Textbook: Interactive Statistics, 3rd ed. (Sullivan & Woodbury), Sections 1.1–1.5
Chapter Summary
Statistics is the science of collecting, organizing, summarizing, and analyzing information so we can draw conclusions and answer questions. Before any of the calculations in later chapters can mean anything, someone has to gather good data — and this chapter is about doing that well.
The big idea is that a study’s conclusions are only as trustworthy as its data. You’ll learn to tell the difference between a population (everyone or everything being studied) and a sample (the part you actually measure), and between a parameter (a number describing the population) and a statistic (a number describing the sample). We take statistics from samples to make inferences about parameters — that one sentence explains most of the second half of this course.
You’ll also sort data into types: qualitative (categories, like majors or blood types) versus quantitative (numbers, like test scores), and the four levels of measurement — nominal, ordinal, interval, and ratio — which decide what math you’re allowed to do. Finally, you’ll see how researchers pick samples: simple random, stratified, systematic, and cluster sampling are the sound methods, while convenience and voluntary-response samples are the ones that produce misleading headlines. If a news story claims something outrageous about “most people,” this chapter teaches you to ask: who was actually asked, and how were they chosen?
Study Guide
Key terms and definitions
- Statistics — the science of collecting, organizing, summarizing, and analyzing information to draw conclusions or answer questions. It also means the plural of a statistic: numerical summaries computed from data.
- Population — the entire group of individuals being studied. Sample — a subset of the population actually measured.
- Individual — a person or object that is a member of the population being studied.
- Parameter — a numerical summary of a population (e.g., the population mean, μ). Statistic — a numerical summary of a sample (e.g., the sample mean, x̄).
- Descriptive statistics — organizing and summarizing data (graphs, averages). Inferential statistics — extending results from a sample to the population (the focus of Chapters 9–13).
- Qualitative data — categorical (e.g., eye color, zip code). Quantitative data — numerical (e.g., height, age).
- Discrete data — quantitative data with countable values (number of students). Continuous data — quantitative data with infinitely many possible values (weight).
- Levels of measurement: nominal (names only, e.g., gender), ordinal (ordered categories, e.g., letter grades), interval (ordered with meaningful differences but no true zero, e.g., temperature in °F), ratio (ordered with a true zero, e.g., height).
- Simple random sample — every group of the same size has an equal chance of selection.
- Stratified sample — population divided into groups (strata), then a random sample taken from each.
- Systematic sample — select every k-th individual after a random start.
- Cluster sample — divide into groups (clusters), randomly select some clusters, and measure all members of those clusters.
- Convenience sample — easy-to-reach individuals (often biased). Voluntary response sample — individuals choose themselves (usually biased).
Essential formulas
- Relative frequency = (frequency of a class) ÷ (total number of observations). Useful for comparing groups of different sizes.
Step-by-step procedures
- Classify a variable’s level of measurement: (1) Is it just names? → nominal. (2) Can values be ordered but differences meaningless? → ordinal. (3) Are differences meaningful but zero arbitrary? → interval. (4) Is there a true zero, making ratios meaningful? → ratio.
- Identify a sampling method: look for the mechanism. Random numbers → simple random. Divided into natural groups first, sampled within each → stratified. Every kth → systematic. Whole groups chosen, everyone inside measured → cluster. Whoever was handy → convenience.
- Spot bias: ask who is missing from the sample and whether the method gives everyone a fair chance.
Common mistakes to avoid
- Calling a statistic a parameter (or vice versa). Rule of thumb: computed from the sample → statistic; describes the population → parameter.
- Saying interval data “has no zero” — it has no true zero (0°F doesn’t mean no heat).
- Mixing up stratified and cluster sampling: stratified samples within every group; cluster samples all members of a few groups.
- Thinking a bigger convenience sample fixes bias — it doesn’t; it just gives a more precise wrong answer.
Self-check: I can…
- [ ] Explain why a parameter and a statistic are different, with an example.
- [ ] Classify data as qualitative or quantitative (and discrete or continuous).
- [ ] Assign the correct level of measurement to a variable.
- [ ] Identify the sampling method used in a described study.
- [ ] Explain why voluntary-response and convenience samples are unreliable.
StatCrunch How-To
- Open StatCrunch: in MyLab Statistics, look for the StatCrunch link (usually under Tools). It opens in your browser with a blank spreadsheet.
- Enter data: click a column header to name it (e.g., “Scores”), then type or paste values down the column.
- Save your work: File > Save so you can reopen the data set later.
- Chapter 1 is mostly vocabulary and reasoning, so StatCrunch practice starts in Chapter 2 — but get comfortable opening it and entering a column of data now.
StatCrunch Video Tutorials
Select a video from the dropdown menu to watch it right here on this page.