Lecture 5

Correlation: we analyze linear relationship between two variables, we cannot draw casual conclusions. Not used when the relationships between two variables are curvilinear.

Covariance: the simplest measure of the relationship between two variables. Carries the most basic info about what happens with the deviation from the mean of one variable when the deviation changes in the case of another variable. Only direction of the relationship, not the strength.

Positive covariance: two variables tend to increase or decrease together.

Negative covariance: one variable tends to increase when the other decreases.

Pearson correlation: informs us about direction and strength of the relationship. We look at absolute value, ignoring minus sign. 0 and -.0.3 weak, 0.31 and -0.5 moderate, 0.51 and -0.7 strong, 0.71 and - 1 very strong.

Positive correlation: as variable X increases, variable increases (the more I read the more I know).

Negative correlation: as variable x increases, variable Y decreases (the more I run the less I weigh).

The fact that two variable are correlated: does not mean that one variable causes or influences another.

Assumptions of Pearson’s r: linear relationships, quantitative scales of the variables, normal distribution of both correlated variables.

Non directional hypothesis: there is no relationship between something.

Directional: there is no positive relationship between something.