Syllabus (public companion)

Orientation and course shape — Blackboard is authoritative for graded specifics

Important

This public page is an orientation companion to the syllabus, not the operational syllabus itself. It describes the shape of the course in qualitative terms. It carries no numeric grade weights, no schedules, and no submission rules. For everything that counts toward your grade — exact weights, deadlines, policies, and submissions — Blackboard (the LMS) is authoritative. If this page and Blackboard ever disagree, follow Blackboard.

Course description

This course is about using statistical methods to answer practical questions with real data — choosing, running, interpreting, and communicating the common applied analyses responsibly. It sits between an introductory statistics course and more specialized courses in modeling, design, inference, Bayesian statistics, or resampling. We begin with statistical questions, data structure, and applied workflow — exploratory analysis, graphical comparison, estimation, uncertainty, and practical significance — and then work method by method: one-sample and paired comparisons, two-group comparisons, many-group comparisons and one-way ANOVA, assumptions and diagnostics, multiple comparisons and planned contrasts, two-way ANOVA and interaction, simple and multiple regression, ANCOVA and adjustment, categorical outcomes and contingency tables, and logistic regression for binary outcomes.

The thread that holds all of this together is one analysis blueprint, returned to on every page. For each method we walk the same six steps: (1) Question — are we comparing, explaining, or predicting? (2) Structure — the unit of analysis; the response versus the explanatory, grouping, or covariate variables; the outcome type (quantitative, categorical, binary); and the design (paired versus independent, one factor versus two, observational versus experimental). (3) Method — the analysis that matches that structure, and why this one and not a neighbor. (4) Assumptions and diagnostics — what the method assumes and how you check it. (5) Estimate and uncertainty — what the model estimates (a mean difference, an effect size, a slope, an odds ratio), reported with a confidence interval, not as a bare p-value. (6) Conclusion — statistical versus practical significance, association versus causation, and what the analysis can and cannot support.

This course is deliberately not four things, and it resists all four drifts:

It is not a generic intro-statistics course. Descriptive summaries, the normal model, a single one-sample t-test, and the mechanics of one confidence interval are assumed background. The subject is connecting a method to a data structure across groups, factors, covariates, and categorical outcomes — and reading what the model estimates.
It is not a pure R or software course. R and Quarto carry out the fit and produce the output; what stays central is the method’s logic — what is compared, what is assumed, what is estimated, and what can be concluded.
It is not a formula-only methods course. The goal is never to memorize a test statistic; it is to map question → structure → method → estimate → conclusion and to read and check real output.
It is not a disconnected catalog of named tests. The paired t, the two-sample t, one-way and two-way ANOVA, ANCOVA, regression, chi-square, and logistic regression are connected expressions of one blueprint, not a box of “use this when…”.

Two disciplines run inside the blueprint and recur on every page: report the estimate with its uncertainty, not just a verdict — an effect size and interval, never a lone p-value — and keep statistical significance, practical significance, and a causal claim distinct. Because most of the example data here are observational, they buy association, not causation.

Who it is for

This course assumes a prior introductory statistics course or comparable preparation. You should be comfortable with variables, data tables, graphical and numerical summaries, means, medians, and standard deviations, proportions, confidence intervals, hypothesis tests, p-values, correlation, and basic regression ideas. Prior R is helpful but not required — software examples are scaffolded, and the course reviews the workflow it needs. The course is less mathematical than a formal inference course, but it is not formula-free: expect light algebra and notation-reading. The main expectation is a willingness to reason about which method a data structure calls for, write short interpretations in plain sentences, read real output, and separate a statistical result from a practical or causal claim.

