Statistics 1770 Lecture : October 4.docx
Document Summary
Summarizing strength of association: where possible, add a numerical summary of the association, linear relationships, reasonably simple and quite common, data may fall close to the straight line, or may be quite variable around straight line trend quantitative variables, x and y. Correlation( r) summarizes the strength of the linear relationships between two: positive relationship both products in () are going to be positive, negative relationship one product in () will be negative. Properties of correlation (r: r takes values between +1 and 1, positive correlation means positive association, negative correlation means negative association, correlation is unit free; value does not depend on units of measurement, correlation does not depend upon which variable is explanatory and which is response, correlation only measures strength of linear relationship, correlation is not resistant to outliers, on average, 50% of marijuana use has approx.
