4508137: C15 Business Statistics II

Description

This course generalizes the concepts of simple linear regression discussed in Business Statistics I to the case of multiple linear regression.

Topics
> Classical linear model assumptions
> Parameter estimation in multiple linear regression
> Model diagnostics
> Inference in multiple linear regression
> Model specification techniques
> Model selection techniques Introduction to the software package R

Learning Outcomes

Students explain the classical linear model assumptions, run multiple linear regressions, check the diagnostics plots and interpret the results correctly. Students apply inference procedures in multiple linear regression models and compare the advantages and disadvantages of different inference procedures. Students apply specification techniques to improve the quality of models and interpret such models correctly. Students apply selection techniques to choose appropriate models.

Lectures Method

The e-learning platform Moodle will be used throughout the course for the dissemination of course material and discussions. Students are usually asked in advance to read corresponding parts of the lecture notes or of the textbook in order to prepare for the upcoming lectures. In the interactive lectures, statistical concepts will be introduced and motivated by discussing examples in detail. Assignments are offered to train these skills. During office hours, individual problems may be discussed with the lecturer. In order to analyse realistic data, the software package R will be used.

Admission Requirements

Recommended previous knowledgeBusiness Statistics I

Literature

Compulsory reading

• Wooldridge, J.M. (2013). Introductory Econometrics. (International Student Edition, 5th edition). Mason: South Western Cengage Learning.

• Montgomery, D.C., Peck, A.E. & Vining, G.G. (2012). Introduction to Linear Regression Analysis. (5th edition). New York: John Wiley & Sons.
• Faraway, J.J. (2014). Linear Models with R. (2nd edition). Boca Raton: Chapman & Hall/CRC.