L3

Question 1

What ANOVA stand for?

Answer 1

Analysis of variance

Question 2

What two characteristics can a data set be described by?

Answer 2

• it’s typical value

- how spread out it is (dispersion)

Question 3

What does ANOVA compare?

Answer 3

Within-group error variance
to
Between-group variance

Question 4

What would it mean for the variance if both samples were from the same population?

Answer 4

Variance within each group is similar to the variance between groups.

Question 5

What is the f ratio?

Answer 5

between groups variance
____________________
within-group variance

Question 6

What does the f ratio test?

Answer 6

The likelihood of two variance estimates being from the same population

Question 7

What does a significant ANOVA tell us?

Answer 7

That at least one group is different from at least one other group, somewhere in the analysis.

Question 8

Name two types of follow up analyses.

Answer 8

• Planned comparisons (a priori)

- Post Hoc (a posteriori)

Question 9

What is the problem with multiple tests/comparisons?

Answer 9

Increases familywise error rate

Question 10

What are type 1 errors?

Answer 10

Errors involving believing there is a difference when there actually isn’t.

Question 11

What are type 2 errors?

Answer 11

Errors involving there is no difference when there actually is.

Question 12

The chance of making a type 1 error is equal to what?

Answer 12

The p value

Question 13

When you have more than one comparison, what needs to be done

Answer 13

Divide the error rate (0.05) by the number of comparisons to make it stricter.

Question 14

Lower error rates lead to more _____ criterion for significance.

Answer 14

Strict

Question 15

How can we get around familywise errors?

Answer 15

• Making the error rate more strict

- Using post hoc tests (e.g. bonferroni)

Question 16

What level of data is needed for ANOVAs?

Answer 16

• Interval data

- Ratio data

Question 17

What are the assumptions of non-parametric tests?

Answer 17

• Distribution free.

- Ordinal data (simple treatment of data)

Question 18

Non parametric tests lead to a greater chance of type ___ errors?

Answer 18

Type 2 errors

Question 19

What is the Kruskal-Wallis test equivalent to?

Answer 19

Non parametric independent one way ANOVAs.

Question 20

How many groups does the Kruskal-Wallis test compare?

Answer 20

3 or more

Question 21

Which test is the Kruskal-Wallis test similar to and why?

Answer 21

Mann-Whitney U because it works on signed ranks.

Question 22

Once data has been ranked, what does the Kruskal-Wallis test look for?

Answer 22

Systematic differences

Question 23

What is Friendman’s test a non-parametric equivalent of?

Answer 23

Repeated measures one way ANOVA.

Question 24

How many conditions does Friedman’s test compare?

Answer 24

3 or more related ones.

Question 25

Which test is similar to Friedman’s?

Answer 25

Wilcoxon, because it uses ranked differences.

Question 26

What is Friedman’s test hypothesis?

Answer 26

The ranks of differences between a pair of conditions are systematically higher (or lower) than the ranks of the differences between another pair of conditions.

Question 27

What is Kruskal-Wallis’ test hypothesis?

Answer 27

The ranks in one condition are systematically higher (or lower) than the ranks in another condition. There are differences between conditions