



Study with the several resources on Docsity
Earn points by helping other students or get them with a premium plan
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
PSYC 2080 MIDTERM VERIFIED ACCURATE STUDY GUIDE
Typology: Exams
1 / 5
This page cannot be seen from the preview
Don't miss anything!




Fundamental principle - Answers - the more error there is in your measurements, the less reliable those measurements are Tests - Answers - standardized means of investigating samples of behavior that will, if properly quantified and interpreted, reveal individual differences in the latent traits (abilities) or developed competencies (achievements) we wish to assess psychological test - Answers - set of items designed to measure characteristics of human beings that pertain to behavior Ability - Answers - present competence or potential to perform some task Personality - Answers - enduring dispositions to behave in certain ways, consistent over the lifespan of the individual. Stable enduring characteristic Achievement - Answers - The result of previous learning Focus on the past Aptitude - Answers - Potential to acquire a particular skill- in the future Focus on the future Intelligence - Answers - General potential to solve problems, think abstractly, adapt to change, and learn the lessons of experience Structured Personality test - Answers - Series of statements to which test-taker responds in a standard way (e.g., Yes/No) Projective Personality tests - Answers - Stimulus, response, or both are ambiguous Question may not be designed to elicit a specific response No standard way of responding Elicits someone's "unconscious thoughts" Individual administration - Answers - More control over test situation (focus on one person at a time, monitor their state, concentration, etc) More information, more complex testing Higher cost Trained examiner Group administration - Answers - More efficient More objective scoring (scored by some automated process
Descriptive statistics - Answers - purposes of description Summarize data and evaluate observations relative to others (observed within our samples) Inferential statistics - Answers - Logical deductions that cannot be observed directly in the population using sample data (subsets of population) Random influences - Answers - fluctuations in brain chemistry, unpredictable distractions Measurement error - Answers - no matter how much we try to regulate or control various influences on behavior there are always some that escape our control true score - Answers - value we would observe if our measurement process were completely free of error Measures of central tendency - Answers - answer the question, "what happened?" - to the data, includes things such as the Mean, median and mode Measures of variability - Answers - Include the Range, Standard Deviation, Average deviation, Variance Range - Answers - Difference between the highest and lowest scores in a set, (50,65,90,190) > (190-50) = standard deviation - Answers - average distance between each score and the mean of that set of scores, scores add up to 0 Variance - Answers - square of the standard deviation Measurement - Answers - application of rules for assigning numbers to objects Magnitude - Answers - particular instance of attribute represents more, less, or equal amounts than does another instance Height - If Rae is taller than Claire, then the "height" scale has magnitude Equal intervals - Answers - Distance between two points on scale has same meaning as distance between two other points ruler - distance between 2 and 4 inches is the same as distance between 4 and 6 inches Nominal - Answers - numbers are used as labels, not as numbers Not really scales at all; only purpose is to name/categorize objects Ordinal - Answers - numbers show ranks of cases on some measure
Split-half reliability - Answers - After testing, divide test items into halves A & B that are scored separately (Can divide in half randomly or divide by odd/even numbers) Spearman-Brown - Answers - re = 2rc/ 1+ rc correct reliability estimate Kuder-Richardson 20 - Answers - avoids problems associated with splitting by simultaneously considering all possible ways of splitting a test into 2 halves Doesn't require you to split the test into halves for situation where test items are dichotomous (typically right or wrong). Cronbach's α (alpha) - Answers - generalizes KR-20 to tests with more than two response categories more widely used than most estimates of reliability When items all assess the same trait or ability, will be larger (closer to 1) Single-observer error - Answers - failure to observe everything Multiple-observer error - Answers - different answers from each observer as to how many behaviors occurred in a unit of time or when they occurred. Inter-rater reliability - Answers - Percent (%) agreement between ≥ 2 observers Issue: over-estimates reliability since observers sometimes agree by chance Kappa Statistic - Answers - Estimates actual inter-rater agreement as a proportion of potential inter-rater agreement after correction for chance Standard error of measurement (SEM): - Answers - estimates extent to which a test (observed) score misrepresents the true score Small ____ means test score is probably very close to true score = (S)√(1 - r) Spearman-Brown prophecy formula - Answers - compute number of items needed to achieve a desired level of reliability Validity - Answers - measures agreement between a test score and the characteristic that score is believed to measure Face validity - Answers - refers to the appearance that a test measures what it is intended to measure public relations value - Answers - if the test appears to be sensible test-takers may be motivated Not recognized as a "real" form of validity
Content validity - Answers - Determined by logic rather than statistics Important in educational settings Refers to the extent to which a measure represents all facets of a given construct. Content-related evidence - Answers - considers coverage of the conceptual domain tested Construct-irrelevant variance Arises - Answers - Arises when irrelevant items are included on test Arises when external factors such as test anxiety or reading comprehension Criterion-related evidence - Answers - tells us how well a test score corresponds to a particular criterion (outcome) measure Criterion-related validity - Answers - extent to which a measure is related to an outcome. Test scored should tell us something about the resulting outcome correlation Borsboom - Answers - Before you create a test of something - an aptitude, an ability, an attitude - you have to have a good scientific model of that thing constructs - Answers - something that we infer, intangible Construct validity - Answers - the degree to which a test measures what it claims, or purports, to be measuring Convergent Construct-related Evidence - Answers - 1) When a test correlates well with other tests believed to measure the same construct