Sampling Methods
(CH 15)
(CH 15)
This type of sampling ensures that every member of the population has a chance of being selected.
What is probability sampling?
When collected data don’t accurately portray the concept being measured.
What is measurement error?
This refers to consistency and is mainly threatened by random error.
What is reliability?
These two types of questions differ in that one lets respondents answer in their own words, while the other provides answer choices.
What are open-ended and closed-ended questions?
Error that has no consistent pattern but makes results inconsistent from one measurement to the next.
What is random error?
In this method, each member of the population has an equal chance of being selected, often using random number generators.
What is simple random sampling?
When a tool works in one culture but not another because terms/meaning differ across groups.
What is cultural bias?
Validity assessed using an external criterion (like predicting college success or comparing to diagnosis).
What is criterion-related validity?
These questions should only be answered by respondents who gave a specific answer to a previous question.
What are contingency questions?
Good closed-ended response options must cover all likely answers and not overlap.
What are exhaustive and mutually exclusive response options?
Selecting every 10th person on a list after choosing a random starting point is an example of this sampling method.
What is systematic sampling?
Reliability tested by administering the same measure twice to the same people, often ~2 weeks apart.
What is test–retest reliability?
Error that consistently distorts results in a particular direction due to bias or method.
What is systematic error?
This question format uses the same set of answer choices for several questions in a chart or table.
What are matrix questions?
A response bias where people tend to agree (or disagree) with statements regardless of content.
What is the acquiescent response set?
Dividing a population into subgroups like age or gender and then randomly sampling from each group describes this method.
What is stratified sampling?
This refers to whether the measure captures the intended construct and is mainly threatened by systematic error.
What is validity?
Construct validity evidence when your measure correlates with other measures of the same construct.
What is convergent validity?
This scale asks people how much they agree or disagree with a statement, using choices like “strongly agree” or “strongly disagree.”
What is a Likert scale?
This bias occurs when people answer in ways that make themselves (or their group) look good, especially on sensitive topics.
What is social desirability bias?
Researchers studying a hidden population ask participants to recruit others they know. This is called:
What is snowball sampling?
Validity supported when the measure behaves as theory predicts in relation to other variables.
What is construct validity?
Strategy: use multiple methods with different likely errors to see if findings converge.
What is triangulation?
This scale asks people to choose between two opposite words, like “good” and “bad.”
What is a semantic differential scale?
A type of reliability for observational/coding studies that checks agreement between observers/raters (often aiming around ~80% agreement).
What is interrater reliability (interobserver reliability)?