HSS 3101 Lecture Notes - Lecture 5: Likert Scale, Content Validity, Visual Analogue Scale

• School: University of Ottawa
• Department: Health Sciences
• Course: HSS 3101
• Professor: Jason Steffener

Document Summary

Measurement: giving a numerical value to some phenomenon. Hypothetical constructs: not directly observable, consists of behaviours, attitudes, and processes. Many different scales exist to measure the same construct. Scale users must be clear about their own de nition of a construct: variables: types of variables. Categories must be collectively exhaustive: discrete variable: the answer is constrained to be a whole number, cant take on any value between the whole number, continuous variable: can assume any reasonable value, variables: levels of variables. There are four levels of variables: nominal: named categories, can calculate mode (category with the most members), order does not matter. N=89, nmale=13, nfemale=76: ordinal: categories in rank order, can calculate median and range or interquartile range (non-parametric stats) Interval: values are equally spaced, can calculate mean and standard deviation (parametric stats) Ie. 1, 2, 3, 4, 5, 6, 7, 8 > 8 is twice as high as 4 (cannot say that 8 is four more than 4)