The aim of the course is to provide the student with knowledge of different methods in statistical experimental planning and sampling theory, to systematically plan, implement and analyze statistical surveys to obtain as much information as possible. The methods presented are widely used in technology and science to streamline and optimize processes and are a natural part of quality assurance in industry and society.
Topics covered in the course include
- General design of experiments.
- Factorial and reduced factorial experiments.
- Analysis of variance (one-way and multi-factor ANOVA).
- Mixed effects models.
- Split plot designs.
- Linear and non-linear regression and optimala designer.
- Responce surface methods.
- Basic techniques of simple random sampling, systemic sampling, stratified sampling,probability proportional to size sampling, cluster sampling, and multi-stage sampling.
- Population estimation using Horvitz-Thompson, ratio and regression estimation.
- Variance estimation for complex sample designs, including the Taylor series expansion method, balanced repeated sampling, and jackknife methods.
- Optimal allocation and optimal sampling schemes.
- Model based inference and pseudo likelihood-methods.
Knowledge corresponding to the courses MMG200 Mathematics 1, MSG200 Statistical Inference, and MSG500 Linear Statistical Models.
EU/EEA citizens, Swedish residence permit holders and exchange students do not pay fees. More information on: http://www.universityadmissions.se
On successful completion of the course the student will be able to
- Describe the classical methods in optimal experimental design, their similarities and differences regarding design, execution and analysis.
- Choose a suitable experimental design for different problems and situations.
- Design an experiment from beginning to end, including planning and execution,data collection, statistical analysis and interpretation of results.
- Describe the most common sampling methods, in which situations they apply, and the corresponding population estimates and variance estimates.
- Describe and analyze both linear and non-linear estimation situations.