Regression is one of the most widely used statistical techniques. In business, it is often used within the realm of what is known as predictive analytics—estimating the use of statistical techniques to estimate the likelihood or magnitude of future outcomes of interest. However, regression is also an explanatory tool because the regression model explains the variability in dependent variables with the help of one or more independent variables.
From the marketing management perspective, discuss regression as an explanatory and a predictive tool. What are the major differences between an explanatory and a predictive tool? In terms of the goodness of fit, what is the most important indicator of regression as an explanatory tool and as a predictive tool?
Question 2): As a human resources manager, you have been assigned the task of determining how to curtail the high employee turnover rate in your company. You decide to use regression analysis to identify specific factors that have a measurable impact on turnover. Specifically, you are interested in assessing the impact of employee demographics (age, gender, education, etc.) and job-related factors (job type, income, advancement history, length of employment, etc.). However, given the similarity of some of these factors (e.g., education and income or age and length of employment), you are concerned with possible collinearity. How would you determine if collinearity is present in your model? If it is, what would you do to remedy it?