SOAN*2120 Capstone Test

What is Solomon's Four-Group Design?

An experimental design where subjects are randomly assigned to two control groups and two experimental groups. Only one experimental group and one control group receive a pretest. All four groups receive a post-test.

Why was Solomon's Four-Group Design created?

To address the issue of pretest effects, which might influence the treatment or the dependent variable, thereby affecting the experiment's outcomes.

What is a One-Shot Case Study?

An experimental design with only one group, a treatment, and a post-test. No pretest or comparison group is included.

What is a Classical Experimental Design?

An experimental design with random assignment, a control group, an experimental group, pretests, and post-tests. It serves as the foundation for other experimental designs.

What does "R," "O," and "X" represent in standard experimental design notation?

- R: Random Assignment

- O: Dependent variable observation

- X: Experimental variable or treatment

What is a Posttest-Only Design?

A design where one group undergoes treatment, and the dependent variable is measured afterward. It lacks a control group and random assignment.

List the seven threats to internal validity.

1. History

2. Maturation

3. Testing

4. Instrumentation

5. Selection

6. Experimental mortality

7. Pre-testing

Why is random assignment important?

It creates comparable groups by assigning subjects randomly, ensuring unbiased and equivalent conditions for the experiment.

What is the difference between random sampling and random assignment?

- Random Sampling: Selecting a smaller subset from a larger population.

- Random Assignment: Dividing subjects into groups using a random process for equivalence in an experiment.

When should you use correlation in analysis?

When both variables are quantitative, e.g., the relationship between income and education.

When should you use a crosstabulation (crosstab)?

When analyzing relationships between two categorical variables.

When is ANOVA used?

When comparing a categorical variable with more than two categories to a quantitative variable (e.g., marital status vs. income).

What is participant observation in field research?

A method involving observing people in natural settings over time, focusing on understanding behavior without relying on structured data or statistics.

What are the steps to conducting a field study?

1. Begin with a general topic.

2. Build rapport and negotiate your role.

3. Observe and document data.

4. Conduct follow-up interviews.

5. Summarize and share findings.

What is ethnomethodology?

A method analyzing social interaction as a process of reality construction, focusing on the commonsense knowledge people use in everyday life.

What is the central limit theorem?

A mathematical principle stating that as the number of random samples increases, the distribution of sample means approaches a normal distribution, with the center equal to the population parameter.

What is the main focus of quantitative sampling?

Obtaining a representative sample using probability sampling techniques to generalize findings to a population.

What is the main focus of qualitative sampling?

Finding cases that clarify and deepen understanding of social life, using nonprobability sampling techniques.

Name four non-probability sampling techniques common in qualitative research.

1. Haphazard Sampling

2. Quota Sampling

3. Purposive Sampling

4. Snowball Sampling

What is systematic sampling?

A type of random sampling where every xth element in the sampling frame is selected using a sampling interval.

Define sampling interval.

The inverse of the sampling ratio, used in systematic sampling to determine how many elements to skip before selecting one.

What is probability sampling?

A sampling strategy where every subject in the population has the same likelihood of being selected, ensuring representativeness.

What are the key types of probability samples? (Quantitative)

1. Simple Random Sampling

2. Systematic Sampling

3. Stratified Sampling

4. Cluster Sampling

What is stratified sampling?

A random sampling method where cases are divided into mutually exclusive categories, and random sampling occurs within each category.

What is purposive sampling, and when is it used?

A nonrandom sampling method where researchers use judgment to select cases that meet specific criteria, often for exploratory or field research.

Explain snowball sampling.

A nonrandom sampling technique where initial cases provide referrals to other cases, often used for studying networks or hidden populations.

What is a sampling frame?

A list of cases in the population or the best approximation of it, used to operationalize the population for sampling.

What is a confidence interval?

A range of values within which the population parameter is estimated to lie, with a specified degree of confidence.

What is theoretical sampling?

An interactive sampling technique tied to grounded theory, where sampling continues until theoretical saturation is reached.

What is the difference between haphazard sampling and quota sampling?

one Selects cases by convenience, leading to potential misrepresentation.

the other selects a preset number of cases from predetermined categories to ensure diversity.

What is survey research?

A quantitative social research technique in which one systematically asks many people the same questions, then records and analyzes their answers.

What are the principles of good question writing?

1. Keep questions clear, simple, and consider the respondent's perspective.

2. Ensure smooth flow between questions.

What should be avoided in survey questions?

- Jargon, slang, and abbreviations.

- Ambiguity, confusion, and vagueness.

- Emotional language.

- Prestige bias, double-barrelled questions, leading questions, false premises.

- Questions beyond respondents' capabilities or about distant intentions.

-Double negatives and overlapping/unbalanced response categories.

What is prestige bias?

A problem in question writing when a highly respected group or individual is linked to an answer, influencing respondents' choices.

Define double-barrelled and leading questions.

- Double-barrelled: Combines two ideas into one question, making answers unclear.

- Leading: A question that influences respondents to choose a specific response through its wording.

How can threatening questions be handled?

Use techniques like a warm-up, rewording, or softening the question to reduce the threat to self-image.

What is socially desirable bias?

Respondents provide socially acceptable answers instead of truthful ones. It can be reduced by careful phrasing and delivery mode selection.

What is a contingency question?

A multi-part question where the answer to one part determines the next question asked. Also known as a screen or skip question.

Compare open-ended vs. closed-ended questions.

- Open-ended: Unlimited answers, richer detail, harder to code.

- Closed-ended: Easier to compare, reduces fatigue, risks oversimplification.

What are partially open questions?

A question with fixed answer choices plus an "other" category for unique responses.

What is a floater in survey research?

A respondent who lacks an opinion but provides an answer anyway, often inconsistently.

What is response set bias?

When respondents agree or disagree with all questions in a series without considering each one carefully.

What are the advantages and disadvantages of mail/self-administered questionnaires?

- Advantages: Cheap, wide geographical coverage, no interviewer bias.

- Disadvantages: Low response rates, no clarification possible, limited question types.

Why are online surveys popular, and what are the concerns?

- Advantages: Fast, inexpensive, flexible design.

- Concerns: Coverage (internet access), privacy/verification, and design compatibility.

Compare telephone interviews to face-to-face interviews.

- Telephone: 90% response rate, less expensive than face-to-face.

- Face-to-face: Highest response rate, allows nonverbal cues but is the most expensive with interviewer bias risks.

When and why are filter questions used?

To direct respondents to relevant questions based on their answers, ensuring data accuracy and avoiding unnecessary questions.