Ch.3 - Assessment, Effect Size, Ethics Flashcards
Omnibus Inventory
Personality tests that assess multiple personality traits in one test
Major Omnibus Inventories
- Minnesota Multiphasic Personality Inventory (MMPI)
- Big Five Inventory
- California Psychological Inventory
- Hogan Personality Inventory
What types of data do personality tests measure?
S-data, B-data
What are projective tests?
Tests where there is no right answer, and the test taker projects their thoughts into ambiguous tests
Examples of Projective Tests
- Rorschach Test
- Draw A Person Test
- Thematic Apperception Test (TAT)
Rorschach Inkblot Test
Inkblot stimulus where clients interpret what they see
Rational Test Construction
Four conditions of validity
- items mean the same to test creator and taker
- capability for self-assessment
- willingness to make an accurate self report
- items must be valid indicators of the construct
Acquiescene Response Set
Putting the same answer for all questions
Social Desirability Response Set
Picking the socially acceptable answers
Reducing the Problems of response sets
- reverse code items
- use neutral wording
- include lie scales
- use different assessment methods
Factor Analytic Test Construction
After generating a long list of objective items, administer to many people and consider what items the group have in common, naming the factor
Empirical Test Construction
Gather many items, administer to people divided into groups, compare answers by different groups, and cross validate
Cross Validate
Smaller groups being used to validate and confirm a initial analysis
Statistical Significance
A result that would occur by chance less than 5% of the time
P-Level
Probability level of obtaining a result from a statistical test if there is no relationship (p<0.05)
Issues with Significance Testing
Arbitrary criteria for significance, with high variation of significance depending on sample size
Effect Size
The size of the difference between groups
Type I Error
Deciding that one variable has an effect on another when it doesnt
Type II Error
Deciding that one variable does not have an effect on another when it really does
Publication Bias
- Occurs when the outcome of an experiment influences the decision to publish
- Bias towards positive results
- Bias towards extreme findings
Quasi-experimental
Compares people in different situations
Ethical Issues of Personality Testing
Fields may not evolve and profiling may become an issue. People may not be honest