PS295 Lecture Notes - Lecture 3: Pearson Product-Moment Correlation Coefficient, Likert Scale, Concurrent Validity
Document Summary
Reliability: refers to the consistency or dependability of a measure, how consistently a measure assigns the same score to the same observation. Total variance in a set of score = variance due to true scores + variance due to measurement error. Reliability = true score variance / total variance. Reliability is the proportion of the total variance in a set of scores that is associated with participants true scores. To assess reliability we estimate the proportion of the total variance in the data that is true-score variance. Increasing reliability: standardize administration, clarify instructions and questions, train observers, minimize coding errors. The more is better rule : reliability is likely to increase as we increase the number of, observers (or raters, observations (or items, occasions, measurement error will average out. Correlation i used to assess reliability and validity. Reliability: correlation using just your measure, eg correlation of the measure with itself across time, eg correlation among parts of your measure.