Syllabus for Advance Business Analytics

MGMT 672F

Advanced Business Analytics

Module 3 2017

Professor Robert Plante

OBJECTIVE

        The objective of this course is to familiarize you with analytical models and statistical software (SAS and Minitab) that are used frequently in decision making and in empirical study.  The focus of the course is on the appropriate means of applying these analytical methods to aid in arriving at decisions.  Underlying theoretical concepts are brought forward and demonstrated to understand important methodology.  Students are expected to have completed MGMT 670 or equivalent as a prerequisite (basic statistics up through Multiple Regression). The materials in this course are intended to have some initial overlap with the content of 670. The overlap will be used to both review fundamental concepts of General Linear Models (Multiple Regression) and introduce you to the analytical software system SAS.

        While there are a multitude of advanced linear models concepts, this course will focus on predictive model building using (1) Multiple Regression Analysis, (2) Independent Indicator Variables (ANOVA, ANCOVA, Blocking Designs, Factorial Designs, Piecewise Linear Regression, and Splines), and (3) Forecasting and Time Series Models (Autoregressive, Moving Average, ARIMA and Cross-Correlation models).

TOPICS TO BE COVERED

1.        Multiple Regression

Simple and Multiple linear regression topics will be covered. These techniques are used to assess the influence of a set of variables on a single response variable. Concepts such as multicollinearity, partitioning of variation and model building will be covered. It is assumed that students already have a background in this area. Your familiarity with this concept will be used to introduce SAS procedural programming, which is the main analytical software that will be used throughout the course.

2.        Analysis of Variance (ANOVA): A Regression Approach

        Techniques such as design of controlled experiments for collecting data and analyzing the factor effects will be introduced.  Techniques such as blocking and analysis of covariance will be covered.

3.        Qualitative Independent Variables

        The techniques associated with the use of dummy or indicator variables are introduced.  Interaction effects involving dummy variables are discussed.  Piecewise linear regression models are introduced, as well as the concept of splines.