Week 2 — Quiz (auto-graded) · Sociological Research Methods

Course: Introduction to Sociology (SOC 1) · Silver Oak University (fictional sample) · Prof. Adeyemi
Objective tested: Objective 2 — the research cycle and methods; reliability/validity; sampling; correlation vs. causation; research ethics.
Points: 10 (1 each) · Assignment group: Quizzes (10% of grade) · Due: end of Module 2.

This is the human-readable quiz with its vetted answer key and feedback. The import-ready Classic QTI is in F-quiz-week-02-qti.xml. The reusable item-bank entries and the Canvas placement block are at the bottom of this file.

Blueprint

No trick questions; distractors target the Week 2 misconceptions named in the lecture outline (reliability vs. validity; bigger-is-better sampling; self-selection; IV vs. DV; correlation as causation).

Questions, key, and feedback

Q1 (MC). A researcher wants to study "social isolation," so she decides to measure it as "the number of days in the past week a person had no in-person contact with a friend or relative." Turning an abstract concept into something concrete and measurable like this is called —
- A. a hypothesis
- B. an operational definition ✅
- C. a spurious correlation
- D. random assignment
Feedback: An operational definition (operationalization) turns a fuzzy concept into something you can actually measure — ideally so two different researchers would measure it the same way. (A hypothesis is a testable prediction; a spurious correlation is a false association; random assignment is an experimental technique.)

Q2 (MC). Among the major sociological methods, which is best designed to establish a cause-and-effect relationship, because it lets the researcher control conditions and use random assignment to comparison groups?
- A. A survey of a large random sample
- B. Participant-observation field research (ethnography)
- C. An experiment ✅
- D. Secondary analysis of existing records
Feedback: The experiment is the one method built for causation: a control group plus random assignment lets the researcher rule out other explanations. (Surveys and secondary analysis usually show correlation; ethnography captures meaning, not cause.)

Q3 (MC). An online news site runs a poll: 50,000 of its own readers click in, and 80% favor a new policy. A sociologist warns the result may not reflect the country. The single biggest problem is that —
- A. the sample is far too small to mean anything
- B. the sample is self-selected and not a random, representative sample of the population ✅
- C. online polls can never measure real opinions
- D. 80% is too large a majority to be believable
Feedback: This is a self-selected sample — readers opt in and differ systematically from everyone else, so it can't be generalized, no matter how many respond. Representativeness beats size: 50,000 is plenty large; the problem is bias, not size.

Q4 (Multiple answer — select all that apply). A well-designed probability (random) sample is valued in survey research because —
- A. Every member of the population has a known, non-zero chance of being selected ✅
- B. It lets researchers generalize from the sample to the larger population within a margin of error ✅
- C. A representative sample matters more than sheer sample size for generalizing ✅
- D. Letting people volunteer themselves makes the sample more representative
- E. A large sample drawn from only one biased source is automatically representative
Feedback: A, B, and C are the point of random sampling — a known chance of selection makes the sample representative, which is what lets you generalize, and representativeness matters more than size. D describes self-selection (a bias), and E is the "bigger is automatically better" error — both false.

Q5 (MC). A bathroom scale always reads exactly 5 pounds too high. It gives the same answer every time but never the true weight. By analogy, a measure that is consistent/repeatable but does not actually capture what it claims to measure is —
- A. valid but not reliable
- B. reliable but not valid ✅
- C. both reliable and valid
- D. neither reliable nor valid
Feedback: Reliable = consistent (same answer every time); valid = accurate (measures the real thing). The 5-lb-high scale is perfectly reliable but not valid. You can be reliable without being valid — and you want both.

Q6 (Matching). Match each sociological research method to its best description.
| Method | Correct description |
|---|---|
| Survey | Asking a sample of people standardized questions through questionnaires or interviews |
| Experiment | Manipulating an independent variable under controlled conditions, often with random assignment, to test cause and effect |
| Field research / ethnography | Observing people in their natural setting, often through participant observation, to understand meaning from the inside |
| Secondary data analysis | Analyzing existing records or data originally gathered by others, as in Durkheim's study of suicide statistics |
Feedback: Each method fits a different question: surveys ask many people standardized questions; the experiment is the causal tool (control + random assignment); ethnography captures meaning from the inside; secondary analysis reuses existing data (Durkheim's Suicide, 1897, used official records).

