Biology 2244A/B Lecture Notes - Lecture 11: Null Hypothesis, Variable Rules Analysis, F-Test
Document Summary
Reading 11 background to anova and introduction to post-hoc. Doing 3 tests means that we get 3 different p-values, one for each test performed. That doesn"t tell us how likely it is that 3 sample means are spread apart as far as these are. The problem gets worse as we compare more groups because we expect the gap between the largest and smallest sample mean to get larger just by chance even if they are all samples from the same population. We cannot compare many groups by doing tests or confidence levels for 2 parameters at a time. Do many comparisons with an overall measure of confidence problem of multiple comparisons. 24. 4 the idea of analysis of variance. When we ask if a set of sample means gives evidence for differences among the population means, what matters is not how far apart the sample means are, but how far apart they are.