chapter 6

Question 1

parametric tests

Answer 1

operate on data from a probability distribution, such as the normal distribution or the t-distribution
applicable to ratio data and interval data

Question 2

non-parametric test

Answer 2

are “distribution free,” which is to say, they make no assumption about the distribution of the underlying data.

the data used in are
nominal categories

you’ll lose information

Question 3

ANOVA

Answer 3

determines if an independent variable—the test conditions—had a significant
impact on a dependent variable—the measured responses.

tests the data to determine the likelihood of the null hypothesis being true
(tenable) or false (rejected)

Question 4

F-statistic

Answer 4

used to compare statistical models that have been fitted to a data set to identify the model that best fits the population from which the data were sampled.

Question 5

p-value

Answer 5

the probability of obtaining
the observed data if the null hypothesis is true.

Question 6

reporting f-statistics

Answer 6

Placed in parentheses
l Uppercase for F
l Lowercase for p
l Italics for F and p
l Space on both sides of the equal sign
l Space after the comma
l Space on both sides of the less than sign
l Degrees of freedom are subscript, plain, smaller font8
l Three or four significant figures for the F statistic
l No zero before the decimal point for the p statistic (because it is constrained
between 0 and 1)

Question 7

degrees of freedom

Answer 7

If n is the number of test conditions and m is the number of participants, then the degrees of freedom are (n − 1) for the variance due to Method and (n − 1)(m − 1) for the variance due to Method × Subject.

Question 8

two-way design

Answer 8

An experiment with two independent variables

Question 9

chi-square test

Answer 9

procedure for investigating relationships, often used on categorical/nominal data

Question 10

which non parametric test?: 2 conditions, between-subjects

Answer 10

mann-whitney U

Question 11

which non parametric test?: 3 conditions, between-subjects

Answer 11

kruskal-wallis

Question 12

which non parametric test?: 2 conditions, within-subjects

Answer 12

wilcoxon signed rank

Question 13

which non parametric test?: 3 conditions, within-subjects

Answer 13

Friedman

Question 14

difference parametric and non-parametric tests

Answer 14

Parametric tests, such as the analysis of variance, assume the data are sampled from a
probability distribution, such as the normal distribution. Provided this assumption is met (and a few others are), parametric tests have more statistical power and are more accurate and more precise than non-parametric tests

Question 15

What to do if assumptions for parametric test are not met?

Answer 15

(1) proceed with the parametric test,

(2) transform or clean the data in some manner to correct the violations and then proceed with the parametric test,

(3) use a non-parametric test.

Question 16

which one is superior? parametric or non-parametric?

Answer 16

unclear, using a
non-parametric test for ratio data that violates the assumptions of a parametric test leads to loss of information; while using a parametric test for ratio data that violates the assumptions of a parametric test seems to not really have a big downside other than that you’re possibly using a test that’s based on normality while your data does not have normality as a feature