Applications of Linear Regression and Other Statistical Tools in the Study of Alcohol Sales

Abstract

This study uses linear regression to model the relationship of alcohol sales as a function of economic and social variables. Data were obtained on the whole U.S. for this study's dependent variable of alcohol sales and independent variables of unemployment rate, personal consumption expenditures, consumer price index, population, and high school graduation rate. For the purposes of developing a reliable regression model, this study focuses on satisfying the seven classical assumptions of ordinary least squares regression. The results of this study show a statistically significant positive relationship between alcohol sales and the variables of unemployment rate, personal consumption expenditures, and high school graduation rate.