The extent to which observers agree, calculated by dividing the total agreements by total number of observations. Results of 0.8 to 1 are good.

A measure of the extent to which something is consistent within itself. e.g. all the questions on an IQ test should be measuring the same thing.

A measure of consistency over several different occasions, e.g. if the same interview by the same interviewer with the same interviewee was conducted one day then a week later, outcome should be the same- otherwise interviewer = unreliable.

Achieved if two interviewers produce the same outcome, like inter-observer reliability.

Compare a person's performance on two halves of a questionnaire or test. If the test is assessing the same thing in all its questions, then there should be a close correlation between both halves' scores. This helps measure internal reliability.

Involves giving an individual a test on one occasion, then this is repeated again after an interval, e.g. 1 month. If the measure is reliable, the outcome should be the same every time.

Is this an inter-observer reliability strengthening technique?
'Training observers in the use of a coding system/behaviour checklist'

Does the test measure what it is supposed to measure, or are EVs getting in the way?

Made up of population, time, and ecological

When what someone observes is influenced by their expectations

Whether the test looks as though it is measuring what the researcher intends to measure, e.g. Are the questions in an interview obviously related to a topic?