This preview shows page 1. Sign up to view the full content.
Unformatted text preview: an One-Population Variance Two-Population Variances More-than-two-Population Means More-than-two-Population Means (ANOVA)
Like before, F is the ratio between two sample variances: F
2 SB 2 Sp SST k SSE n 1 k MST MSE 2 But now S1 is the variance of different population means around a pooled mean (or grand mean), i.e., 2 SB k j 1 nj xj 1 x 2 k SST k1 MST 2 and Sp is the (pooled) variance of the samples around its own means: 2 Sp k j 1 nj k j 1 nj 1 Sj2 1 k j1 nj i1 xji k xj 2 n
13 SSE nk MSE Statistical Inference Types of Test Exercises One-Population Mean Two-Population Mean One-Population Variance Two-Population Variances More-than-two-Population Means More-than-two-Population Means (ANOVA)
If all the means are equal (null hypothesis cannot be not rejected), the variance between samples will be 0 (zero), 2 S1 MST 0. Otherwise, the variance between samples will be greater 2 than zero, S1 MST 0. In other words, H0 H1
1 2 k MST 0 MST 0 At least two means are different from each other Thus it is a one-tailed test and you are always looking at the upper tail.
14 Statistical Inference Types of Test Exercises Midterm Questions # 12, p. 226 # 10, p. 225 # 14, p. 226 # 24, p. 231 # 29-31, p. 233 15...
View Full Document
This note was uploaded on 02/14/2011 for the course ECON 203 taught by Professor Petry during the Spring '09 term at University of Illinois, Urbana Champaign.
- Spring '09