CHLH 244 Lecture 10 Pt. II

# CHLH 244 Lecture 10 Pt. II - ANOVA Lecture 2 One Way ANOVA...

This preview shows pages 1–17. Sign up to view the full content.

ANOVA Lecture 2

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
One Way ANOVA table Source of Variation Mean Squares F Ratio P value Between SS b F k-1, N-k Computer generated Within SS w N-k Total SS t N-1 k=# of groups Test statistic If we are given these, k and N, We can do a problem
Example Source of Variation Sum of Squares df Mean Squares (s 2 ) F Ratio Critical F P value Between 93.75 3 31.25 7.35 3.24 Within 68.00 16 4.25 Total 19 Does the F Ratio exceed the critical value? Yes: So we reject the null hypothesis and say that the group means are not equal at the alpha=0.05 level.

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Post Hoc Test Multiple comparison tests helps to find out where the difference(s) between means are test the hypothesis that all possible pairs of means are equal pairs whose differences exceed the HSD are considered to be significantly different
Tukey’s HSD (Honestly Significant Difference) 73 . 3 ) 922 (. 05 . 4 5 25 . 4 05 . 4 = = = HSD ( 29 n MS q HSD w k N k - = , , α

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Pair Mean Difference Critical Value A-B 7-1= 6* 3.73 A-C 5-1= 4* 3.73 A-D 4-1= 3 3.73 B-C 7-5= 2 3.73 B-D 7-4= 3 3.73 C-D 5-4=1 3.73 Mean Difference and Critical value for weight gains of all possible pairs

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Calculate the means of groups 1 5 / 5 = = = A A A n X X 7 5 / 35 = = B X 5 5 / 25 = = C X 4 5 / 20 = = D X
Pair Mean Difference Critical Value A-B 7-1= 6* 3.73 A-C 5-1= 4* 3.73 A-D 4-1= 3 3.73 B-C 7-5= 2 3.73 B-D 7-4= 3 3.73 C-D 5-4=1 3.73 Mean Difference and Critical value for weight gain of each pair There is a significant difference in weight gain between A-B and A-C.

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Example 1 Again, we are interested in finding out about differences in health care service in Illinois elementary schools We have information from four counties : 5 schools for each county We are told at each school how many days a licensed medical professional is on site.
Example 1: Scenario County A 1 0 1 2 0 County B 3 3 4 5 1 County C 1 2 1 2 1 County D 3 3 1 1 1 Number of days there is a licensed health care provider at 5 schools in four different counties

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Example 1: Question Is there a significant difference in the number of days between the four counties at the α =0.05 level? How do we solve this? ANOVA? Yes…More than two groups and looking for a difference
Example 1: Hypotheses in ANOVA The null depends on how many groups. For n groups, H 0 : μ 1 = μ 2 = μ 3 = …= μ k So for 4 groups, H 0 : μ 1 = μ 2 = μ 3 = μ 4 The alternative is H 1 : One or more of the means are different from the others

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Example 1: Fill in the table Source of Variation Sum of Squares Df Mean Squares (s 2 ) F Ratio Critical F Between Within Total
Preparation for calculating SS (sum of squares) A X 2 B X 2 C X 2 D X 2 Total 1 1 3 9 1 1 3 9 0 0 3 9 2 4 3 9 1 1 4 16 1 1 1 1 2 4 5 25 2 4 1 1 0 0 1 1 1 1 1 1 Sum x 4 16 7 9 36 6 60 11 21 98

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Calculate SS between and SS within SS Within = SS
This is the end of the preview. Sign up to access the rest of the document.

## CHLH 244 Lecture 10 Pt. II - ANOVA Lecture 2 One Way ANOVA...

This preview shows document pages 1 - 17. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online