You are here

Applied Regression Analysis

Summer 2013 MBA Course

B8831-001: Applied Regression Analysis

T - A Term, 09:00AM to 01:15PM
Location: URI 326

Instructor: David Juran

This half-semester course is designed for students who wish to increase their capability to build statistical models for business. It is also appropriate for students who exempt out of B6014 but want to strengthen their statistical skills.

The course builds on the statistical background gained from B6014, the core course in managerial statistics. The goal of the course is to enable students to build and evaluate statistical models for managerial use in finance, operations and marketing. The focus is on generating managerially useful information and practical decision-making tools, rather than on statistical theory per se. A number of actual business cases are studied. Concepts covered are multiple linear regression models and the computer-assisted methods for building them, including stepwise regression and all subsets regression. Emphasis is placed on diagnostic and graphical methods for testing the validity and reliability of regression models. Course topics include interpretation of the analysis of variance tables, multicolinearity and its causes and cures, the use of dummy (indicator) variables, and logistic regression for binary dependent variables.

The course studies applications of regression to business forecasting and also examines alternative times series forecasting models, including exponential smoothing.

Term project: A major aspect of course is the opportunity to carry out a practical statistical analysis project of one’s own. Students work in teams of two or three on a problem of their own choosing or on a project presented by the professor. The goal of the project is to develop a useful statistical model for a specific business problem. The professor provides ongoing guidance and advice during the course of project. The teams give an oral presentation of their results at the term’s end.

Excel is used for basic statistical analysis as well as for developing straightforward regression models. In addition, more advanced commercial statistical software, such as Minitab or SAS, is used to carry out more complex and advanced analyses. In addition to the term project, here is one quiz and some computer-based homework.

View video introduction.