HSS 2381 Chapter Notes - Chapter 7: Null Hypothesis, Squared Deviations From The Mean, Relaxation Technique
10 Dec 2016
School
Department
Course
Professor
Document Summary
Analysis of variance: often abbreviated as anova, used to compare group means when three or more groups are being compared (t-tests are not appropriate) Anova: measurement issues: dependent variable, independent variable: Interval or ratio level (e. g. , heart rate, scores on self-esteem scale) Ordinal level with small number of categories (normal weight, overweight, obese) Anova hypotheses: the null hypothesis: group means are equal h0: 1 = 2 = 3 = 4, the alternative hypothesis: at least some of the group means are not equal: Dependent variable is normally distributed in the populations. Variances in the populations are equal (levene"s statistic: robustness of anova: Robust to violation of normality assumption if n per group > 20. Robust to homogeneity assumption if ns are similar. Anova principles: a key concept of anova: partitioning variance. Involves isolating reasons why people"s scores might differ from one another. Some of the reasons people differ is because there is individual variability.
