What are constructs?
Unobservable, underlying already existing traits or characteristics that we can try and measure directly using tests
Observable, underlying hypothetical traits or characteristics that we can try and measure indirectly using tests
Observable, underlying already existing traits or characteristics that we can try and measure indirectly using tests
Unobservable, underlying hypothetical traits or characteristics that we can try and measure indirectly using tests
Statement 1: construct under-representation is the variation in an underlying construct that that is not captured by the measure Statement 2: construct irrelevant variance is the variance that is not related to to the construct that is captured by the measure
Statement 1: false Statement 2: true
Statement 1: true Statement 2: false
Both are true
Both are false
Statement 1: opinion-base validity measures include face and content validity Statement 2: a measure with high validity has a small overlap between construct under-representation and construct irrelevant variance
Statement 1: tests may have good face validity without any actual validity Statement 2: tests may have poor face validity while still having good actual validity
What type of validity is the following example demonstrating: a 3020 exam could have reasonable empirically-based validity without actually including any PSYC3020 content
Content validity
Face validity
Criterion validity
Convergent validity
How is content validity measured?
By getting novices and experts to both take the tests and comparing the differences
By getting the test-takers to rate how relevant the measure is to the construct
By getting experts to rate each question
By doing a factor analysis
Statement 1: measurements that are reliable are also valid Statement 2: on the other hand, one can have a valid test if it is unreliable
What is the difference between non-random attrition and self-selection?
Non-random attrition: certain types of people dropping out of a longitudinal study Self-selection: only certain types of people are in your sample in the first place
Non-random attrition: different types of people dropping out of a longitudinal study Self-selection: random selection of people are in your sample
Non-random attrition: only certain types of people are in your sample in the first place Self-selection: certain types of people dropping out of a longitudinal study
Non-random attrition: random selection of people are in your sample Self-selection: certain types of people dropping out of a cross-sectional study
Statement 1: two factors that restrict the range of scores in a validity study is non-random attrition and self-selection Statement 2: the validity coefficient always has to be above .70
Statement 1: in criterion validity a method of contrasted groups is defined as test scores of groups of people varying as expected Statement 2: criterion validity involves a 'criterion' that is a standard against which a test is evaluated
What is criterion contamination?
The criterion that is being used to assess validity undermines the logic of criterion validity because the test scores of groups of people did not vary as expected
The criterion that is being used to assess validity undermines the logic of criterion validity because it failed to achieve high ratings from experts
The criterion that is being used to assess validity is determined after the test has been taken which undermines the logic of criterion validity
The criterion that is being used to assess validity is pre-determined by the test which undermines the logic of criterion validity
Statement 1: Concurrent validity is where a number of different predictors (tests) are used together Statement 2: it is unimportant for both the test and its criterion to have decent reliability because the reliability is irrelevant to the size of the validity coefficient
Statement 1: incremental validity is how much each individual predictor adds to predicting the criterion in addition to the effect of other predictors Statement 2: predictive validity is a subset of criterion validity where the test is trying to predict what the criterion will be at some future time
Statement 1: There is no difference between discriminant and divergent validity Statement 2: for incremental validity if two predictors are highly correlated then you should include both as each one is adding predictive power beyond the other
Statement 1: convergent validity is when test scores correlated with other measures of the same thing Statement 2: discriminant/divergent validity is when tests scores do not correlate highly with measures that are not supposed to measure the same construct
What is the Wechsler Intelligence Scale for Children (WISC-IV)?
A test designed for children aged 10+ which contains 10 core subtests arranged into two groups (verbal comprehension, perceptual reasoning)
A test designed for children aged 10+ which contains 10 core subtests arranged into four groups (verbal comprehension, perceptual reasoning, long-term memory, processing speed)
A test designed for children aged 6-16 which contains 10 core subtests arranged into two groups (long-term memory, processing speed)
A test designed for children aged 6-16 which contains 10 core subtests arranged into four groups (verbal comprehension, perceptual reasoning, working memory, processing speed)
What is factor analysis?
Mathematical techniques are used to group items into clusters on the basis of how much they fail to correlate with each other
Mathematical techniques are used to group items into clusters on the basis of how much they correlate with each other referred to as internal structure
Mathematical techniques are used to group items into clusters on the basis of how much they correlate with each other and most of the time produce high correlations
Mathematical techniques are used to group items into clusters on the basis of how much they correlate with each other and most of the time produce low correlations
