Master's Programme in Mathematics and Statistics is responsible for the course.
The course belongs to the Statistics and Social statistics module.
The course is available to students from other degree programmes.
Student gets knowledge on approaches, methods and computational tools needed in the analysis of complex surveys and is able to apply the selected methods in typical real-world analysis situations.
Recommended time/stage of studies for completion: 1. or 2. year
Term/teaching period when the course will be offered: varying
The course covers topics in the analysis of complex survey data where the complexity arises from the complex (multi-stage) cluster sampling design. Complex sampling designs involve correlation between observations within clusters. Methods are needed that properly account for the complexities in the analysis phase. Methods covered include variance estimation by linearization, jackknife and bootstrap, design-based Wald tests of independence and homogeneity, linear and logistic regression and ANCOVA, and linear mixed modelling. Methods are applied with SAS and R tools to complex survey data collected by stratified cluster sampling.
Lehtonen R. and Pahkinen E. (2004) Practical Methods for Design and Analysis of Complex Surveys. 2nd Edition. Wiley.; Lohr S.L. (2010) Sampling: Design and Analysis, 2nd Edition. Brooks/Cole.
Lectures and exercise classes
Exam and written assignment, Course will be graded with grades 1-5
Exam and written assignment