Activity Number:
|
134
- Design of Experiments: Case Studies and Advancements
|
Type:
|
Contributed
|
Date/Time:
|
Monday, July 29, 2019 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Section on Physical and Engineering Sciences
|
Abstract #301828
|
|
Title:
|
A Practical Framework for the Design and Analysis of Crossover Experiments
|
Author(s):
|
Katherine Allen Moyer* and Jonathan Stallrich
|
Companies:
|
North Carolina State University and North Carolina State University
|
Keywords:
|
Optimal Design;
Crossover Experiments;
Repeated Measures
|
Abstract:
|
A drawback of crossover experiments is that effects from treatments applied to a unit early in the experiment may carry over into later periods, biasing estimates of effects for treatments applied subsequently. While including washout periods during the design stage can mitigate such carryover effects, situations exist where carryover cannot be avoided, such as experiments with time constraints. Many currently employed design and analysis methods to account for carryover do not mirror how this problem presents itself to the practitioner. We propose an optimal design framework that accounts for more general design questions associated with these types of experiments. This framework allows for flexibility in when treatments are applied and measured. The framework also includes new analysis methods to cover real-world cases where quantities of interest occur at uneven time points throughout the experiment or when experimenters are unable to follow the design plan perfectly. Examples are provided to demonstrate the framework and an exchange algorithm is used to find the optimal design under these scenarios.
|
Authors who are presenting talks have a * after their name.