Learning outcomes

By the end of the course, a successful student will be able to:

Start from a statistical question and a data structure — the unit of analysis, the response versus explanatory or grouping or covariate variables, the outcome type, and the design — and choose an analysis that matches, rather than reaching for a named test by habit.
Carry out and read one-sample and paired comparisons and two-group comparisons, distinguishing a paired design from independent samples and preferring Welch’s t when equal variances are not justified.
Fit and interpret one-way ANOVA for many-group comparisons, report an effect size such as \(\eta^2\), and use multiple-comparison control (Tukey, Bonferroni) and planned contrasts to ask sharper questions while controlling the family-wise error rate.
Check assumptions and run diagnostics — residual normality, equal variance, independence, outliers and influence — and respond to a diagnostic finding without auto-deleting unusual observations.
Read a two-way ANOVA, recognize an interaction, and report main effects as conditional when an interaction is present.
Fit and interpret simple and multiple regression and ANCOVA, explain how an estimate changes after adjustment (a partial slope, an adjusted mean), and use that to reason about confounding.
Analyze categorical outcomes with contingency tables and the chi-square test, and report a risk difference, relative risk, or odds ratio as the effect, not a bare p-value.
Fit and interpret logistic regression for a binary outcome — read coefficients on the log-odds scale, exponentiate to an odds ratio, and report a predicted probability as the conclusion.
Throughout, report an estimate with its confidence interval rather than a lone p-value, and keep statistical significance, practical significance, and causation distinct, stating honestly what an observational analysis can and cannot support.

Weekly rhythm

This is a lecture/activity course meeting three days a week (MWF), and each day has a settled role:

Monday — method concept + checkpoint. We introduce the week’s method by walking the analysis blueprint: what question it answers, what data structure calls for it, and what it estimates. A short applied-methods checkpoint near the end of class confirms you can read the structure.
Wednesday — analysis and diagnostics day. We carry out the fit, read the real output, and check the assumptions — residuals, equal variance, independence, influence — turning the method into an estimate with its uncertainty.
Friday — quiz / interpretation day. A short quiz on recent material, then we practice the conclusion step: separating statistical from practical significance, association from causation, and writing the result in plain sentences.

This rhythm is the plan; the authoritative weekly schedule, including any shifts, lives in Blackboard. A few calendar facts are fixed: classes begin Mon Aug 24; Labor Day (Mon Sep 7) has no class, so week 3 runs compressed on Wednesday and Friday; the midterm is in class on Fri Oct 9 (covering weeks 1–7 — applied workflow, exploratory analysis, estimation and uncertainty, practical significance, one-sample and paired comparisons, two-group comparisons, many-group comparisons and one-way ANOVA, assumptions, and diagnostics); the last day to drop is Oct 20; fall break is Nov 22–28; the last class is Mon Dec 7; consultation day is Dec 8; and the final-exam window is Dec 9–15, with the exact block posted via Blackboard. Attendance is not graded directly, but checkpoints, quizzes, labs, and in-class activities happen during class, so consistent attendance matters — the course builds judgment by repeated passes through question → structure → method → estimate → conclusion.

Assessment shape (indicative — not a contract)

The table below conveys the relative emphasis of each graded category in qualitative terms only. It is not a grading contract: it carries no percentages and no point values, and the actual weights live in Blackboard.

Category	Rough emphasis
Applied-methods checkpoints	small
Weekly quizzes	small
Homework and analysis memos	the largest single category
Applied analysis labs	moderate
Midterm	moderate
Applied methods project	moderate
Final exam	small

Read this as a picture of where the weight sits: regular homework and analysis memos are the backbone of the grade, the labs and the two big instruments (midterm, project) carry moderate weight, and the smaller pieces — checkpoints, weekly quizzes, and the final — add up around them. The homework and memos are where you practice the discipline that defines the course: report an estimate with its interval, and say plainly what the analysis does and does not support. For the exact weighting, consult Blackboard.

Software and reproducibility

We use R (through RStudio or Posit Cloud) and Quarto, along with spreadsheets and browser-based tools, to fit models, read output, check assumptions, and build tables and figures. Computation supports the reasoning rather than replacing it: you read, edit, and run code; interpret the output; and write short written conclusions. When software is used, you are expected to explain what the code is doing, what is being compared or estimated, what assumptions remain, and how the output supports the conclusion — the code carries out the fit, but the method logic is the message.

All example data on this site are synthetic, with the seed set (set.seed(35203)) so results are reproducible — they are not real student records. Because this is a draft course site, the R code on the public pages is shown as static, non-executed examples (R is not run in this build), and every numeric value here is drafted and provisional until it is independently checked. Setup instructions for running R yourself live on the resource pages.

