Correlation Analysis

Question 1

Correlation Analysis

Answer 1

• trying to understand if two sets of data are associated with each other
• data points are close to the line, they are strongly associated
• scale of -1 to 1

Question 2

Pearson Correlation Coefficient

Answer 2

• Measures the degree of LINEAR association b/w two variables
• Positive correlation reflects a tendency for a high variable to be related to another high variable
• Negative correlation reflects a tendency for a high variable to be related to a low variable

Question 3

Population Correlation (p)

Answer 3

• measure based on the population

Question 4

Sample Correlation (r)

Answer 4

• measure based on a sample

Question 5

4 Rules for Interpreting Correlation Coefficients

Answer 5

1. Correlation does not imply causality
2. Correlation can be influenced by the size of the sample
3. Visually examining the scatter plot will tell you more than the correlation coefficient
4. How to determine what a “good” coefficient is

Question 6

The smaller the sample…

Answer 6

the higher chance of creating a meaningless coefficient

Question 7

To create a meaningful coefficient…

Answer 7

• large sample

- variability

Question 8

Linear vs Non-Linear

Answer 8

Pearson’s Correlation Coefficient is for linear associatons

– for non-linear relationships it will show a coefficient close to zero

Question 9

Lack of Equal Variability

Answer 9

• Pearson’s is describing the average strength of the relationship between x and y
• watch for regions of higher/lower variability

Question 10

Discontinuous Distributions

Answer 10

• running analysis without looking at data could create issues when you have outliers
• can lead to misleading correlations

Question 11

Deciding what is a “good” correlation

Answer 11

• build confidence with our “r”

- the larger the r the more likely the correlation coefficient is meaningful