 13 — Categorical outcomes

Evidence synthesis and close-out (Weeks 14–15)

  • Week 14 — Meta-analysis and forest plots
  • Week 15 — Final review