Correlation

These flashcards cover key concepts related to correlation analysis, including its definitions, types, statistical significance, and limitations.

Correlation Analysis

The degree to which changes in one variable are associated with changes in another.

Bivariate

Involving two variables.

Pearson correlation

A type of correlation analysis used when both variables are interval and/or ratio.

Spearman correlation

A type of correlation analysis used when at least one variable is ordinal.

Correlation coefficient (r)

A test statistic ranging from -1 to +1 indicating the strength and direction of a relationship between two variables.

p-value

A statistical measure that indicates whether the correlation between two variables is statistically significant.

Statistically related (p<.05)

Indicates that there is a statistically significant relationship between the two numeric variables.

Weak correlation

An r value less than 0.3 (either positive or negative).

Moderate correlation

An r value between 0.3 and 0.7 (either positive or negative).

Strong correlation

An r value greater than 0.7 (either positive or negative).

Regression analysis

An analysis method that examines the relationship between a dependent measure and a predictor.

T-test

A statistical test used to compare the means between two groups.

Correlation Does NOT Prove Causation

The principle stating that correlation between two variables does not imply that one causes the other.

Limitations of Correlation Analysis

Correlation can only examine the relationship between two variables and does not measure the degree of change of one variable due to another.

The best approach for communicating the importance of each independent variable in the regression model?

Using simulations to demonstrate the effects on the dependent variable

In a one-variable regression model, the intercept is

the value of the dependent variable when the independent variable = 0

In building a regression model explaining cups of coffee consumed per day, we are evaluating multicollinearity because

If 2 or more independent variables are highly correlated then the coefficient estimates for those variables becomes unreliable