Testing Flashcards
Shrinkage
When validity scores (coefficients) tend to be lower for cross-validation sample than for the original sample.
What is the difference between oblique and orthogonal?
Oblique = correlated (related in some way)
Orthogonal = uncorrelated (statistically independent)
What is the purpose for using the multi-method matrix to evaluate tests?
To measure a tests construct validity.
If there are high correlations between the scores tests being measured with other scores on tests being measured for the same traits, the evidence for CONVERGENT VALIDITY
when the test has low correlation of scores with tests that measure unrelated traits, this is evidence for DIVERGENT VALIDITY.
What is a coefficient of determination?
It is a measure of the amount of difference in one item/trait that is accounted for by difference in another item/trait. (ex. how does EPPP score correlate with a psychologist’s salary five years after taking the exam?)
What was the Larry P. v. Wilson Riles case all about?
It prohibited scores from IQ tests to place African-American children in special education classes.
What is the PPVT – 5 used for?
Know that the PVT stands for “Peabody picture vocabulary test” and is used to assess the receptive vocabulary of individuals ages 2.5–90 years old. It can be used with individuals who have ASD, symptoms of psychosis, cerebral palsy, or other physical disabilities.
What is the Vineland-III used for?
Measures adaptive functioning. (Remember that a vine adapts around the trellis as it’s growing.)
What is the KABC– 2 used for?
Based on the Cattell-Horn-Carroll model and Luria’s neuropsychological processing model.
Provides five scales: simultaneous, sequential, planning, learning, knowledge
What are the four types of composite scores and the mean and standard deviation of the SB5?
- Full scale IQ
- Factor index score
- Verbal/nonverbal Domain scores
- Abbreviated Battery IQ score
Mean= 100
Standard deviation = 15
what does “shrinkage“ mean?
Is associated with cross validation, and refers to the fact that a validity score is likely to be smaller than the original score when the test and item are administer to another testing sample. Shrinkage occurs because the factors that contributed to the relationship between the test items in the original simple are not present in the cross validation sample.
Ravens progressive matrix (RPM)
Measures fluid intelligence and are considered to be culture reduced because they do not use language and performance does not depend on specific cultural or academic learning.
There are three RPM tests: standard progressive metrics, colored, progressive metrics and advanced progressive metrics.
Woodcock Johnson
Slauson intelligence test
Kuhlmann-Anderson test
Bender-Gestalt II
Is a measure for visual-motor integration, and a screening test for brain damage especially right parietal lobe damage.
What does it mean when a psychological assessment has a limited floor or limited ceiling?
The floor and ceiling of a test are the degrees to which a test can discriminate on examines who have very low levels or high levels of characteristics measured by the test.
What is the Leiter International Performance Scale used for? (Leiter-3)
- Cognitive abilities for ages 3 to 75+
- nonverbal format design
- useful for non- English speakers and individuals with language impairments cognitive. abilities and Autism.
- measures fluid intelligence
Wisconsin card sorting test
- Sensitive to frontal damage
- assesses abstract thinking for perseveration
- distinguishes between frontal and non-frontal lesions.
How was the SB5 developed and what is it used for?
It comes from the Cattell-Horn-Carroll model that combines the distinction of fluid and crystallized intelligence with Carol’s Three Stratum theory of general intelligence that includes several broad cognitive abilities and some narrow cognitive abilities.
SB five is the only test out of many that are built on CHC model test five cognitive abilities which are:
– Knowledge
– Fluid reasoning
– Quantitative reasoning
– Visual spatial processing
– Working memory
What are the four tests that are built off of the CHC model?
– SB5
- WAIS-IV
– KABC-II
- WJ-IV
List the highest to lowest scale on the WAIS-IV that identifies an adult with ADHD.
Verbal comprehension
Perceptual reasoning
Working memory
Processing Speed
What are some general test construction rules that help improve reliability scores?
- Longer tests are more reliable than shorter tests
- When there’s more variation in the attributes of the testing population.
What is a major rule when choosing between T tests and analysis of variance?
T test is used when there’s one IV.
MANOVA is used when there are two or more DV’s
ANOVA is used when there are two IVs and one DV that are on an interval or ratio scale.
How are parametric statistical test more powerful than non-parametric tests? And what are some example of parametric and non-parametric tests?
Parametric tests are able to reject a false null hypothesis?
Parametric tests are T tests and ANOVAS. Nonparametric are Chi-Square tests.
What is the item discrimination index used for and how is it calculated?
It’s used to measure low and high overall scores on a test. The scoring ranges from -1.0 to +1.0 and the closer is to 0, the weaker it’s ability to discriminate.
According to classical test theory variability in test scores is due to a combination of what?
True score variability, and random error.
What is the Wonderlic personnel test – revise (WPT-R) a measure of?
It’s a 12 minute test of general mental ability that’s used to predict job success.