Virtual StatsPD@Waite meeting

Every month, the professional development meetings of statisticians and data scientists at Waite, known as StatsPD@Waite, bring together specialists in various aspects of data sciences in agriculture from Waite, Roseworthy and Adelaide.

Please join us for the next StatsPD@Waite seminar where Zhanglong Cao from the SAGI West node, Curtin University will present on a Bayesian Workflow for Spatially Correlated Random Effects in On-farm Experiment

Also please note that the StatsPD@Waite meetings are recorded. If you have a question to the speaker but had rather not be recorded, please send me your question via chat during the meeting and I will ask it on your behalf.

Please email Beata Sznajder for details of the Zoom meeting.

Title: A Bayesian Workflow for Spatially Correlated Random Effects in On-farm Experiment

Presenter: Zhanglong Cao (SAGI West node, Curtin University)

Accounting for spatial variability is crucial while estimating treatment effects in large strip on-farm trials. It allows for determining the optimal treatment for every part of a paddock, resulting in a management strategy that improves the sustainability and profitability of the farm. We specify a Bayesian hierarchical model with spatially correlated random parameters to account for the spatial variability in large strip on-farm experiments (OFE). A Bayesian workflow was used to check the prior and estimate the posterior distribution of these parameters. By accounting for spatial variability, this framework allows the estimation of spatially-varying treatment effects in large strip on-farm trials. Several approaches have been proposed in the past for assessing spatial variability. However, these approaches lack an adequate discussion of the potential problem of model misspecification. Using Bayesian post-sampling tools, we show how to diagnose the problem of model misspecification. To illustrate the applicability of our proposed method, we analysed a real on-farm strip trial from Las Rosas, Argentina, with the main aim of obtaining a spatial map of locally-varying optimal nitrogen rates for the entire paddock. Additionally, with the reproducibility of the Bayesian hierarchical model, we tested the power of geographically weighted regression (GWR) in fitting two types of experimental design for OFE: randomised designs and systematic designs. We conclude that the difference between randomised designs and systematic designs is not significant if a linear model of treatments is fitted or if the spatial variation is not taken into account. But for a quadratic model, systematic designs are superior to randomised designs.