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 Virtual StatsPD@Waite seminar where Omer Ozturk from the Ohio State University will present on order restricted randomization in agricultural field experiments.

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

Please email Beata Sznajder for details of the Zoom meeting.

Presenter: Omer Ozturk (Ohio State University)

Title: Order restricted randomization in agricultural field experiments
Field experiments are run under two competing objectives, high precision, and minimal cost. The precision can be increased by either using sound experimentation techniques that account for the sources of variation with reasonable statistical models or increasing the sample size. Large sample sizes usually increase the cost of the experiment and may not be feasible. This paper uses order restricted randomized designs (ORRD) to increase the precision while keeping the sample size and cost of the experiment minimal.

The ORRD described here starts with a randomised block design but adds a second layer of blocking by ranking plots within each block. This creates a two-way lay-out, blocks and ranking groups, and uses a restricted randomization to improve the precision of estimation of the treatment parameters. Ranking groups create a correlation structure for within-block units. The restricted randomization uses this correlation structure to reduce the error variance of the experiment. The paper computes the expected mean square for each source of variation in the ORRD design under a suitable model. It also provides approximate tests for treatment and ranking group effects. The efficiency of the ORRD is investigated through empirical power studies. Finally, an example based on a uniformity trial illustrates the use of the method in a split-plot experiment.