Yesterday, I had the pleasure of presenting at the Australian National University (ANU) seminar series. The presentation focused on statistical strategies for the design and analysis of on-farm experiments, from fundamental principles to simulation evaluations.
📋 Abstract
This study explores statistical strategies for the design and analysis of on-farm experiments (OFE), grounded in established principles of experimental design and spatial modelling. Through simulation studies, we assess various approaches, including design layouts combined with Geographically Weighted Regression (GWR) for continuous response variables and Linear Mixed Models (LMM) for categorical treatments.
Our results align with key findings in the literature, emphasising the importance of appropriate design and modelling choices for effectively capturing spatial heterogeneity. Additionally, we compare two trial types—large-strip trials and stacked replicated trials—and highlight the significance of data granularity, which informs data collection strategies for industry partners.
The findings advocate for appropriate trial designs for different purposes, and increased within-trial sampling, rather than reliance solely on average values to better reflect local variability and enhance inference accuracy. This work underscores the critical role of tailored statistical methods in improving the reliability and practical applicability of OFE outcomes.
Authors
Zhanglong Cao, Julia Easton, Suman Rakshit, Barbara Kachigunda, Mark Gibberd
Downloads
🎯 Key Topics Covered
- Design principles for on-farm experiments (OFE)
- Spatial modelling approaches including Geographically Weighted Regression (GWR)
- Linear Mixed Models (LMM) for categorical treatments
- Simulation studies comparing design layouts and analysis methods
- Trial type comparisons: Large-strip trials vs. stacked replicated trials
- Data granularity and within-trial sampling strategies
- Industry applications and practical implementation considerations
💡 Highlights
The presentation demonstrated how appropriate statistical design and modelling choices are crucial for effectively capturing spatial heterogeneity in on-farm experiments. A key finding emphasised the importance of increased within-trial sampling and data granularity, rather than relying solely on average values, to better reflect local variability and enhance inference accuracy.
The comparison between large-strip trials and stacked replicated trials provided valuable insights for industry partners in making informed decisions about trial design based on their specific research objectives and practical constraints.
🙏 Acknowledgments
Thank you to ANU for the invitation and to all attendees for the engaging discussion and valuable feedback.