Experimental design is a fundamental area of statistics that focuses on planning studies to collect data efficiently and draw reliable conclusions. This session is devoted to model-based design of experiments, where statistical models are used to select the most informative experimental settings before data are collected. The contributions cover a range of applications, including agricultural science and psychology, and present both analytical solutions and computational methods for constructing optimal designs. The proposed methods are illustrated using real data examples.
Organized by:
Maryna Prus (Germany)Invited Speakers:
- Stephan Bark (Germany)
A Bayesian updating framework for long-term multi-environment trial data in plant breeding - Nadja Malevich (Germany)
Estimation and design strategies for inter-individual differences in an overparameterized paired comparison model - Maryna Prus (Germany)
Optimal allocation of trials to sub-regions in multi-environment crop variety testing
Contributed Speakers:
- Małgorzata Graczyk (Poland)
Selected properties of estimators in the model of weighing design