| A | B |
|---|
| psychological assessment | gathers and integrates psychology related data for the purpose of evaluation |
| three-legged stool | tests, interviews, observations |
| collaborative psychological assessment | seeks feedback and information from client |
| therapeutic psychological assessment | assesses while also helping the client achieve insight into problem |
| dynamic assessment | gives prompts, feedback or hints |
| psychometrics | science of psychological measurement |
| psychometric soundness | how consistently and accruately a test measures what it is supposed to measure |
| portfolio | used to assess job- or school-related activities or progress |
| behavioral observation | observe behaviors of people while testing |
| naturalistic observation | observe in a normal setting |
| Binet and Simon | published first intelligence test in 1905 |
| Wechsler | created WAIS in 1939 |
| eugenics | belief that feeble-minded should not be allowed to have children |
| measurement | act of assigning numbers to things according to set of rules |
| scale | specialized use of numbers used to measure a variable |
| discrete scales | only allow gross classification |
| continuous scales | allow for equal changes from one point to another |
| index | where multiple indic ators of a variable are combined into one score |
| nominal/ordinal scales | discrete scales |
| interval/ration scales | continuous scales |
| nominal scales | gross classification |
| ordinal scales | a ranking system can be used within each category |
| interval scales | There are equal intervals between numbers like in a ruler |
| ratio scales | includes a true zero point |
| distribution | a set of test scores listed in an order |
| simple distribution | list from highest to lowest or using names followed by scores |
| grouped distribution | scores are listed followed by the frequency of people making that score |
| test score intervals | class intervals |
| graph | a diagram/chart composed of symbols that describe and illustrate data |
| histogram | x and y axis; rectangle goes up to maximum number of cases |
| bar graph | two non-contiguous rectangles |
| frequency polygon | continuous line connecting where test scores or intervals meet frequencies |
| mean | add scores, divide by number of cases |
| median | middle score of a distribution |
| mode | when a score repeats more than any other score |
| variability | indication how scores in a distribution are scattered |
| range | difference between highest score and lowest score |
| measures of variability | statistics that describe the amount of variation in a distribution |
| interquartile range | from Q1 to Q3, 50% |
| semi-interquartile | half way between Q1 and Q3 |
| standard deviation | square root of variance, equal distance from mean, both positive and negative |
| skewness | not symmetrical data |
| kurtosis | steepness of a distribution at its center |
| platydurtic kurtosis | relatively flat steepness |
| leptokurtic | relatively peaked steepness |
| mesokurtic | somewhere in the middle of steepness |
| tail of the normal curve | the area between 2 and 3 standard deviations above and below the mean |
| Z scores | type os standard score that converts a specific score into an exact measure of how well a student did in relation to resto fo class and student's own scores |
| T scores | mean of 50; total of 5 SD, range of 10 |
| traits | any distinguishable, relatively enduring way in which one individual varies from another |
| state | relatively less enduring than a trait |
| construct | an informed, scientific concept developed or constructed which describes or explains behavior |
| overt behavior | behavior that is directly observed |
| operational definitions | able to measure, avoid stereotyping, agreement by experts |
| domain sampling | a sample of behaviors from the total group of behaviors that are attributed to a particular construct |
| norm-referenced testing | taking a test score of an individual and comparing it to the scores of a group of test takers |
| norms | a collection of scores that provide a reference by which to compare an individuals' score |
| standardization | process of administering a test to a representative sample of test takers for the purpose of establishing norms |
| population | all of the people that represent your group you want to test |
| sampling | taking a smaller subgroup from out of a population for testing |
| random sample | select a sample using a random process |
| stratified sampling | select sample from specifically identified subgroups |
| stratified random sampling | randomly select from specifically identified subgroups |
| convenience sampling | whoever is available that fits your needs |
| advanced norming process | stratified, radom sample; standardized instructions; controlled conditions |
| fixed reference | a norm that is used for future test takers, usually over a period of years |
| criterion-referenced | administering a test to see if student has reached a standard by which he/she can be assigned to a group |
| Pearson r | statistic to see if two sets of scores are related in some way - linear and continuous |
| positive correlation | scores increase or decrease together |
| negative correlation | scores move in opposite directions |
| Spearman rho | used for ordinal data that has been ranked; useful when sample size is small |
| outlier | a point noticeably outside the usual clumping of the data |
