Title: Designing experiments for general network structures
Authors: Ming-Chung Chang - Institute of Statistical Science, Academia Sinica (Taiwan) [presenting]
Frederick Kin Hing Phoa - Academia Sinica (Taiwan)
Jing-Wen Huang - National Tsing-Hua University (Taiwan)
Abstract: Network experiments are commonly conducted in various fields, such as agriculture trials, medical experiments, and social networks. In these cases, an experimental unit may connect with some others, and the treatment applied to a unit has an effect on the responses of the neighboring units. Designing such experiments is rarely discussed in the literature. In this work, we study optimal network designs given unstructured treatments. Alphabetical optimality criteria are considered for selecting designs with high efficiency in estimating the treatment effects. We provide theoretical conditions for designs to be optimal and illustrate our theory with numerical examples.