Stats 2 Third Exam

Question 1

What does Repeated Measures ANOVA / “Within Subjects Design” do?

Answer 1

Test to see if responses change over time OR Test significance between multiple simultaneous responses on the same item

Question 2

What is most common within subjects design?

Answer 2

Pre-Post Design: O X O

Question 3

Pre-post statistical test sometimes called

Answer 3

“Dependent t test” This is inaccurate.

Called “Dependent Test of Means”

Question 4

What are the issues with within subjects designs?

Answer 4

• Same people responding – impacts our measurements
• Individuality differences
• Start separating out error terms

Question 5

What comprises a Repeated Measures ANOVA Model?

Answer 5

• 1 fixed categorical (dependent) IV with 2 levels that will be repeated
• 1 continuous random DV measured multiple times

Question 6

What are assumptions of Repeated Measures designs?

Answer 6

• R - random selection (not random assignment)
• N - Normality of error term
• H - Homogeneity of variance
• D - Dependence (not independence)

Question 7

What are potential methods of analysis for within subjects designs?

Answer 7

1. Multiple dependent t tests
2. Gain scores
3. ANCOVA
4. Univariate repeated measures
5. Adjusted univariate repeated measures
6. Multivariate repeated measures

Question 8

Defining features of gain scores approach to analysis in within subjects design?

Answer 8

1. Frequently used in pre-post
2. Issues:
   a. Reliability issues
   b. Alpha issues
   c. However, Observed score is true score + error
   d. Assumes same reliability across measurements

Question 9

Defining features of ANCOVA approach to analysis in within subjects design?

Answer 9

1. No test of time

2. Violates assumption of independence (it’s the very thing we want to test)

Question 10

Defining features of Univariate repeated measures approach to analysis in within subjects design?

Answer 10

Requires new assumption: Sphericity (symmetry)

Question 11

What is assumption of sphericity?

Answer 11

1. Deals with correlations among variables

2. Assumes correlation matrix will have equivalent values within it

Question 12

Defining features of Adjusted univariate repeated measures approach to analysis in within subjects design?

Answer 12

1. Adjusts for symmetry (through degrees of freedom)

2. Employs multiple tests (experimentwise alpha considerations)

Question 13

Defining features of Multivariate repeated measures approach to analysis in within subjects design?

Answer 13

1. Allows for non-symmetry
2. Controls alpha
3. One test

Question 14

What are implications of testing the assumption of syphericity (Mauchly test)

Answer 14

1. If meets symmetry, univariate approach

2. If does not, multivariate approach

Question 15

What are three types of repeated measures?

Answer 15

1. Time
2. Response mode
3. Persons unit (e.g., family)

Question 16

What is a twice repeated design?

Answer 16

1) Pre-post-follow up.

2) Unit pre-post

Question 17

In repeated measures, what are implications of unequal n?

Answer 17

Cannot work with unequal n. Excluded participants with missed observations.

Question 18

What are defining features of repeated measures error terms?

Answer 18

Every factor and every interaction has its own error term.

Question 19

Class example of a 2x2 fully repeated design

Answer 19

Child-parent, pre-post

Question 20

What are defining features of a mixed model design?

Answer 20

• 1 fixed categorical IV (between subjects)
• 1 fixed categorical repeated IV (within subjects)
• 1 continuous random DV

Question 21

In an # x # mixed model design, 1st number represents

Answer 21

Non-repeated factor

Question 22

In a # x # mixed model design, 2nd number represents

Answer 22

Repeated factor

Question 23

In a # x # x # mixed model design, 2nd number represents

Answer 23

• 1st refers to non-repeated factor
• 3rd refers to repeated factor
• Nothing in our language denotes what middle number represents

Question 24

What are assumptions of mixed model designs?

Answer 24

• Homogeneity
• Independence for some IVs
• Dependence for some IVs

Question 25

Effect size for mixed model design?

Answer 25

Eta squared or partial eta squared

Question 26

Eta squared

Answer 26

SSH/SST

Question 27

Partial eta squared

Answer 27

SSH/SSH+SSE

Question 28

What is the relation between eta squared and partial eta squared?

Answer 28

Partial eta squared gives higher value and thus overestimates strength of association. Eta squared is a more conservative estimate.

Question 29

What assumptions do you check in a mixed model design?

Answer 29

Homogeneity and sphericity first.

Question 30

If sphericity assumed

Answer 30

Look at sphericity assumed

Question 31

If mauchley test is significant

Answer 31

Look at multivariate or greenhouse geisser

Question 32

What post hocs should one examine in a mixed model design?

Answer 32

ONLY for main effects.

Question 33

When would one use a non-parametric test?

Answer 33

1. Non-continuous DV 2. Ordinal data 3. Measurement reliability less than .60

Question 34

Does using non-parametric tests resolve issues associated with a small sample?

Answer 34

No. Still requires power analysis.

Question 35

What assumptions do non-parametric tests use?

Answer 35

R, I, D. Not N or H.

Question 36

What are defining features of Kreska Wallace test?

Answer 36

An analysis of mean ranks.

Question 37

What are defining features of Friedman test?

Answer 37

Used for pre-post-follow up or participant unit over time for non-parametric data.

Question 38

When should one use an Independent t test?

Answer 38

Fixed categorical IV with 2 levels (can also use 1-way ANOVA)

Question 39

When should one use a Dependent t test

Answer 39

Fixed categorical repeated IV with 2 levels

Question 40

When should one use a 1-way ANOVA?

Answer 40

Fixed categorical IV with 3 or more levels

Question 41

When should one use a 1-sample test of means?

Answer 41

Comparing sample to larger population

Question 42

When should one use a 2-way ANOVA?

Answer 42

2 fixed categorical IVs

Question 43

Number of hypotheses is determined by...

Answer 43

Number of IVs, not number of levels

Question 44

When should one use a Helmert contrast?

Answer 44

To compare 1st group vs everything else

Question 45

When should one use a Difference contrast?

Answer 45

To compare last group vs everything else

Question 46

When should one use a simple contrast?

Answer 46

To conduct pairwise comparisons

Question 47

When should one use a Polynomial contrast?

Answer 47

To test shape of lines and trends (e.g., linear, quadratic, cubic)

Question 48

When should one use a Mixed Model design?

Answer 48

1 or more fixed categorical IV, repeated | 1 or more fixed categorical IV, non-repeated

Question 49

SSbetween =

Answer 49

Column mean - grand mean OR row mean - grand mean

Question 50

MS =

Answer 50

SS/df

Question 51

F =

Answer 51

MS/MS