BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Virtual Seminar: “Including expert knowledge in genomic selectio
 n through intuitive tree-based joint priors” - Ingeborg Hem\, Norwegian 
 University of Science and Technology
DTSTART:20200416T130000Z
DTEND:20200416T140000Z
UID:TALK139525@talks.cam.ac.uk
CONTACT:Alison Quenault
DESCRIPTION:Bayesian hierarchical models with additive latent structures a
 re popular since additivity simplifies interpretation and inference. Howev
 er\, the common choice of independent priors on the variances of the model
  components result in haphazard a priori control on the total variance and
  how it is attributed to the model components. We propose a joint prior fo
 r the variance parameters that explicitly controls the total variance and 
 how it is distributed to the model components. For latent Gaussian models\
 , we can utilize the penalized complexity prior framework to achieve the d
 esired shrinkage between the random effects in the model\, or we can choos
 e to be ignorant through Dirichlet priors. The resulting priors have intui
 tive hyperparameters and are weakly-informative.\n\nIn the field of plant 
 breeding\, geneticists have strong expert knowledge on the relative sizes 
 of the different genetic effects: additive\, dominant and epistasis. We de
 monstrate how one can intuitively incorporate this knowledge in the model 
 in a robust way\, and how the prior knowledge can be communicated between 
 geneticists and statisticians through a visualization of the prior assumpt
 ions. We show through a simulated breeding program of wheat that our metho
 d\, which takes advantage of the expert knowledge on additive\, dominant a
 nd epistasis effects in the analysis\, performs better\, in terms of genom
 ic selection and robustness\, than standard methods using only additive ef
 fects.\n\nImportant information: \nThis will be a virtual seminar using Mi
 crosoft Teams. To register (for FREE)\, please sign-up using EventBrite (h
 ttps://www.eventbrite.co.uk/e/bsu-virtual-seminar-tickets-102087269772) an
 d we will then contact you to let you know how to join the seminar.
LOCATION:Virtual Seminar 
END:VEVENT
END:VCALENDAR
