SOC202H1 Lecture Notes - Lecture 8: Null Hypothesis, Statistical Hypothesis Testing, Sampling Distribution
Document Summary
Content: chapter 5 to 9, february 6, 13, 27 and march 6. Format: 30 mc (60%, 5 open ended questions (40%) So total alpha is 1 - 0. 60 = 0. 40. Type 1 error: the analysis if variance procedure overcomes this problem by providing a single test comparing means from multiple samples. You can think of anova as extension of t-test for more than two groups. Anova asks (cid:498)are the differences between the samples large enough to reject the null hypothesis and justify the conclusion that the populations represented by the samples are different? (cid:499) The h0 is that the population means are the same: H0: 1= 2= 3 = = k. Of h0 true then sample means show be about the same value. If h0 is false, there should be substantial differences between the sample means of the categories, combined with relatively little difference within (sample standard deviations should be low in value) categories.