Chapter 8: Bivariate Correlational Research

Question 1

Bivariate Correlations

Answer 1

Associations that involve exactly two variables

E.g., Level of happiness & days spent on vacation

Question 2

Cohen’s Guidelines

Answer 2

• r has two qualities: direction and strength
• Direction refers to whether the assoication is positive, negative or zero
• Strength refers to how closely related the two variables are (close to 1 or to -1)

Guideline:
.10 (or -.10) = small/weak
.30 (or -.30) = medium/moderate
.50 (or -.50) = large/strong

Question 3

T - test

Answer 3

A statitistic to test the difference between two group averages

Question 4

Effect Size

Answer 4

Describes the strength of an association

Question 5

Effect Size, Sample and Significance

Answer 5

• Statistical significance is related to effect size; usually, the stronger a correlation, the more likely it will be statistically significant
• Have to look for the p values association as long size with the effect size
• Statistical significance calculations depend not only on the effect size but also on sample size
• A very small effect size will be statistically significant if it is identified in a very large sample
• A small sample is more affected by chance events than a large sample is. Therefore, a weak correlations based on a small sample is more likely to be the result of chance variation and is more likely to be judged “not significant”

Question 6

Outliers

Answer 6

• Extreme scores are more likely to effect the outliers
• It changes the slope of the line - Makes a correction stronger than what it suppose to be
• Problematic if there is a small sample (can effect the results and less likley to find a significant. Thye may exert disproportiante infleunce)
• Have a large impact on the direction or strength of the correlation

Question 7

Restriction of Range

Answer 7

• Another issue to consider when it comes to outliers
• You not looking at the full range, that it can make correlation appear smaller than it really is
• Will have an impact on strength with the correlation
• Slope tends to be steeper
• Scatter plot is a good way to find the restriction of range
• It can be applied when one of the variables has very little variance
• Because restriction of range makes correlations appear smaller, but ask about it when the correlation is weak

Question 8

Curvilinear

Answer 8

• Pearson r looks at linear correlation and when you have curvilinear it will give you an inaccurate estimate
• Underestimate or just no relationship when using the pearson r
• Tend to be a weak correlation
• Curvilinear association in which the relationship between two variables is not a straight line; it might be positive up to a point, and then become negative

Question 9

Moderating Variables

Answer 9

• Setting is moderating the variable (Is positive but it depedends on the seeting)
• You not changing the association but making it stronger
• Is wehn the relationship between two variables changes depedning on the level of another variable
• It can inform external validity
• It does not generalize