Advanced Sampling Methods

Advanced sampling methods

Course Leader

Rosanna Verde

Target Group

Junior or senior staff of methodology divisions using sample survey techniques in the production of statistics.

Entry Qualifications

Good knowledge of basic sampling techniques and survey methodology.

Objective(s)

This course aims to equip participants with advanced knowledge and practical skills in survey sampling methodologies, with a particular focus on applications in official statistics. Some of the theory will be illustrated by examples and some exercises will follow. The course starts with an introduction to the R software which will allow the participants to better understand the practical applications of these survey techniques and implement them successfully in practice.

By the end of the course, participants will be able to:

• Distinguish between probability and non-probability sampling methods and apply suitable strategies for non-probability samples. 

• Design sampling strategies for rare populations, including the use of adaptive and cluster sampling techniques. 

• Understand and implement implicit and explicit stratification in complex survey designs. 

• Combine samples from multiple frames and address challenges in multiple-frame sampling. 

• Apply adaptive sampling designs and adjust survey strategies based on observed data. 

• Implement oversampling techniques in official statistics, ensuring unbiased estimation through proper weighting. 

• Apply these advanced sampling methods using R and Python through practical examples. 

Contents

• Introduction to the R software (lecture + practicals) 

• Non-response (lecture)

• Calibration (lecture + practicals)

• Variance estimation (lecture + practicals)

• Sample coordination techniques (lecture + practicals) 

Expected Outcome

At the end of the course participants are expected to have a deeper understanding of the techniques they have learned and be able to apply successfully the new methodology in their daily practice.

Training Methods

The course is based mainly on lectures, which for all the courses except for Non-response, will be followed by practical exercises on PC using the R software.

Required Reading 

• Särndall C.E., Swensson B. and Wretman J. (1992). Model Assisted

     Survey Sampling. PART I: Principles of Estimation for Finite

• Populations and Important Sampling Designs (Chapters 1 to 5)

Suggested Reading

• Thompson, S. K. (1990). Adaptive cluster sampling. Journal of the American Statistical Association, 85(412), 1050-1059.

• Thompson, S. K. (1991). Stratified adaptive cluster sampling. Biometrika, 78(2), 389-397

• Sixia Chen, Graham Kalton, Geographic Oversampling for Race/Ethnicity Using Data from the 2010 U.S. Population Census, Journal of Survey Statistics and Methodology, Volume 3, Issue 4, December 2015, Pages 543–565, https://doi.org/10.1093/jssam/smv023

• Roger Vaughan, 2017: Oversampling in Health Surveys: Why, When, and How? American Journal of Public Health 107, 1214_1215, https://doi.org/10.2105/AJPH.2017.303895

Required Preparation

None

Trainer(s)/
Lecturer(s)

Rosanna Verde (Independent expert)

Antonio Balzanella (Independent expert)