ECOR 1010 Lecture 14: Lectures 14 15 Summary Correlation and Regression Page 1
Document Summary
Before studied univariate statistics with just one variable. Bivariate statistics are used for two variables which come in pairs. Correlation: want to know if there is a relationship between variables x and y and how strong it is. Just because two variables are correlated does not mean there is any connection between them. Regression: want to know if we can predict the y"s from the x"s. Correlation measures strength of relationship (how correlated are variables?) The correlation coefficient conveys how good the assumption of a straight line of relationship exists between data.