The distribution of continuous real life variables is usually not normal and plant
phenotypes are no exception to the rule. These distributions often show heavy tails which
are sometimes asymmetric. In such scenarios, the classical approach whose likelihood-based
inference leans on the normality assumption may be inappropriate, having low statistical e-
ciency. Moreover, association tests may also be underpowered. Robust statistical methods are
designed to accommodate for certain data deciencies, allowing for reliable results under various
conditions. They are designed to be resistant to in
uent factors as outlying observations,
non-normality and other model misspecications. Additionally, if the model veries the classical
assumptions, robust methods provide results close to the classical ones. Therefore, a new
methodology where robust statistical methods replace the classic ones to model, structure and
analyse genotype-by-environment interactions in the context of multi-location plant breeding
trials, is presented. Here interest lies in the development of a robust version of the additive main
eects and multiplicative interaction model whose performance is compared with its classical
version. This is achieved through Monte Carlo simulations where one particular contamination
scheme is considered.

CEMAT - Center for Computational and Stochastic Mathematics