Help
Options
Didn't know it?
click below
click below
Knew it?
click below
click below
Don't Know
Remaining cards (0)
Know
retry
shuffle
restart
0:00
Embed Code - If you would like this activity on your web page, copy the script below and paste it into your web page.
Normal Size Small Size show me how
Normal Size Small Size show me how
I/O Personnel Psych
LA Tech, Psych. 516, Test 1 Chapter 6
| Question | Answer |
|---|---|
| heart of personnel psychology | Measurements of individual differences. measured on nominal, ordinal, interval, and ratio scales |
| first law of psychology | people are different. Not only in respects to physical characteristics, but in a lot of other ways as well (e.g., some people are outgoing, shy, creative, unimaginative, etc.) |
| goal of scientists and practitioners is to describe what? | through laws and theories, to understand, explain, and predict physical & psychological variances. Measurement is one of the tools that enable us to come closer to these objectives. |
| Measurement is what? | the assignment of numerals to objects or events according to rules. |
| measurement answers the question of _____? | "how much?" |
| Psychological measurement is principally concerned with what? | individual differences in psychological traits. (e.g., dominance, creativity, agreeableness). |
| Qualitative | describes in terms of classification (e.g., sex, hair color). |
| Quantitative | describes in terms of frequency, amount, or degree (e.g., number of cars driving the speed limit, etc.) measurement |
| Nominal Scales | The lowest level of measurement, the primary job is assignment into different categories. |
| Ordinal Scales | provides a ranking in magnitude (e.g., jim is taller than jane; jane is taller than becky), however, it doesn’t mean there are equal intervals |
| Interval Scales | provides rankings that are in equal intervals. (e.g., 2 to 5 is the same distance as 12 to 15). The biggest difference is that there is no TRUE ZERO. (for example, temperature at 0 degrees doesn’t mean an absence of temperature). |
| Ratio Scales | provides rankings that are equal intervals and has a TRUE ZERO (for example, Jim ate three cookies, now he has ZERO cookies, an absence of cookies). |
| Raw Scores | derived directly from the measurement instrument in use. (An 80 on a test is a _______ because you need to understand it in context. If it is out of 100, then you have a B, but an 80 of out 80 is an A). |
| most commonly used scales in psychological measurement | nomial or ordinal scales. |
| examples of ordinal measures | intelligence, aptitude, and personality scales are ________ measures. They indicate not the amounts of intelligence, aptitude, or personality traits of individuals, but rather their rank order with respect to the traits in question. |
| the most important purpose of psychological measures | decision making |
| how best are psychological measures evaluated? | in terms of their social utility. The question isnt whether the psychological measures as used in a particular context are accurate or inaccurate, but, rather, how their predictive efficiency compares with that of other available procedures & techniques. |
| content, administration, and scoring of a test | Testing is systematic in these three areas (being systematic reduces effects of outside contaminants. Also important factors to consider when selecting and classifying a test. |
| 9 steps to creating a new measure | Decide measure’s purpose, define attribute, develop measure plan, write items, pilot study&traditional item analysis, item analysis using item response theory (IRT), Select items, Determine reliability & gather evidence for validity, Revise&update items |
| Determining a measure’s purpose | (e.g., will it be used for research, predict future performance, evaluate performance adequacy, etc.) |
| Defining the attribute | needs to be a clearly stated concept with all things that make it up and those things that are not included in the concept) |
| Developing a measure plan | ______is a road map of the content, format, items, and administrative conditions for the measure) |
| Writing Items | twice as many items should be written than needed because a lot of items won’t make the final version of the measurement |
| Conducting a pilot study and traditional item analysis | administer the measure to a sample that is representative of the target population |
| 3 steps to Item analysis | a. Distractor analysis b. Item difficulty analysis c. Item discrimination analysis |
| Distractor analysis | evaluate multiple-choice items in terms of the frequency with which incorrect choices are selected |
| Item difficulty analysis | evaluate how difficult it is to answer each item correctly |
| Item discrimination analysis | evaluate whether the response to a particular item is related to responses on the other items included in the measure |
| Conducting an item analysis using item response theory (IRT) | focuses on items as opposed to the entire test. does not assume all questions are equaly difficult. It relies on the proportion of correct responses to determine hard from easy questions (more people miss an item the harder the item is said to be) |