AI use (summary)

Generative AI tools may be used as a study and workflow aid — to explain a concept a second way, generate practice questions, help debug R code, suggest a way to visualize a result, or check your understanding of a method. They may not produce work you submit as your own, complete homework or analysis-memo solutions, write project interpretations, fabricate output, invent conclusions, or replace your responsibility to understand and verify the reasoning, and they are prohibited on quizzes and exams unless explicitly allowed.

Because the heart of this course is matching a method to a data structure and reporting an estimate honestly, AI output must be checked carefully against the design. AI assistants frequently mismatch the method to the design (running a one-way ANOVA where the structure calls for a paired or two-way analysis), confuse paired and independent samples, ignore unequal variance (defaulting to a pooled t when Welch is safer), treat every p-value as a decision rule instead of reporting an estimate with its interval, misread an interaction (reporting a main effect as if it applied uniformly), or make a causal claim from observational data. Whenever you use AI on a graded homework, analysis memo, lab, code submission, or project component, include a brief AI Use Note with three labeled lines:

Field	What to record
Tool	which assistant you used (with approximate date or version)
Purpose	what you used it for
Verification	how you checked, tested, revised, or validated the output

Verification is the load-bearing line: rerun the code, confirm the design (paired versus independent, one factor versus two), check the assumptions against the notes, recompute a key estimate and its confidence interval by hand or in R, confirm that an effect is reported as an estimate-with-uncertainty rather than a bare p-value, re-read whether an interaction makes a main effect conditional, and make sure no causal language has slipped into an observational conclusion. Rewrite any AI explanation in your own words after checking it. The full policy lives in Blackboard.

Materials

You will need:

Instructor notes, examples, and applied-methods guides — the primary course materials, posted on this site and in Blackboard. These connect the supplements to the course’s weekly arc, coding examples, interpretation guides, and project expectations; the analysis blueprint and the recurring datasets originate here.
Introduction to Modern Statistics, 2nd ed. (Çetinkaya-Rundel & Hardin) — the main free open-text anchor, CC BY-SA 3.0, at openintro-ims.netlify.app, used for exploratory analysis, inference for means and proportions, comparing many means (ANOVA), two-way tables, regression, and logistic regression.
Statistical Inference via Data Science: A ModernDive into R and the Tidyverse, 2nd ed. (Ismay, Kim & Valdivia) — a free computational supplement, CC BY-NC-SA 4.0, at moderndive.com/v2, used for the R workflow, visualization, inference-for-regression, and reproducible reporting.
Introductory Statistics for the Life and Biomedical Sciences (Vu & Harrington) — a free OpenIntro-family supplement (license to be confirmed), used selectively for applied, health-flavored examples and R-supported labs.
Learning Statistics with R (Navarro) — an optional reference, named and cited only, for selected topics (t-tests, chi-square, ANOVA, regression).
R, RStudio or Posit Cloud, and Quarto (plus spreadsheets or browser tools) — for the labs and analyses.
Blackboard (the LMS) — for all graded work, dates, and announcements.
A non-graphing scientific calculator for in-class quizzes; most computation is done in R.

These notes are the course’s own synthesis, grounded in but not copied from the sources. Not used in this course: Cengage, WebAssign, MyLab, or any paid homework platform.

Where things live

Keep the two homes of the course straight:

Blackboard (the LMS) is the operational home: graded applied-methods checkpoints, weekly quizzes, homework and analysis memos, applied analysis labs, the midterm, the applied methods project, the final exam, all due dates, all submissions, and all grades. It is authoritative.
This public site is the public notes home: the weekly notes, the labs as study material, the resources (the method chooser, the methods glossary, the assumptions-and-diagnostics guide, and the reporting-and-interpretation guide), and orientation pages like this one. It is ungraded.

Note

This companion exists to orient you. Whenever a graded specific is at stake — a weight, a deadline, a policy — go to Blackboard, which is authoritative.

Public vs. graded

These notes, the examples, and the practice here are public and ungraded — study material only. No graded prompts, answer keys, rubrics, point values, or due dates appear on this site. Graded applied-methods checkpoints, weekly quizzes, homework and analysis memos, applied analysis labs, the midterm, the applied methods project, and the final exam live in Blackboard (the LMS), which is authoritative for due dates, submissions, and grades. If this page and Blackboard ever disagree, follow Blackboard.