# DECS 434 Waiver Information

Course Title:
Statistical Methods for Managerial Decisions

Course Description:
This course introduces to students the regression, a powerful statistical techniques used to understand the relationship between variables of interest. For example, how does demand depend on price and seasonality? How does the success of merger depend on the characteristics of the firms being merged? Topics include one- and two-population hypothesis testing, correlation, simple and multiple regression analysis, and qualitative variables. The course also covers applications of the material and a number of case studies. Extensive use of STATA software is required.

Student who have taken DECS 445-0 are waived from taking DECS 434.

Waiving DECS-434 completely:

Every student (whatever their prior education and experience) may take the waiver exam. Only students who have a good understanding of the topics listed below, however, are encouraged to take a waiver exam. In particular, a student will only be successful in passing the waiver exam if all of the following keywords are familiar to him/her: hypothesis testing, confidence intervals, linear regression, log-regression, multicollinearity, omitted variable bias, heteroskedasticity, dummy variables, and slope-dummy variables (variables which are products of one variable and a dummy-variable). Here is a more precise list of topics a student should be familiar with for a waiver examination:

1. Hypothesis testing and interval estimation of the difference between two means or proportions.

2. Basic linear regression model and assumptions; both simple and multiple regression.

3. Evaluating and interpreting regression output generated by a computer package; the ability to relate regression output to a particular problem or setting.

4. Goodness-of-fit (R-squared and adjusted R-squared), prediction, interval estimation (both confidence and prediction intervals) and hypothesis testing (t-tests, F-tests, Generalized F-tests, p-values, etc.) in the framework of the regression model.

5. Use interpretation of regression diagnostics/residual analysis to check if regression assumptions are satisfied.

6. The consequences if various regression model assumptions are violated; how to remedy violations of the regression assumptions.

7. How to introduce and use slope- and intercept-dummy (qualitative) variables; how to recognize and analyze omitted variable bias; how to diagnose and remedy multicollinearity, when and how to use a LOGIT regression.

8. The ability to apply the above techniques in management settings, such as using regression to evaluate the riskiness of an asset within the Capital Asset Pricing Model; to evaluate the impact of advertising; as an aid to managerial decision making.