The SQuID group is a collaborative network of international scientists with the aim of:

  1. Using simulation-based models of variability at multiple levels to enhance the understanding and the use of generalised linear mixed models (GLMM) in different biological research contexts. We investigate statistical power and bias, explore best practices for complex data, and provide insight into fundamental conceptual issues. (link to publications)

  2. Providing educational tools for learning GLMM. For example, by offering online interactive teaching material through our R package or by organizing in person workshops in different countries. (link to package)

Birth of SQuID

It all started in Hannover in November 2013 at the occasion of a workshop on personality organised by Susanne Foitzik, Franjo Weissing, and Niels Dingemanse and funded by the Volkswagen Foundation. During this workshop, a group of researchers discussed the potential issues related to sampling designs on the estimation of components of the phenotypic variance and covariance. It became obvious that there was an urgent need to develop a simulation package to help anyone interested in using a mixed model approach at getting familiar with this method and avoiding the pitfalls related to the interpretation of the results. A first model and a working version of the R package were created in January 2014, during a meeting at Université du Québec à Montréal.

Biological motivation

SQuID seeks to understand patterns of phenotypic variance, which is the material on which natural selection is acting, and thus is a most essential feature of biological investigation. Different sources of variations are at the origin of the phenotype of an individual. Individuals differ in their phenotypes because they have different genes. They also experience different types of environmental effects during their lifetime. Some are imposing a very permanent mark on the phenotype over the whole lifetime. For example, by their parental behaviour individuals can affect their offspring phenotypes permanently, causing among-individual variation. Other environmental sources play more short-term effects on the phenotype, as individuals react in the plastic way to these sources, causing within-individual variation. The patterns of variation can be very complex. For instance, individuals differ not only in their average phenotypes but also in how they can change their phenotype according to changes in the environment, which represents an interaction between the among- and the within-individual levels. Selection can act differently on these different components of variance in the phenotypes of a trait, and therefore it is important to estimate them.

Mixed models are very flexible statistical tools that provide a way to estimate the variation at these different levels and represent the general statistical framework for evolutionary biology. Because of the progress in computational capacities mixed models have become increasingly popular among ecologists and evolutionary biologists over the last decade. However, running mixed model is not a straightforward exercise, and the way data are sampled among and within individuals can have strong implications on the outcome of the model. This is why we considered it was necessary to create the squid group that could help new users interested in decomposing phenotypic variance to get more familiar with the concept of hierarchical organization of traits, with mixed models and to avoid pitfalls caused by inappropriate sampling.