Sound sampling design is essential for the collection of data to support reliable scientific inference and decision making for management and policy. What counts as a sound design depends on the problem of interest, and the nature of the statistical inference that is required. Two broad aims can be distinguished, estimating the overall mean or total of a population, e.g. the total soil carbon stock in an area, and mapping. Estimating the means or totals of several subpopulations (subareas) is in between these two extremes. This course presents an overview of spatial sampling strategies for the full spectrum of aims. For estimating (sub)population means or totals probability sampling and design-based or model-assisted estimation is most appropriate, whereas for mapping probability sampling is not required, and there is scope to optimize the locations of the sampling points with a statistical model of the spatial variation.
In this course you will learn how to choose a sampling design that is most appropriate for the aim of your project. Theoretical concepts from classical sampling and geostatistics will be explained with a strong emphasis on practical application. In the course you will be provided with scripts for the free R platform, which will allow you to use the methods that are described to solve your sampling problems.
Former occurrences of this course
16-19 Febr 2021 | 22-24 Apr 2015 | 1-3 Dec 2014