Deck 7: Non-Parametric Models

Question 1

In a study investigating whether there is a difference in age at diagnosis of type 2 diabetes for young adult males and females, the result obtained for a two-tailed probability is U =3, p = .09 ( HYPERLINK "http://mlsc.lboro.ac.uk/resources/statistics/Mannwhitney.pdf" http://mlsc.lboro.ac.uk/resources/statistics/Mannwhitney.pdf). What does this result signify?

A) Indeterminate result
B) No real evidence that age at diagnosis is different for young males and females
C) Significant and therefore there is evidence of a difference in age at diagnosis
D) None of the above

Answer 1

No real evidence that age at diagnosis is different for young males and females

Question 2

Which of the following tests does not constitute an alternative to the Mann-Whitney test?

A) Kolmogorov-Smirnov Z
B) Kruskal-Wallis
C) Moses extreme reactions
D) Wald-Wolfowitz runs

Answer 2

Kruskal-Wallis

Question 3

A psychologist was interested in whether there was a gender difference in the use of email. She hypothesized that because women are generally better communicators than men, they would spend longer using email than their male counterparts. To test this hypothesis, the researcher sat by the email computers in her research methods laboratory and when someone started using email, she noted whether they were male or female and then timed how long they spent using email (in minutes). How should she analyse the differences in males and females? (Use the output below to help you decide.)

A) Paired t-test
B) Mann-Whitney test
C) Wilcoxon signed-rank test
D) Independent t-test

Answer 3

Mann-Whitney test

Question 4

The non-parametric equivalent of the one-way between-measures ANOVA is

A) Mann-Whitney test
B) Wilcoxon sign test
C) Friedman test
D) Kruskal-Wallis test

Question 5

The non-parametric equivalent of the one-way repeated-measures ANOVA is

A) Mann-Whitney test
B) Wilcoxon sign test
C) Friedman test
D) Kruskal-Wallis test

Question 6

Ten visitors to an art gallery are asked to rate a Van Gogh painting alongside a sculpture each by Henry Moore and Michelangelo. What test would be used to see if there is a significant difference in ratings amongst the three pieces?

A) Mann-Whitney test
B) Signed-rank test
C) Friedman test
D) Kruskal-Wallis test

Question 7

What might be a reason to choose parametric tests over non-parametric tests even if some parametric assumptions are violated?

A) Non-parametric tests are harder to carry out.
B) Non-parametric tests are less powerful.
C) Parametric tests are less robust.
D) Parametric tests are more likely to show causal effects.

Question 8

When would the Jonckheere-Terpstra test be used?

A) When the Kruskal-Wallis test returns an insignificant result.
B) When comparing large numbers of groups.
C) When the groups being compared are expected to produce a meaningful order of median values.
D) None of the above.

Question 9

Another term for non-parametric tests is

A) Non-normal tests
B) Data-free tests
C) Non-continuous tests
D) Distribution-free tests

Question 10

Which of the following tests allows for comparing several conditions?

A) Wilcoxon signed-rank test
B) Mann-Whitney test
C) Kruskal-Wallis test
D) Wilcoxon rank-sum test

Question 11

Look at the outputs below obtained from running Friedman's ANOVA on data relating to the use of three different drugs on groups of patients. What does this information mean? Ranks
Test Statistic^{a
a Friedman Test}
Http://www.statsguides.bham.ac.uk/TSQ/TSQ4/np/Q1.htm

A) There are differences between each drug used and there are no sampling errors.
B) There are no differences between each drug used and there are no sampling errors.
C) There are differences between each drug used and significant sampling errors.
D) None of the above.

Question 12

Ten visitors to an art gallery are asked to rate two sculptures for aesthetic value on a scale of 1(low value) to 5 (high value).The results are as follows. What conclusion would be drawn? Test Statistics(b)

A. Based on positive ranks.

A) There is a significant difference in ratings, with the Henry Moore piece being rated higher than the Michelangelo piece.
B) There is no significant difference in ratings.
C) There is a significant difference in ratings, with the Henry Moore piece being rated lower than the Michelangelo piece.
D) Not enough information.

Question 13

Which of the following is not a condition for using non-parametric tests?

A) When one or more variables (including the dependent variable) is measured on either a nominal or ordinal scale
B) When the sample is normally distributed
C) When one or more variables in the data set (including the dependent variable) violates the normality assumption
D) When the sample size is small (less than 20 cases)

Question 14

If the null hypothesis is true and we run the Mann-Whitney test on data, the expectation is that the _____ in the two groups will be approximately equal.

A) means
B) ranks
C) variances
D) mean ranks

Question 15

The non-parametric equivalent of the paired-samples t-test is the

A) Mann-Whitney test
B) Signed-rank test
C) Friedman test
D) Kruskal-Wallis test

Question 16

A researcher was interested in stress levels of lecturers during lectures. She took the same group of eight lecturers and measured their anxiety (out of 15) during a normal lecture and again in a lecture in which she had paid students to be disruptive and misbehave. The data were not normally distributed. Which test should she use to compare her experimental conditions?

A) Paired t-test
B) Mann-Whitney test
C) Wilcoxon signed-rank test
D) Wilcoxon rank-sum test

Question 17

In an experiment involving cholesterol levels in type A and type B men (http://www.sjsu.edu/faculty/gerstman/EpiInfo/cont-two.htm), the following data output was reported for a Kruskal-Wallis test Chi Square 6.333
Df 1
Asymp. Sig 0.01185
What does this result suggest?

A) There is a significant difference between the two groups, p = .011853.
B) There is no significant difference between the groups, p > .05.
C) There is no significant difference between the groups, p = .011853.
D) None of the above.

Question 18

What would this result be if a one-tailed probability were required?

A) .045
B) .45
C) .09
D) None of the above

Question 19

The non-parametric equivalent of the two-sample independent t-test is the

A) Mann-Whitney test
B) Wilcoxon sign test
C) Friedman test
D) Kruskal-Wallis test

Question 20

Ten visitors to an art gallery are asked to rate two sculptures for aesthetic value on a scale of 1(low value) to 5 (high value) What procedure would be used to test the hypothesis that the ratings are not significantly different?

A) Mann-Whitney test
B) Signed-rank test
C) Friedman test
D) Kruskal-Wallis test