Statistical Methods for Sample Surveys

Spring 2009

Photo by Argos Panoptes via flickr.com. Creative Commons BY-NC-ND.

Description

Presents construction of sampling frames, area sampling, methods of estimation, stratified sampling, subsampling, and sampling methods for surveys of human populations. Students use STATA or another comparable package to implement designs and analyses of survey data.

Syllabus

Course Description

Presents construction of sampling frames, area sampling, methods of estimation, stratified sampling, subsampling, and sampling methods for surveys of human populations. Students use STATA or another comparable package to implement designs and analyses of survey data.

Course Objectives

Upon successfully completing this course, students will be able to: 1) design and implement surveys with the following sampling designs: simple random, systematic, stratified, cluster and multistage; 2) estimate sample size for different sampling designs in order to estimate population level point estimates and testing null hypothesis; 3) explain and apply intraclass correlation and design-effects (DEFF) for complex surveys; 4) estimate design weights and adjust for non-response.

Prerequisites

Statistical Methods in Public Health II or Methods in Biostatistics II

Readings

United Nations Department of Economic and Social Affairs: Designing Household Survey Samples. United Nations, 2005.

Levy PS, Lemeshow S: Sampling of Populations: Methods and Applications, 3rd edition. New York: Wiley Interscience, 1999. - Optional

Lohr SL: Sampling: Design and Analysis. Duxbury Press, 2009. - Optional

Course Requirements

Laboratory Exercises - 60%

Final Project - 40%

Schedule