Q7 (MC). According to the Pew Research Center Mobile Fact Sheet (data from a 2025 survey of U.S. adults), 91% of U.S. adults own a smartphone, and ownership is higher among younger and higher-income adults than among adults 65 and older. Reading this figure carefully, which statement is best supported?
- A. The data prove that owning a smartphone causes people to earn higher incomes
- B. The data describe a pattern of ownership across groups but do not, by themselves, establish why those differences exist ✅
- C. Because most adults own a smartphone, age and income have no relationship to ownership
- D. The figure proves that being older causes people to reject smartphones
Feedback: A survey statistic describes a pattern; it does not, by itself, establish a cause (A and D both leap from correlation to causation). The age/income gaps are real — so C is wrong — but the number tells us that they exist, not why.

Q8 (MC). Across U.S. cities, neighborhoods with more bookstores tend to have higher average incomes. Concluding that "opening bookstores raises a neighborhood's income" is most likely an example of —
- A. a valid causal claim established by random assignment
- B. a spurious correlation driven by a third (confounding) variable, such as the education or wealth of who already lives there ✅
- C. a reliable but invalid measurement
- D. an operational definition
Feedback: This is a spurious correlation: a third variable — the wealth/education of residents — likely drives both the bookstores and the income (wealthier areas attract bookstores). The arrow may also run in reverse. No experiment established a cause here.

Q9 (True / False). "If a survey finds that two variables are strongly correlated, that finding by itself proves that one of the variables causes the other."
- True
- False ✅
Feedback: False. A correlation has three possible stories — X→Y, Y→X (reverse direction), or a third variable driving both. To claim causation you also need correct time order and the elimination of third variables (what an experiment is built to do). "Correlation is a clue, not a verdict."

Q10 (MC). In modern social-science research, the requirement that participants be told the study's risks and purpose and agree to take part, that their identities be protected, and that the project be reviewed by an Institutional Review Board (IRB), are all core principles of —
- A. operationalization
- B. research ethics (e.g., informed consent and confidentiality) ✅
- C. random sampling
- D. the correlation coefficient
Feedback: These are core research ethics: informed consent, confidentiality, avoiding harm, and IRB review before the study. (Operationalization is about measurement; random sampling is about who's selected; the correlation coefficient is a statistic.)

Answer key (quick reference)

Quality gate (self-checked): each single-answer item has exactly one correct option; the multiple-answer item (Q4) keys the three true features (A, B, C) and requires D and E to be left unselected; the matching item (Q6) pairs four prompts to four distinct descriptions. The one published figure (Q7) — Pew's 91% U.S. adult smartphone ownership, 2025 — was verified live at the Pew Research Center Mobile Fact Sheet (pewresearch.org) before shipping, and the keyed answer explicitly treats it as a descriptive pattern, not a cause (no correlation is dressed up as causation). Durkheim's Suicide (1897) is named factually as secondary-data analysis. The correlation-vs-causation items (Q8 spurious correlation; Q9 keyed False) and the reliability-vs-validity item (Q5) target the named Week-2 misconceptions. No computation in this quiz, so no arithmetic to mis-key.

Item-bank entries (for variants + the midterm/final)

All ten items are tagged course=SOC1 · week=2 · objective=2 · topic=research-methods-and-data-literacy and deposited in Item Bank: Week 2 — Sociological Research Methods. The midterm (Week 8) and the per-term variant updates draw fresh items from this bank. (Tags: q1 operationalization, q2 experiment-causation, q3 self-selection, q4 probability-sampling, q5 reliability-vs-validity, q6 methods-match, q7 read-the-data-pew, q8 spurious-correlation, q9 correlation-causation, q10 research-ethics.)

Canvas placement block

canvas_object   = Quizzes::Quiz
title           = "Week 2 Quiz — Sociological Research Methods"
assignment_group = "Quizzes"
points_possible = 10
grading_type    = points
due_offset_days = 6        # 6 days after module start
published       = true
shuffle_answers = true
provenance      = "~ Prof. Adeyemi's edition · Fall 2026 · built with thecoursemaker.com"