PSY 313 Study Guide - Quiz Guide: Syphilis, Random Assignment, Internal Validity
22 Jan 2018
School
Department
Course
Professor
Document Summary
Will it produce the same result over and over. How much do we trust the measurements to be accurate. Observed score= true value +or- error (exam score= knowledge+- stress) Random error: can be in the instrument or in the person being measured. Because it is random, it cancels out with repeated measures (weight)- body weight may produce different values: intrinsic noise (drink water between measurements- may weight more) or measurement/observer error (reading of the scale) Systematic error: consistent error (scale always adds 2lb to the real weight)- could be something wrong with the instrument being used. The way we measure reliability in a study: Inter-rater reliability: same observations, different raters (people)- test the correlation between the ratings of different judges (don"t have to be exact same values)- but same relative order is important. The correlation between a test on different trials/days/weeks. Measure a groups ability to block an air hockey puck 20 times to assess hand eye coordination.
