Advanced Multivariate Analysis -Integrating Classical Techniques with multivariate GLMM

Onsite course

Advanced Multivariate Analysis - Integrating Classical Techniques (PCA, RDA, CA, CCA) with multivariate GLMM

This course offers a journey through classical multivariate analysis techniques and advances into recently developed tools for multivariate GLM and GLMM.

We start with classical multivariate techniques like principal component analysis, redundancy analysis, correspondence analysis and canonical correspondence analysis. We then continue with generalised linear latent variable models (GLLVM). A GLLVM is a GLM (or GLMM) in which multiple response variables are analysed simultaneously, while allowing for dependency between the response variables and also between the observations. We will discuss extensions of GLLVM that allow for constrained latent variables (concurrent ordination) and spatial and temporal dependency structures.

Course content

Preparation material (with on-demand video):

  • Exercise on linear regression.
  • Exercise on Poisson / negative binomial GLM.
  • Exercise on Poisson / negative binomial GLMM.
  • Matrix notation.
  • DHARMa for model validation.

Monday:

  • General introduction.
  • Theory presentation on principal component analysis (PCA), redundancy analysis (RDA), correspondence analysis (CA) and canonical correspondence analysis (CCA).
  • Exercise on PCA and RDA.
  • Exercise on CA and CCA.
  • Theory presentation on generalised linear latent variable models (GLLVM).

Tuesday:

  • Catching up.
  • Four exercises on GLLVM using Poisson and negative binomial models for count data.

Wednesday:

  • Theory presentation on constrained GLLVM (reduced rank regression and concurrent ordination).
  • Four exercises on constrained GLLVM.

Thursday:

  • Catching up.
  • Exercises using GLLVM with Tweedie, Gamma, Gaussian and beta distributions.
  • Time allowing: Adding spatial and temporal dependency structures.

This is an applied and non-technical course that focuses on the practical implementation in R. We reserve the right to change the exercises. Pdf files of all theory material will be provided. All exercises consist of data sets and annotated R scripts. Access to the course website is for 12 months. The material covered from Monday to Thursday does not contain on-demand video.

Pre-required knowledge

  • Participants should be familiar with data exploration, linear regression and basic GLM and GLMM (i.e. Poisson and negative binomial GLM) in R. The course website contain revision/preparation material with on-demand videos covering these topics.

1 hour face-to-face

  • The course includes a 1-hour face-to-face video chat with the instructors (to be used after the course). You are invited to apply the statistical techniques discussed during the course on your own data and if you encounter any problems, you can ask questions during the 1-hour face-to-face chat.

A discussion board, accessible for 12 months, facilitates interaction on course content between instructors and participants after the course.

For terms and conditions, see:
https://www.highstat.com/index.php/component/hikashop/checkout/termsandconditions/step-3/pos-6/tmpl-component