Week 6 - Lecture 6 Flashcards

1
Q

What does ANOVA tell you?

A

ANOVA tells you if there’s a difference somewhere between 3+ group means

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What do follow-up tests help you determine after ANOVA?

A

Follow-up tests help you find out which groups are different

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What are the two main types of follow-up tests?

A
  • Planned Comparisons (A Priori)
  • Unplanned Comparisons (Post Hoc)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What are Planned Comparisons?

A

You decide before collecting data what comparisons to make

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Why are Planned Comparisons considered more powerful?

A

They have less error risk

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What statistical method do Planned Comparisons use to control Type I error?

A

Uses Bonferroni t test

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What are Unplanned Comparisons?

A

You decide after seeing the results

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is a characteristic of Unplanned Comparisons?

A

More exploratory

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What test is used for pairwise comparisons in Unplanned Comparisons?

A

Tukey

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What test is used for all comparisons in Unplanned Comparisons?

A

Scheffé

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What are Linear Contrasts?

A

A fancy way of doing multiple t-tests without inflating error

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What do Linear Contrasts compare?

A
  • One mean vs another mean
  • An average of group means vs another group
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

How do you set up Linear Contrasts?

A

Each group gets a weight (called A)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What are the rules for setting up Linear Contrasts?

A
  • Groups not involved = weight of 0
  • Positive weights vs negative weights
  • Weights must add up to zero
  • Use whole numbers
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is the formula for Linear Contrast (L)?

A

L = ∑(A_j × group mean)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What is the formula for Bonferroni t?

A

t = L / (MS_error × ∑A_j²)

17
Q

What does MS_error represent in the Bonferroni t formula?

A

MS_error is from the ANOVA table

18
Q

What are Orthogonal Contrasts?

A

Each comparison asks a different question

19
Q

What conditions must Orthogonal Contrasts satisfy?

A
  • Be valid linear contrasts
  • Have sum of products of weights = 0
  • Be no more than (k−1) comparisons
20
Q

How many orthogonal contrasts can you have with 3 groups?

A

Max 2 orthogonal contrasts

21
Q

What did Bonferroni t-tests reveal about anxiety management in treatments?

A

Those receiving any treatment had better anxiety management than the control group

22
Q

What was the significant finding between ACT and CBT?

A

There was no significant difference between ACT and CBT

23
Q

In the Dog Jealousy study, what triggered more jealousy?

A

Any pretend animal triggered more jealousy than jack-o’-lantern

24
Q

In the Diet and Mood study, what was found about any diet?

A

Any diet lowered mood compared to no diet

25
Fill in the blank: _______ is used for all comparisons in Unplanned Comparisons.
Scheffé