PSY201H1 Lecture Notes - Lecture 3: Internal Validity
Document Summary
One individual will get same score every time. People give consistent response on multiple items of the questionnaire. Reliability is necessary but not sufficient for good measurement. E. g. self-report measure on satisfaction with life. When people wait longer, the reliability goes down because such satisfaction might now be consistent. Contextual variables exists in this case: interrater. Consistent no matter who is observing: internal. The extent to which multiple measure, are all answered the same by the same se of people. Extend to which multiple measure/multiple items fo single measure are all answered the same. An individual items on the questionnaire all mean the same thing. Cronbach"s alpha: an average of all the possible item - total correlations. See how related it is to other values. A good experiment is both valid and accurate. One can be: reliable but not valid. Focus on individual variables but not the relationship. Allow us to make frequency claim : correlational (association)
