Chapter 1: The World of Psychological Testing
Chapter 2: Sources of Information About Tests
Chapter 4: Reliability
Chapter 5: Validity
Chapter 6: Test Development and Item Analysis
Terms : Hide Images
| 951779504 | Achievement Tests | Tests designed to measure knowledge or skills especially as developed through school or job experience. | 0 | |
| 951779505 | Attenuation | Lessening or reduction; in testing it refers to reduction in correlation between two variables due to imperfect reliability and/or group homogeneity. | 1 | |
| 951779506 | Base Rate | The rate at which some characteristic appears in a population. | 2 | |
| 951779507 | Classical Test Theory | The traditional theory about the construction and reliability of tests, incorporating true score theory. | 3 | |
| 951779508 | Coefficient Alpha | A measure of the internal consistency of items on a test | 4 | |
| 951779509 | Concurrent Validity | Test validity demonstrated by relationship between a test and some other criterion measured at approximately the same time. | 5 | |
| 951779510 | Constructed-Response Items | A test item requiring the examinee to construct an answer rather than select an answer from given alternatives. | 6 | |
| 951779511 | Construct Validity | A broad array of methods used to support the proposition that a test is measuring its target construct. | 7 | |
| 951779512 | Content Validity | Test validity defined by the match between test content and some well-defined body of material such as a curriculum or set of job skills. | 8 | |
| 951779513 | Convergent Validity | Validity evidence showing that performance on a test agrees with other measures of the target construct. | 9 | |
| 951779514 | Contrasted Groups Validity | The criterion is group membership; generally the better the differentiation between groups, the more valid the test. | 10 | |
| 951779515 | Correction for Attenuation | Correcting the validity coefficient for unreliability in either the test or the criterion or both. | 11 | |
| 951779516 | Correlation Coefficient | The numerical expression ranging from -1.00 to +1.00, of the relationship between two variables. | 12 | |
| 951779517 | Construct Irrelevant Variance | Variance in test scores associated with variables other than those we want to measure. | 13 | |
| 951779518 | Criterion-Related Validity | Demonstrating test validity by showing the relationship between test scores and some external criterion. | 14 | |
| 951779519 | Cutoff Score | A score on a test or criterion indicating passing vs. failing or some other such division. | 15 | |
| 951779520 | Dichotomous Response Format | Items scored as "correct-incorrect" or "yes-no" where possible scores for each item are 1 or 0. | 16 | |
| 951779521 | Differential Validity | Not predicting the same performance on the criterion, but predicting equally well for two (or more) groups. | 17 | |
| 951779522 | Discriminant Validity | Validity evidence showing that performance on a test has a relatively low correlation with measures of constructs expected to have a low correlation with the trait of interest. | 18 | |
| 951779523 | Domain Sampling | The process of choosing test items that are appropriate to the content domain of the test (also see content validity and domain-referenced tests) | 19 | |
| 951779524 | Employment Tests | Content domain consists of the knowledge and skills required by a particular job. | 20 | |
| 951779525 | Error Variance (Score) | The difference between the true score and observed score which may be positive or negative. (picture on pg 129) | 21 | |
| 951779526 | Face Validity | The appearance that a test measures its intended target, especially unaccompanied by any empirical evidence. | 22 | |
| 951779527 | Factor Analysis | A class of statistical methods for identifying dimensions underlying many scores or other indicators of performance. | 23 | |
| 951779528 | False Positive | A case that passes the cut-score on a test intended to predict a criterion but does not pass the cut-score on the criterion. | 24 | |
| 951779529 | False Negative | A case that passes a cut-score on the criterion but does not pass the cut-score on a test intended to predict the criterion. | 25 | |
| 951779530 | Generalizability Theory | A method for studying reliability that allows for examining several sources of unreliable variance simultaneously. | 26 | |
| 951779531 | Hit Rate | A case that either passes the cut-scores on both criterion and test or fails on both. | 27 | |
| 951779532 | Homoscedasticity | Equal degree of scatter at various points along a best-fitting line. | 28 | |
| 951779533 | Incremental Validity | The increase in validity achieved by adding a new test or procedure to existing tests or procedures. | 29 | |
| 951779534 | Internal Consistency Reliability | Items that, for the most part, are measuring the same trait or characteristic as indicated by the intercorrelations among the items; has the same score you're measuring; the items are consistent with what you're measuring | 30 | |
| 951779535 | Interval Score | A scale that orders data points in equal intervals but lacking a true zero point. | 31 | |
| 951779536 | Item Analysis | Statistical analysis of individual test items, especially to determine their difficulty level and discriminating power. | 32 | |
| 951779537 | Kuder-Richardson Reliability Coefficients (KR-20) | Yields the average correlation among all possible split-halves for the test; a formula to optimize reliability of consistency coefficients | 33 | |
| 951779538 | Likert Response Format | A format for attitude items in which an examinee expresses degree of agreement or disagreement with a statement. | 34 | |
