MKC2500 Lecture Notes - Lecture 18: Null Hypothesis, Shampoo, Total Variation
ETC2500 Notes
Conducting One-Way ANOVA
1. Identify the dependent and independent variables
• Must have a dependent variable (preference for a shampoo) that is metric
(measured using an interval or ratio scale) and one or more independent
variables
• The independent variables must be categorical (nonmetric) – age and
income categories
2. Decompose the total variation
• In one-way ANOVA, separation of the variation observed in the dependent
variable into the variation due to the independent variables plus the
variation due to error
• This variation is measured by the sums of squares corrected for the mean
(SS)
• Between variation: amount of variation between group sample means
• Within variation: (leftover) variation within each group
SSy = SSbetween + SSwithin
SSy = SSx + SSerror
3. Measure the effects
• The effects of X and Y are measured by SSx
• As SSx is related to the variation in the means of the categories of X
4. Test significance
• The interest lies in testing the null hypothesis that the category means are
equal in the population
5. Interpret the results