This course covers a set of quantitative research methods considered to be important for both marketing researchers and practitioners. Such methods include classical techniques like market response modeling, binary logit/probit and discrete choice models as well as contemporary data science methods from the field of data mining and artificial intelligence focusing on market basket analysis, recommender systems and classification systems for marketing applications.

The course builds on the content already covered in the "Marketing Research Design and Analysis", but expands them along two dimensions: (1) The conceptual and statistical assumptions underlying methods discussed in previous classes are challenged and the portfolio of available data analytical methods is extended. (2) The course offers opportunities to train the application of these methods in various marketing decision making contexts and to derive managerial conclusions.

The emphasis in this course is on a more thorough understanding of marketing research techniques and to demonstrate why extensions of standard models are necessary and useful in specific marketing environments.

By the end of this course, students will be able to:

• Be comfortable with R and RStudio
• Understand the assumptions, limitations and possible extensions of standard marketing research methods
• Integrate the components discussed in this course into the topics covered in the basic marketing research course
• Understand the practical importance and relevance of the discussed methods in real-world marketing decision making contexts
• Familiarize themselves with suitable the statistical programming language R to analyze marketing data sets and to interpret the results
• Further improve their presentation and team working skills

Full attendance is compulsory. This means that students should attend at least 80% of all lectures, at most one lecture can be missed.

The course is taught using a mix of interactive lectures, business cases, class discussions, computer exercises, and student presentations. The structure of this course is organized in three parts:

The first part is an introduction to programming with the statistical programming language R. No prior knowledge of computer programming is required nor assumed.

The second part contains sessions on various quantitative research methods. While in the first half of each session we will discuss the conceptual idea, the statistical properties, and interpretative aspects of the focused method, the second half  trains students to use and apply the presented method to a marketing related data assignment. The data assignments will be  homework as well as in-class assignments.

The third part builds on the introductory sessions but is organized in breakout groups. Each group of students will work on a course project mimicking a real-world marketing research issue using the concepts and methods learned throughout the program. The findings will be presented in a final presentation session.

Grading of this course is based on the following components:

• 15% programming with R 
• 40% in-class participation and data case/home assignments
• 25% course project
• 20% final presentations

The assessment of the homework assignments and course project will be based on the correctness of results, the clarity and persuasiveness of each bit of work and the recognizable effort made. This implies an ability to work in teams.

Successful completion of the course "Marketing Research and Data Analysis" is a prerequisite to attend this course.