Week 2

Question 1

What is the model for an ANOVA?

Answer 1

score = grand mean + treatment effect + residual error

Question 2

What is residual error?

Answer 2

Differences unique to each person and experimental noise

Question 3

What are the 3 assumptions of ANOVA?

Answer 3

1. homogeneity of variance
2. normality
3. independence of observation

Question 4

What two variances produce the F statistic in an ANOVA?

Answer 4

1. variance due to the effects of treatment

2. error variance

Question 5

What is the sum of squares, being the first step toward the calculation of each part of the variance?

Answer 5

A sum of squares is the sum of the squared deviation about some mean, or some multiple of that.

Question 6

What are the degrees of freedom?

Answer 6

Number of things that were used in the estimation of a particular value.

Question 7

What is the sum of squares due to total scores?

Answer 7

The difference of a value against the grand mean, squared. Do this for all values in a SS total.

Question 8

What is a sum of squares due to treatment?

Answer 8

The difference between the overall treatment score against the grand mean, squared.

Question 9

What is a sum of squares due to the error (overall error)?

Answer 9

Difference between the SS total and the SS treatment is the SS error - the overall amount of unexplained error in the study.

Question 10

What is the definition of variance?

Answer 10

The SS divided by the degrees of freedom.

Question 11

What is the df total?

Answer 11

number of observations - 1

Question 12

What is the df treatment?

Answer 12

number of groups - 1

Question 13

What is the df error (overall error)?

Answer 13

df total-df treatment.

The bit “left over” is the unexplained variation

Question 14

What is the mean square?

Answer 14

variance

Question 15

how is the total mean square variance obtained?

Answer 15

SS total/df total

Question 16

how is the treatment mean square variance obtained?

Answer 16

SS treat/df treat

Question 17

How is the total mean square variance obtained?

Answer 17

SS error/df error

Question 18

How is the F statistic calculated?

Answer 18

the numerator = df treat
divided by
the denominator = df error

Question 19

Both MS treat and MS error are estimates of the population variance.

While MS error is always a ___ ____
MS treat is _____ ___ _ _ _ _

Answer 19

1. true estimate

2. only a true estimate if Ho is true

Question 20

The further away from 1 F is, the:

Answer 20

less likely it is that the Ho is true

Question 21

If Ho is true, what does this mean for MS treat and MS error should be:

Answer 21

similar and F should be close to 1

Question 22

What is one way to see if our F ratio is critical (significant)

Answer 22

We have to check out F ratio against a sampling distribution of F ratios to find the critical value to evaluate how large the F ratio has to be without rejecting the null hypothesis. If F is bigger than critical value, then we can say it’s less than 5% likely that results occurred due to chance (reject the null).

Question 23

What does the critical value (to determine if the F statistic is great enough to reject the null) vary depending on?

Answer 23

the dfs, the alpha level of interest and direction of hypothesis

Question 24

What is one way to look at statistical significance?

Answer 24

p value

Question 25

What is one way to look at psychological significance?

Answer 25

The effect size

Question 26

What type of effect size expresses the difference between means in terms of the size of the standard deviation of scores in your study?

Answer 26

Cohen’s (and Hedges’ g)

Question 27

Is Cohen’s d bias? If so, when?

Answer 27

Yes it is positively bias (overly generous) when you have a small sample size.

Question 28

What is a rough “minimum” for sample size for using Cohens’ d?

Answer 28

100

Question 29

If you have a small sample size and are worried about Cohens’ d, what’s one way to take the small sample into account so that the data can still be used?

Answer 29

Hedges g - is practically equivalent but has a correction factor to account for the bias from small samples.

Question 30

Can you interpret hedges g and cohens d in exactly the same way?

Answer 30

pretty much

Question 31

Can Cohen’s d go above 1?

Answer 31

Yes, it can go way above 1.

Question 32

What are the R effect sizes?

Answer 32

measures the strength of association between the DV and IV. i.e., how much of the variation in your scores, are associated/due to variation in your IV.

Question 33

How do you calculate eta squares?

Answer 33

SS treatment divided by SS total

Question 34

what would an R square score of 0.477 tell us?

Answer 34

That 47.7% of the variance in the DV can be explained by the IV.

Question 35

In a perfect experiment, what would the R squared value be?

Answer 35

As close to 1 as possible (all score variation is associated with the IV).