Vocabulary, ch. 5 Educational Research
Terms
undefined, object
copy deck
- construct
- abstraction that cannot be observed directly, i.e. intelligence, personality, effectiveness, creativity
- data
- pieces of information collected to examine a topic
- variable
- construct that can take on two or more values or scores
- instrument
- tool used to collect data
- measurement scale
- instrument used to obtain a range of values or scores for each variable
- nominal (categorical) variables
- classify persons or object into two or more categories, i.e. male/female, married/divorced/ single
- ordinal variables
- classify and rank persons or objects
- interval variables
- classify and rank using equal intevals, i.e. test score of 88%
- ratio variables
- classify, rank in equal intervals with a true zero point, mostly used with physical measurements
- dependent variable
- effect
- independent variable
- cause, treatment
- test
- formal, sytematic, paper-and-pencil procedure
- cognitive
- acheivement, ability, reading
- affective
- attitudes, emotions, interests, values
- assessment
- process of collecting, sythesizing, interpreting info from formal or informal instruments
- measurement
- process of quantifying or scoring person's performance on assessments
- performance assessment
- authenthic or alternative assessment
- raw score
- number correct on a test, 78 out of 100 would be 78
- norm-referenced test
- scoring indicates how one student did compared to other students who took the test
- criterion-referenced
- scores compared against predetermined levels of performance
- self-referenced
- measures how an individual student's performance changes over time
- cognitive test
- measures intellectual processes, i.e. thinking, memorizing, problem solving, analyzing, reasoning
- achievement test
- measures how well students have learned what they have been taught in school
- diagnostic test
- measures student's strengths and weaknesses
- aptitude test
- used to predict how well a student will perform in the future
- affective test
- assesses feelings, values, attitudes toward self, others, actrivities, institutions, and situations
- attitude scales
- determine what an idivdual believes, perceives, or feels about self, others, etc.
- Likert scale
- participants respond to a statement indicating whether they strongly agree, agree, undecided, disagree or strongly disagree
- semantic differential scale
- scale between two polar adjectives, i.e. necessary/unnecessary; fair/unfair, better/worse
- rating scale
- measures attitudes toward others
- Thurston scale
- measures attitude
- Guttman scale
- measures attitude and determines if it is munidmentsional, using a cumulative scale
- interest inventory
- determines an individual's like and dislikes ex. Strong-Campbell Interest Inventory and Kuder Preference Record-Vocational
- Study of Values
- test of individual's values
- personality inventory
- describes an individual's personality, i.e. Personality Adjective Checklist, California Psychological Inventory, Minnesota Multiphasic Personality Inventory, Mooney Problem Checklist, Myers-Briggs Type Indicator, Sixteen Personality Factor Questionnaire
- response set
- tendency of individual to continually respond in a particular way
- bias
- when respondent's race, gender, language, or religious orientation distorts their performance
- projective test
- answers are ambiguous and not obvious to the respondent, i.e. inkblot
- validity
- extent to which a test measures what it is supposed to measure
- content validity
- degree to which the test measures the intended content area
- item validity
- degree to which test items are relevant to the intended content area
- sampling validity
- how well the test samples the total content area being tested
- concurrent validity
- degree to which the scores on two test taken at about the same time are correlated
- predictive validity
- degree to which a test can predict how well an individual will do in a future situation
- criterion-related validity
- determined by establishing a relatoinship between scores on the test and scores on some other established test or criterion
- construct validity
- degree to which a test reflects the construct it is intended to measure
- consequential validity
- measure possible harmful effects
- reliability
- degree to which a test consitently measures whatever it is measuring
- reliability coeefficient
- a perfectly reliable test would score a 1.00
- stability
- test, retest reliability, degree to which socres on the same test are consistent over time
- equivalence
- consistency between alternate forms of the test
- internal consistency reliability
- measures reliability one test at a time using split-half, Kuder-Richardson or Chronbach's alpha
- split half reliability
- breaking single test into two halves and correlating the two sets of scores
- Kudar-Richardson
- measures intennal consistency by determining how all items on a test relate to other test items and to the total test (multiple choice)
- Cronbach's alpha
- general formula on which K-R is based
- score/rater reliability
- degree to which scoring is reliable
- interjudge reliability
- scoring reliability of two ormore independent scoreers
- intrajudge reliability
- consistency of the scoring of a single judge over time
- reliability coefficents
- .90 is a high score
- standard error of measurment
- estimate of how often you can expect test errors of a given size