International Program in Survey and Data Science
  1. Home
  2. IPSDS
  3. Courses
  4. All
  5. Step by Step in Survey Weighting

SURV748: Step by Step in Survey Weighting

Area: 
Data Analysis, Data Curation/Storage
Credit(s)/ECTS: 
1/2
Core/Elective: 
Elective

Apply through UMD

Instructor: Anna-Carolina Haensch

This course and the textbook give students the necessary tools to calculate analysis weights for various survey designs in a real-world setting. We will cover topics on calculating base weights for single- and multistage designs, adjusting weights for unknown study eligibility and nonresponse using a few techniques, and aligning survey estimates with known population values through weight calibration.

We will use specialized software for the procedures mentioned. This course will emphasize R but some examples in SAS and Stata are also discussed. R is downloaded for free from http://cran.r-project.org/. Students may also find https://www.rstudio.com/ a helpful interface to execute program code. For those new to R, there are many MarinStatsLectures available at https://www.youtube .com/playlist?list=PLqzoL9-eJTNBDdKgJgJzaQcY6OXmsXAHU

There will be homework problems each week for students to gain practice using all methods covered in the course. The emphasis will be on using the methods to solve practical problems; we review theory as needed for a clear understanding of the underlying assumptions. All are encouraged to discuss their own weighting challenges and solutions during our weekly online meetings.

Course objectives: 

By the end of the course, students will understand:

  • Role of survey weights in population inference.
  • Steps in weighting, including computation of base weights, nonresponse adjustments, and uses of auxiliary data.
  • Nonresponse adjustment alternatives, including weighting cell adjustments, formation of cells using classification algorithms, and propensity score adjustments.
  • Weighting via poststratification, raking, general regression estimation, and other types of calibration.
  • Assessing if weights are not needed.
Grading: 

Grading will based on

  • 4 Homework assignments (60% of grade)
  • A take-home final exam (30% of grade)
  • Class Participation (10% of grade) in discussion during the weekly online meetings and posting questions to the weekly forum (deadline: 24 hours before class) demonstrating understanding of the required readings and video lectures
Prerequisites: 

Sampling theory, Applied Sampling (e.g., SURV626 Sampling I), or Practical Tools for Sampling.

Some experience with variance estimation, statistical analysis using survey data, and the R statistical computing software will be  helpful.

Readings:

Valliant, R., Dever, J.A., and Kreuter, F. (2018). Practical Tools for Designing and Weighting Survey Samples, 2nd Edition. New York: Springer.

Weekly online meetings & assignments:

  • Week 1: Basic Steps in Weighting (Homework 1)
  • Week 2: Basic Steps in Weighting (continued) (Homework 2)
  • Week 3: Calibration and Other Uses of Auxiliary Data in Weighting (Homework 3) 
  • Week 4: Calibration (continued) and Replicate Weights (Homework 4)
  • Final exam 

Course Dates

2019

Fall Semester (September – December)

2021

Fall Semester (September – December)