Week 5 (Correlation, Nonparametric tests, Nonparametric Analysis for Relationships/Associations)

Question 1

Factors are seen as what in exploratory and observational research?

Answer 1

Exposures

Question 2

Conditions are seen as what in exploratory and observational research?

Answer 2

Outcome

Question 3

Longitudinal studies are studies that are…

Answer 3

overtime

Question 4

What are the 2 types of longitudinal studies?

Answer 4

Prospective and retrospective

Question 5

prospective longitudinal studies

Answer 5

into the future

Question 6

Retrospective longitudinal studies

Answer 6

into the past

Question 7

Cross-sectional studies are studies that are…

Answer 7

a “snapshot”

Question 8

Correlation can be shown using…

Answer 8

scatter plots, pairs of scores

Question 9

How do you know the strength of the correlation?

Answer 9

values between -1.0 and 1
- “0” is no relationship
- 1.0 = perfect positive relationship
- -1.0 = perfect negative relationship

Question 10

what does the ‘sign’ imply on the correlation?

Answer 10

sign implies direction of the relationship

Question 11

Assumptions of correlation

Answer 11

• scores represent the underlying population
• scores are normally distributed
• each subject has a score for both X and Y
• X and Y are independent measures
• X and Y are observed, not controlled
• relationship between X and Y is linear

Question 12

Correlation coefficient: <= .25

Answer 12

little or no relationship

Question 13

Correlation coefficient: .25 to .50

Answer 13

low to fair

Question 14

Correlation coefficient: .50 to .75

Answer 14

moderate to good

Question 15

Correlation coefficient: >= .75

Answer 15

strong relationship

Question 16

limitations of correlations

Answer 16

• relationship between 2 variables only
• only quantifies linear relationships
• does not tell us “cause and effect”
• does not account for agreement
• range of observations

Question 17

Coefficient of Determination (r^2)

Answer 17

• coefficient of determination
  -“the percent of variance in y that is explained by x”

Question 18

the coefficient is very sensitive to…

Answer 18

sample size

Question 19

Small effect size for r

Answer 19

r = .10

Question 20

medium effect size for r

Answer 20

r = .30

Question 21

large effect size for r

Answer 21

r = .50

Question 22

non-parametric statistics are based on:

Answer 22

• comparisons of ranks of scores
• comparisons of counts (yes/no) or “signs” of scores

Question 23

data can be “collapsed” from Ratio to…

Answer 23

ordinal/nominal

Question 24

advantages of nonparametric methods

Answer 24

• appropriate for a wide range of situations
• can use with categorical data
• simple computations
• outliers have LESS effect

Question 25

Disadvantages of Nonparametric Methods

Answer 25

- they waste information - less power (65-95%; increase sample size) - if outliers are not errors, effects may be underestimated

Question 26

nonparametric test for: 2 independent groups

Answer 26

- Mann-Whitney U (BEST) - wilcoxon rank sum test

Question 27

nonparametric test for: >= 3 independent groups

Answer 27

Kruskal-Wallis ANOVA by ranks

Question 28

nonparametric test for: two related samples

Answer 28

- Sign test - Wilcoxon Signed-ranks test**

Question 29

nonparametric test for: >=3 related samples

Answer 29

Friedman two-way ANOVA

Question 30

Non-parametric analog of Pearson r

Answer 30

- 1 continuous, 1 ordinal variable - 2 ordinal variables - non-normal distribution of ratio/interval data

Question 31

Chi-square (x^2)

Answer 31

- measures association between 2 categorical variables - tests the difference between observed frequencies (O) and frequencies expected by chance (E)

Question 32

what are the 2 types of Chi-square (x^2)

Answer 32

goodness of fit tests of independence (association)

Question 33

what is goodness of fit?

Answer 33

- coin flip - compare observed frequencies of 1 variable to uniform frequencies of another - with enough tests will end up being 50/50

Question 34

what is tests of independence (association)?

Answer 34

- much more common - compare observed frequencies from 1 variable to observed frequencies of another variable - ex: male or female?

Question 35

assumptions of chi-square

Answer 35

- frequencies represent individual counts - categories are exhaustive and mutually exclusive - no subject is represented twice

Question 36

Most common application of chi-square is...

Answer 36

test of independence