Chapter 10: Correlation and Regression

Students begin by constructing and interpreting scatterplots, which provide visual representations of paired data and allow for preliminary identification of linear patterns, strength of association, and direction of relationship. The Pearson correlation coefficient, denoted as r, serves as the foundational measure for quantifying the strength and direction of linear association between variables, with detailed attention given to its calculation, proper interpretation across the range from negative one to positive one, and assessment of statistical significance through hypothesis testing. Critical limitations receive substantial emphasis, including the fundamental principle that correlation does not establish causation, the distorting effects of outliers and extreme values on the correlation coefficient, and the importance of examining scatterplots alongside numerical summaries. Regression analysis extends this framework by developing the equation of the best-fit line, calculated through the least-squares method, which minimizes the sum of squared vertical deviations from predicted values. Students learn to interpret the slope as the predicted change in the dependent variable for each unit increase in the independent variable and to understand the y-intercept within appropriate contexts. The coefficient of determination, r squared, quantifies the proportion of variability in the response variable that the regression model explains. The chapter addresses residuals, which measure discrepancies between observed and predicted values, and teaches identification of outliers and influential points that disproportionately affect the regression line. Students also learn prediction techniques using the regression equation while understanding the critical dangers of extrapolation beyond the range of observed data. Throughout, technological tools facilitate computation and hypothesis testing, enabling students to apply these methods to real-world problems in fields including business, health sciences, and social research.