VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.
Applied Statistical Methods in Animal Sciences
Last Updated: 2026-02-05 16:08:19
Abstract
Genomic selection is currently the method of choice for improving the genetic potential of selection candidates in livestock breeding programs. This lecture introduces the reason why regression cannot be used in genomic selection. Alternatives to regression analysis that are suitable for genomic selection are presented. The concepts introduced are illustrated by excersises in R.
Objective
The students are familiar with the properties of multiple linear regression and they are able to analyse simple data sets using regression methods. The students know why multiple linear regression cannot be used for genomic selection. The students know the statistical methods used in genomic selection, such as BLUP-based approaches, Bayesian procedures and LASSO. The students are able to solve simple exercise problems using the statistical framework R.
Content
- Introduction to multiple linear regression - Problem n << p when using least squares in genomic selection - BLUP based approaches of solving problem of n << p - LASSO (Least Absolute Shrinkage and Selection Operator) as an alternative to approaches used in animal breeding - Introduction to Bayesian Statistics and parameter estimation - Application of Bayesian methods in genomic selection (BayesA, BayesB, BayesC, BayesN)
Resources
Lecture Notes
Course notes in the form of a monograph, copies of the slides and solutions to the exercise questions are available on the net.
Literature
To be announced in the lectures.
General Information
- Language
- English
- Levels
- MSC
- Frequency
- Yearly recurring
Examination
- Type
- graded semester performance
Course Components
| Type | Title | Time & Place | Hours |
|---|---|---|---|
| lecture | Applied Statistical Methods in Animal Sciences |
|
2 h weekly |