ANOVA

Question 1

We use ANOVA instead of multiple t-tests to control the

Answer 1

Error rate (familywise error)

Question 2

What type of error can you make from familywise error?

Answer 2

Type 1 - you think there’s an effect when there isn’t

Question 3

Independent groups ANOVA the level of measurement for the IV is

Answer 3

Nominal/caregoric

Question 4

Independent ANOVA the level of measurement for the DV is

Answer 4

Interval

Question 5

ANOVA produces an ………statistic

Answer 5

F

Question 6

ANOVA compares the

Answer 6

Systematic variance to the unsystematic variance

Question 7

What does k represent?

Answer 7

Number if groups

Question 8

Instead of n-1 for different ANOVA what do we have to do???

Answer 8

Take the number of groups I.e. K-3 (3groups)

Question 9

One way ANOVA assumptions

Answer 9

Interval or ratio measurement for DV
Scores randomly sampled from pops if interest
Scores are independent (participants not in multiple groups)
Scores on DV normally distributed
Homogeneity of variance

Question 10

What test tests homogeneity of variance?

Answer 10

Levenes

Question 11

If levenes test is not sig variances are assumed

Answer 11

Equal

Question 12

If levenes test is sig than variances are assumed

Answer 12

Unequal

Question 13

If normality violated what non parametric test would u use?

Answer 13

Kruskal-Wallis

Question 14

If homo of variance is violated what tests would u use?

Answer 14

Brown-forsythe or welch f

Question 15

What is the grand mean

Answer 15

The mean outcome variable of all groups

Question 16

The bigger the diff between the group means the bigger the difference between the model and the

Answer 16

Grand mean

Question 17

Total variance is the

Answer 17

Total sum of squares

Question 18

Model sum of squares is when the variance is calculated

Answer 18

Between groups

Question 19

Residual sum if squares is where the variance is calculated

Answer 19

Within groups

Question 20

ANOVA simply analyses the

Answer 20

Variance in scores to determine the source of that variance

Question 21

How to calculate SD?

Answer 21

Take each score minus the mean. Add up all and the square them

Question 22

To get the sum of squares SST total we…

Answer 22

Take each score from the mean, square it and add them all up

Question 23

How do you calculate sum of squares SSM for the model?

Answer 23

Mean of each group minus the grand mean. Square each of the differences. Then multiply each by the n of participants in that group

Question 24

How to calculate sum of squares residual SSR?

Answer 24

Sum of squares total SST minus the Model Sum of Squares SSM

Question 25

How many types of degrees of freedom are there with ANOVA?

Answer 25

3

Question 26

Between groups ANOVA df calculated by

Answer 26

k-1 (k=n of groups)

Question 27

Within groups ANOVA df calculated

Answer 27

N-k (k= n of groups, n = total sample size)

Question 28

How do you work out the within groups df?

Answer 28

N (total sample) - k (n of groups)

Question 29

To calculate the mean squares we

Answer 29

Take the SSM and divide by its df

Question 30

How is F Calculated

Answer 30

F = MSM divide by MSR

Question 31

What happens if F is greater than 1?

Answer 31

Indicates the experimental manipulation has some effect above and beyond the effect of extraneous factors

Question 32

If F is sig in an ANOVA it indicates that there are

Answer 32

Differences among group means that cannot be attributed to error

Question 33

Sig F does not tell us

Answer 33

How big these differences are or if they have practical importance

Question 34

Eta squared is just

Answer 34

R squared

Question 35

Eta squared tells us about the

Answer 35

Effect size in %

Question 36

Observed power tells us

Answer 36

The % at which we would expect to get the same result if the study was replicated

Question 37

Power depends on

Answer 37

Effect size Alpha level Sample size

Question 38

ANOVA tell about

Answer 38

The overall effect. Not between each group etc

Question 39

Ways to make comparisons btwn groups in an ANOVA

Answer 39

Priori comparisons | Post-hoc comparisons

Question 40

Priori comparisons are comparisons between group means are devised

Answer 40

Before data is collected and the ANOVA performed

Question 41

Examples of priori comparisons

Answer 41

Multiple independent groups t-tests Linear contrasts Nonferrous t Sidak test

Question 42

Most common priori comparison

Answer 42

Bonferroni

Question 43

What do you do with bonferoni?

Answer 43

Take alpha and divide by 3 (amount of groups)

Question 44

Post hoc comparisons are conducted between groups

Answer 44

AFTER data collected. Look at means and noted which group means appear diff

Question 45

Common post-hoc tests

Answer 45

``` Fischers least sig diff Student-Newman-keuls tests Tukeys The Ryan einot Gabriel welch Q procedure Scheffe test Dunnets test ```

Question 46

Post hoc with equal variances assumed generally use

Answer 46

Tukey or REGWQ

Question 47

Post hoc unequal variances use

Answer 47

Games howell

Question 48

Factorial designs are diff because they look at 2 or more

Answer 48

IVs

Question 49

In factorial designs each level of every factor is

Answer 49

Paired with each level of every other factor

Question 50

Factorial designs allow us to establish if

Answer 50

IVs interact with one another. Does the effect of an IV depend on another IV? Ie does learning time and learning setting depend on each other?

Question 51

A 2x2 ANOVA has

Answer 51

Two IVs

Question 52

Factorial designs are also

Answer 52

Mixed designs. Comprise of at least one within subjects factor and at least one between subjects factor. Ie new versus old method

Question 53

Mean square is the

Answer 53

Sum of squares divided by its degrees of freedom

Question 54

What is a box whisker plot?

Answer 54

Graphically depicts groups of numerical data through quartiles (used this in 1012 assign)

Question 55

Box whisker plots don't show the

Answer 55

Mean