Multiple Imputation - Why and How

You are here: Executive Education » Open Courses » Data Science

This Page

Multiple Imputation - Why and How - Course Details

Delve into the course contents and find out about the faculty members.

Single Course Price:

400.00 EUR (tax exempt)

 

Instructor:

Prof. Jörg Drechsler (Institute for Employment Research)

Video lecture:

Prof. Jörg Drechsler (Institute for Employment Research)

 

Course Dates

To see all courses in the upcoming term click here.

 

This course is part of the Mannheim Data Science Certificate: Item Nonresponse & Multiple Imputation.

Book this course or the entire certificate here!

In order to book the course with alumni conditions, please get in touch with Manon Pfeifer directly.

Course Description

Short Course Description
This course will provide a detailed introduction to multiple imputation, a convenient strategy for dealing with (item) nonresponse in surveys. We will motivate the concept and illustrate why multiple imputation should generally be preferred over single imputation methods. The main focus of the course will be on strategies to generate (multiple) imputations and how to deal with common problems when applying the methods for large scale surveys. We will also discuss various options for assessing the quality of the imputations. All concepts will be demonstrated using software illustrations in R.

Prerequisites
Students should be familiar with generalized linear models and basic probability theory. We also expect that students know the basic concepts for dealing with nonresponse in surveys (the difference between item and unit nonresponse, formalizing the missing data mechanism, deterministic and stochastic approaches for imputation). For students unfamiliar with these concepts we highly recommend to enroll in the course “Nonresponse and Imputation” before participating in this course.
Some background knowledge in Bayesian statistics and Markov Chain Monte Carlo Methods (MCMC) is helpful but not mandatory. The statistical software R will be used for illustrations and for (some of) the homework assignments. Thus, basic knowledge of R is required to be able to complete the assignments.

Course Objectives
By the end of the course, students will…

  • understand why multiple imputation should be preferred over single imputation methods in most situations
  • know about the two main approaches for multiple imputation
  • be familiar with various imputation routines for different types of variables
  • know how to implement these routines using R
  • be able to deal with various problems that typically arise when imputing large scale surveys
  • know about various strategies to assess the quality of the generated imputations

Course Composition
This is a 2 ECTS course, which runs for 4 weeks. The content of the course is broken down into 4 units:

  1. MI Intro & MI Analysis
  2. MI for Continuous Variables
  3. MI for Categorical Variables and Nonparametric Alternatives
  4. Modeling Strategies and Quality Evaluations

Learning and Teaching Methods
In this course, you are responsible for watching video recorded lectures and reading the required literature for each unit and then “attending” mandatory weekly one-hour online meetings where students have the chance to discuss the materials from a unit with the instructor. In addition, students are encouraged to post questions about the materials covered in the videos and readings of the week in the forum before the meetings. Just like in an on-site course, homework will be assigned and graded and there will be a final exam at the end of the course.

Grading
Grading will be based on:

  • 2 online quizzes (worth 20% total)
  • 2 homework assignments (worth 40% total)
  • Participation in the weekly online meetings, engagement in discussions during the meetings and/or submission of questions via e-mail (worth 10%)
  • A final online exam (worth 30%)

ZFU Certification and Online Dispute Resolution

ZFU Certification

The Mannheim Master of Applied Data Science & Measurement program is certified according to the regulations of the ZFU (Staatliche Zentralstelle für Fernunterricht).

 

Online Dispute Resolution

Online dispute resolution according to Art. 14 Sect. 1 ODR-VO: The European Commission provides a platform for online dispute resolution (ODR). You can find more information under http://ec.europa.eu/consumers/odr/

MANNHEIM BUSINESS SCHOOL (MBS)

Located in the heart of the German and European economy, Mannheim Business School (MBS), the umbrella organization for management education at the University of Mannheim, is considered to be one of the leading institutions of its kind in Germany and is continuously ranked as Germany’s #1.

SOCIAL MEDIA NEWS WALL