*Elevate your geometric morphometric analyses with advanced mixed-models* Introduction to Generalised Linear Mixed Models for Ecologists
Learn to build and interpret linear, generalised linear, and multilevel models for ecological data using R, lme4, and rstanarm in this five day applied training course. https://prstats.org/course/introduction-to-generalised-linear-mixed-models-for-ecologists-mmie02/ *NOW ONLY 6 PLACE LEFT!* If you’re working with shape data from landmark-based or outline-based geometric morphometrics and need to test hypotheses about variation across individuals, populations, species or conditions — then this course on *Introduction to Generalised Linear Mixed Models for Ecologists* is exactly what you need. In this five-day live online workshop, you’ll learn to build and interpret linear, generalised linear and mixed-effects models in R (using **lme4, **rstanarm and **brms) with a focus on the hierarchical and multilevel structure common in geometric morphometric datasets. *Why it’s essential for morphometric work* Geometric morphometric datasets often come with grouped structure (e.g., landmark sets nested within individuals, individuals nested within populations, repeated measurements across time or treatments) and non-normal response distributions (e.g., principal component scores, Procrustes distances, shape variables). Mixed-models let you account for this structure, partition variance among levels (e.g., individual, population, species), and make valid inferences about shape variation, treatment effects or evolutionary patterns. *What you will learn* - To specify and fit fixed-effect and random‐effect structures appropriate to landmark/shape data (e.g., random intercepts for individual, random slopes for treatment by individual). - How to interpret model outputs, partition variance components, and test effects in multilevel morphometric designs. - How to handle non-Gaussian responses relevant to shape analysis (e.g., counts, binary outcomes, zero-inflation) and mixed designs across levels. - How to visualise hierarchical structure, correlate shape variation with other variables (ecological, behavioural or morphological), and clearly communicate your results with rigorous statistical backing. - Practical R workflows using lme4, rstanarm and brms — enabling you to move from simple regression toward full hierarchical modelling of morphometric data. *Who should attend* This course is ideal for morphometricians, evolutionary biologists, functional morphologists, and ecologists working with shape/landmark data who have some familiarity with R and basic statistics (means, variances, simple linear models). Whether you’re comparing populations, testing treatment effects on shape, modelling repeated-measurements or integrating morphometrics with environmental covariates — this workshop will equip you with appropriate modelling tools. *Format & logistics* - Live online for five days, approx. 6 hours per day — combining theory, coding, applied exercises and discussion. - Sessions recorded and available afterward, so you can revisit the material and apply it to your own morphometric datasets. - Participants encouraged to bring their own landmark/shape data for hands-on application. *Secure your place now* Visit the PR Stats website for full course details, upcoming dates and registration. Early booking advised — places are limited. Geometric morphometric datasets demand appropriate models; ensure your analyses are statistically sound and cutting-edge. -- Oliver Hooker PhD. PR stats -- You received this message because you are subscribed to the Google Groups "Morphmet" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion visit https://groups.google.com/d/msgid/morphmet2/CAEsSYzwjnfy-PNz6sMOks8zuBiaz-%2BZ%3DiB6LAsYxMHoPuiwhtA%40mail.gmail.com.
