Biology 2244A/B Lecture Notes - Lecture 11: Alternative Hypothesis, Bonferroni Correction, Squared Deviations From The Mean
2 Jan 2017
School
Department
Course
Professor
Document Summary
Example: if we call the mean weights for the three experimental populations of diet types mu1 for chow, mu2 for restricted, mu3 for extended, the subscript reminds us which group a parameter/statistic describes. Everything mentioned above ignored the effect of sample sizes: small differences among smaple means can be significant if the samples are large large differences among sample means can fail to be significant if the samples are small. Big idea: if sample means are far apart relative to the variation among individuals in the same groups, the(cid:396)e"s e(cid:448)ide(cid:374)(cid:272)e that so(cid:373)ethi(cid:374)g othe(cid:396) tha(cid:374) (cid:272)ha(cid:374)(cid:272)e is at (cid:449)o(cid:396)k. Comparing several means is the simplest form of anova called one-way anova. Numerator of the anova f statistic is a variance calculated using the sample means. Denominator is an average of the sample variances. The anova f test is nondirectional because any violation of h0 tends to produce a large value of f.
