COMM3330 Lecture Notes - Lecture 2: Inter-Rater Reliability, United States, Guttman Scale
Document Summary
Anything that exists, exists in quantity, and anything that exists in quantity can be measured. What can be measured: attributes (closeness, love, ability to resolve conflict) Reliability (pg 122-125) - is your measurement consistent? (consistency) A matter of whether a particular technique, applied repeatedly to the same object, would yield the same result each time. Inter-observer reliability (between observers or raters, a. k. a. inter- coder or inter-rater reliability) Intra-observer reliability one observer gets the same result several times (ex. getting tired? same over time?) (being consistent with oneself) Inter-item reliability one item/question/point of measurement that is consistent with the other points (how similar are questions?) Test-retest method do you get a similar result later (ex. personality measures, if you get an a on a first test and a c on the next test) Split half-method two halves with different wording (internal consistency) (taking the entire questionnaire and looking at consistency among answers) (ex.