| Selecting items | Based on pilot study and item analysis, items are selected to be included in the measure. |
| Determining reliability and gathering evidence for validity | Does the measure score the same over when given to someone twice and does the measure actually measure the construct. |
| Revising and updating items | Some items in the 1990’s might not be applicable when giving in the 2000’s. |
| Affective tests are designed to measure | aspects of personality (interests, values, motives, attitudes, and temperament traits). These self-report instruments also are referred to as INVENTORIES, while aptitude and achievement instruments are called tests. |
| Tests can be classified in terms of | efficiency (e.g., time limit, group vs individual administration, computer vs paper and pencil tests). |
| Speed Tests | (e.g., number checking) consist of many easy items, but time limits are so stringent that no one can finish all the items. |
| Power Tests | Generous time limit to permit everyone an opportunity to attempt all the items. The difficulty of the items is steeply graded and the test includes items too difficult for anyone to solve, so that no one can get a perfect score. |
| Standardization or (normative sample) | is used to establish norms in order to provide a frame of reference for interpreting test scores. |
| Standardized Tests | Have fixed directions for administration and scoring. These are necessary in order to compare scores obtained by different individuals to the larger population in order to figure out where one stands based on the population. |
| Nonstandardized tests | More common than published, standardized tests. Typically these are classroom tests, usually constructed by a teacher or trainer in an informal manner for a single administration. |
| Factors used to select a test | content, ease of administration, scoring, Cost, interpretation, and face validity |
| Face validity | Whether the measurement procedure looks like it is measuring the trait in question. |
| Reliability | a measurement procedure that refers to its freedom from unsystematic errors of measurement. (i.e., does it produce the same score over and over on the same individual?) |
| Reliability coefficient | a measure of the accuracy of a test or measuring instrument obtained by measuring the same individuals twice and computing the correlation of the two sets of measures |
| Coefficient of determination | the reliability coefficient may be interpreted directly as the percentage of total variance attributable to different scores. asses how well a model explains & predicts future outcomes. How well does the model fit? 1 is perfect 0 is not. |
| Coefficient of stability | Administering the same form of a test to the same group of examinees on two different occasions. The scores from both occasions are correlated to yield a _______. It is a way to check reliability over time. |
| parallel form | is an alternate form of a test that has different questions from another version, but it measures the exact same thing |
| Coefficient of equivalence | evaluates consistency of scores from 1 form to another form of the same test. The correlation gives a reliability estimate. Checks the reliability of alternate forms of a test. Can be done through 2 administrations of test or using odd & even #'s. |
| goal of internal consistency measures | see if all the items are equally measuring the same thing and that they are discriminating between different traits being measured. For ex., if someone rates high on a question like “I am depressed”, then a question like “I am happy” should be rated low. |
| popular measure of internal consistency and an estimate of reliability | Coefficient alpha - cronbach's alpha |
| Split-Half Reliability Estimate | takes half the questions and compares the first half with the second half. The best way to divide the test is by odd and even number of questions. The test is interpreted as a coefficient of equivalence. |
| Coefficient of stability and equivalence | a combination of the test-retest and equivalence methods can be used to estimate reliability simply by lengthening the time interval between administrations. |
| Rater or (scorer) variance | the error due to the scoring of a measure and not the measure itself. |
| Interrater Reliability | How much do two different raters agree on the same administration of a single test. |
| coefficient | a number used to multiply a variable. 6x 6 is the coefficient. x is the variable. |
| two ways to classify the content of a test | tasks - verbal, nonverbal, manipulate objects, arrange blocks (performance tests) process - cognitive (tests) or inventories (reporting of feelings, beliefs & attitudes) |
| 4 ways to classify the administration of a test | efficiency (individual/group), time (speed/power), standardized, non-standardized |
| 2 ways to classify the scoring of a test | objective, subjective |
Created by:
cjd021
Popular Psychology sets