------------------------------

*Advance Your Marine Mammal Research with Bayesian Multilevel Modelling*

https://prstats.org/course/bayesian-multilevel-modelling-using-brms-for-ecologists-bmme02/

Marine mammal science increasingly relies on sophisticated statistical
tools to extract robust insights from complex datasets. From
photo-identification studies and acoustic monitoring to telemetry and
population assessments, the challenges are clear: hierarchical structure,
imperfect detection, sparse sightings, zero inflation, individual
heterogeneity, spatial dependence, and non-Gaussian responses.

To meet these analytical demands, PR Stats is offering:

*Bayesian Multilevel Modelling using brms for Ecologists (BMME02)*
A 5-day, live online workshop designed for researchers who want to apply
modern Bayesian approaches to real ecological data using the *brms* package
in R.

Developed by ecologists for ecologists, this course provides the skills,
understanding, and confidence needed to analyse the kinds of messy,
hierarchical, and data-limited systems that define marine mammal research.
------------------------------
What you will learn

*Fundamentals of Bayesian inference*
Understand priors, posteriors, credible intervals, and how Bayesian
reasoning supports transparent and reproducible ecological modelling.

*Fitting and interpreting multilevel models in brms*
Learn to build models that reflect the real structure of your data, such as
repeated sightings of individuals, nested sampling designs, varying
detection effort, or multi-year monitoring programs.

*Best practices for model evaluation*
Develop rigorous habits in posterior predictive checking, residual
diagnostics, and model comparison, ensuring your conclusions are well
supported.

*Tools for zero-inflated, overdispersed, and imperfect detection data*
Marine mammal datasets often contain many zeros, sparse detections, or
uneven coverage. You will learn to use model families and structures that
address these challenges directly.

*Application to your own research*
Throughout the course, there is a strong emphasis on practical
implementation. You will gain experience applying the tools to ecological
case studies and be guided on how to adapt these methods to your own
datasets and research goals.
------------------------------
Why this course is especially useful for marine mammal researchers

Marine mammal ecology routinely involves:

   -

   *Photo-ID datasets* with repeated observations of individuals, varying
   capture probabilities, and long-term resight histories.
   -

   *Passive acoustic monitoring* with count, presence–absence, or
   detection-based outputs that are often zero-inflated.
   -

   *Telemetry and movement data* that require hierarchical structures and
   careful modelling of individual variability.
   -

   *Abundance and distribution surveys* with spatially structured effort
   and imperfect detection.
   -

   *Long-term monitoring* where temporal autocorrelation and multilevel
   variation are central features of the data.

Bayesian multilevel models provide a principled framework for analysing all
of these data types. The *brms* package allows you to fit sophisticated
hierarchical models while writing code that is clear, expressive, and
accessible to non-specialists. This course teaches you how to build models
that reflect ecological reality, quantify uncertainty, and communicate
results with clarity.

Whether your work focuses on population dynamics, distribution modelling,
acoustic behaviour, or conservation assessments, the tools gained here will
allow you to tackle complex analyses with confidence and rigour.
------------------------------

Spaces are limited. Secure your place today and expand your ability to
model, interpret, and understand ecological data in marine mammal research.

*Register here
<https://prstats.org/course/bayesian-multilevel-modelling-using-brms-for-ecologists-bmme02/>*

-- 
Oliver Hooker PhD.
PR stats
_______________________________________________
MARMAM mailing list
[email protected]
https://lists.uvic.ca/mailman/listinfo/marmam

Reply via email to