| 951779539 | Measurement Error | Divided into two components (systematic and random). Random: caused by any factors that randomly affect measurement of the variable across the sample. Systematic: caused by any factors that systematically affect measurement of the variable across the sample. | 35 | |
| 951779540 | Multitrait-Multimethod Matrix | A technique for examining the relationships among several variables each measured in several different ways. | 36 | |
| 951779541 | Nominal Scale | A primitive type of scale that simply places objects in separate categories, with no implication of quantitative differences. | 37 | |
| 951779542 | Nomological Network | A representation of the constructs of interest in a study, their observable manifestations, and the interrelationships among and between these (Cronbach and Meehl's view of construct validity that in order to provide evidence that a measure has construct validity, it has to be developed for its measure). | 38 | |
| 951779543 | Normal Score Distribution (Continuous Probability Distribution) | A function that tells the probability of a number in some context falling between any two real numbers. | 39 | |
| 951779544 | Observational Techniques | A social research technique that involves the direct observation of phenomena in their natural setting. | 40 | |
| 951779545 | Observed Score | A person's actual score on a test. | 41 | |
| 951779546 | Ordinal Scale | A scale that places objects in order, without implying equal distances between points along the scale. | 42 | |
| 951779547 | Phi Coefficient (Mean Square Contingency Coefficient) | A measure of association for two binary variables introduced by Karl Pearson. | 43 | |
| 951779548 | Predictive Validity | Validity demonstrated by showing the extent to which a test can predict performance on some external criterion when the test is administered well in advance. | 44 | |
| 951779549 | Psychometrics | Theories of intelligence that depend heavily on the use of tests and examination of relationships among the tests. | 45 | |
| 951779550 | r2 (Coefficient of Determination) | Indicates how well data points fit a line or curve. A statistic used in the context of statistical models whose main purpose is either the prediction of future outcomes or the testing of hypotheses, on the basis of other related information. | 46 | |
| 951779551 | Ratio Scale | A type of scale that classifies, then orders objects along a scale, with equal intervals and a true zero point. | 47 | |
| 951779552 | Reliability | The consistency or dependability of test performance across occasions, scorers, and specific content. | 48 | |
| 951779553 | Reverse Scoring (Distractor?) | An incorrect/non-preferred option in any item (an "incorrect" option may actually behave as a "correct" option). | 49 | |
| 951779554 | Selected-Response Items | Test items in which the examinee selects a response from given alternatives. | 50 | |
| 951779555 | Selectivity | The ability of a test to identify individuals with some characteristic. | 51 | |
| 951779556 | Self-Report | A type of survey, questionnaire, or poll in which respondents read the question and select a response by themselves without researcher-influence (any method which involves asking a participant about their feelings, attitudes, beliefs, etc.) | 52 | |
| 951779557 | Sensitivity | Proportion of individuals the test correctly identifies. | 53 | |
| 951779558 | Shared Family Variance | In studies of heredity and environment, variance attributable to the fact that members of a family presumably have similar environments. | 54 | |
| 951779559 | Spearman-Brown Formula | A formula allowing estimation of the effect on reliability of lengthening or shortening a test. | 55 | |
| 951779560 | Specific Domain Measures | A test that focuses on just one or a few variables in the non-cognitive domain; contrasted with comprehensive inventories. | 56 | |
| 951779561 | Specificity | The ability of a test to not select individuals who do not have the same characteristic. | 57 | |
| 951779562 | Split-Half Reliability | A measure of reliability based on splitting the test into two halves, then correcting performance on the two halves. | 58 | |
| 951779563 | Standard Error of Measurement | An index of the degree of variability in test scores resulting from imperfect reliability. | 59 | |
| 951779564 | Table of Specifications | A table with the content getting measured and the data, to determine the content validity of the test by matching the content of the test with the table. | 60 | |
| 951779565 | Test Bias | Showing that a test measures somewhat different constructs for different groups of examinees, especially for majority and minority groups. | 61 | |
| 951779566 | Test-Retest Reliability (Rtt) | Reliability determined by correlating performance on a test administered on two different occasions. | 62 | |
| 951779567 | True Score | The score a person would theoretically get if all sources of unreliable variance were removed or cancelled out. | 63 | |
| 951779568 | Validity | An indication of the extent to which a test measures what it is intended to measure. | 64 | |
| 957933820 | Inter-Rater Reliability (Rrr) | Someone else provides the testing from the scores; the rater is a source of error variance | 65 | |
| 957933821 | Intra-Rater Reliability (Rir) | The same rater of the test and score rates from one time to another; finds consistency among the rater | 66 | |
| 957933822 | Cohen's Kappa (Observer Agreement) | People trained to notice what constitutes a certain behavior | 67 |
