Word Doc Week 7

Question 1

ANOVA

Answer 1

One-way (single-factor) Analysis of Variance

Question 2

ANOVA can be used in a variety of ways

Answer 2

• Independent groups
• Repeated measures
• Matched samples
• Designs involving mixtures of independent groups and repeated measures
• More than one independent variable can be evaluated at the same time
• ANOVA can be tailored to address virtually any research question.

Question 3

F statistic - Sources of Variability in a data set

Answer 3

Between-group variability

Within-group variability

Treatment+individual differences+experimental error

Individual differences+experimental error (error term)

• If there is no treatment effect at all, then F = 1
• the stronger the treatment the bigger value of F ration
• Does not have an upper limit
• Cannot be negative

Question 4

Null Hypothesis for ANOVA

Answer 4

• Group 1 - MOL treatment
• Group 2 - Drug treatment
• Group 3 - Imagery treatment
• Group 4 - No treatment Control Grou

Question 5

Post-Hoc Tests

Answer 5

• Tests carried out after you have obtained a significant overall ANOVA
• Locates the sources of significance in the F ratio
• Overall F must be significant to justify the use of post-hoc tests

Question 6

Types of Post-Hoc tests

Answer 6

• Scheffé test
• Newman-Keuls test
• Tukey’s Honestly Significant Different Test
• Fisher’s Least Significant Different Test

These tests do the same thing, tests every group with every group to unpack a significant result

Question 7

Pairwise Comparisons

Answer 7

Is there a significant difference between each pair of group means

Question 8

Planned Comparisons - Priori Tests

Answer 8

• Specific hypothesis involve sub-groups of you experiment
• Carried out instead of overall ANOVA followed by post-hoc tests
• can test complex comparisons that involve combinations of groups

Question 9

Advantages of Planned Comparisons over Post-Hoc tests

Answer 9

1. More likely to find a significant difference with a planned comparison than with an equivalent post-hoc test
2. Are statistically more powerful.
3. Can design complex comparisons

Question 10

Advantages of Post-Hoc tests over Planned Comparisons

Answer 10

• can compare each group with each group
• planned comparisons permit a smaller number of focussed comparisons

Question 11

Rules for Planned Comparisons

Answer 11

• Done instead of an overall ANOVA
• Maximum number of planned comparisons you can have is the number of groups
• Your contrast coefficients must sum to zero
  *