Nicholas Clark
Nicholas Clark
  • 3
  • 190
Time series in R and Stan using the mvgam package: an introduction
This video is the first of a five-part series on using the mvgam R package for Bayesian inference of dynamic time series models. In this video, we introduce the package mvgam by using a range of dynamic State-Space models to analyse a time series of disease counts. This video covers the basics of mvgam, including:
1. Data preparation and visualisation
2. Inspection of default prior distributions
3. Updating priors and fitting models using Stan as the backend
4. Conditional effect plots
5. Residual analysis
6. Prediction and forecasting
About the mvgam package:
The goal of mvgam is to fit Bayesian (Dynamic) Generalized Additive Models, using the probabilistic programming language Stan for MCMC inference. This package constructs State-Space models that can include highly flexible nonlinear predictor effects for both process and observation components by leveraging functionalities from the impressive brms and mgcv R packages. This allows mvgam to fit a wide range of models, including hierarchical ecological models such as N-mixture or Joint Species Distribution models, as well as univariate and multivariate time series models with imperfect detection.
Where to find out more information:
- The R code used for this video: gist.github.com/nicholasjclark/c8f2fa827da233c810d1b2103fdcf7b7
- The mvgam package website: nicholasjclark.github.io/mvgam/
- A blog post on fitting Gaussian Processes with autocorrelation: ecogambler.netlify.app/blog/autocorrelated-gams/
- A blog post on models with time-varying seasonality: ecogambler.netlify.app/blog/time-varying-seasonality/
- The Stan Discourse: discourse.mc-stan.org/
มุมมอง: 123

วีดีโอ

Harnessing the power of ecological forecasting
มุมมอง 4521 วันที่ผ่านมา
Rapidly changing climates and landscape modification are impacting global ecosystems at all micro- and macroecological levels, incurring significant economic and environmental costs. Human encroachment into bushland and habitat alterations are magnifying risks of zoonotic diseases and shifting key conservation targets. Changing temperatures are altering food distributions and influencing reprod...
Rapid winter warming associated with major shifts in coastal fish communities - Nicholas Clark
มุมมอง 2521 วันที่ผ่านมา
Mathematical modelling inspired by social media is identifying the significant impacts of warming seas on the world’s fisheries. University of Queensland School of Veterinary Science researcher Dr Nicholas Clark and colleagues from the University of Otago and James Cook University have assembled a holistic picture of climate change’s impacts on fish stocks in the Mediterranean Sea. “Usually, wh...

ความคิดเห็น

  • @ahmed007Jaber
    @ahmed007Jaber 9 วันที่ผ่านมา

    Ll have to watch this later Is this better than fable, feast and prophet?

    • @NJ_Clark
      @NJ_Clark 9 วันที่ผ่านมา

      @@ahmed007Jaber The goals are very different. Those packages are designed to give good forecasts for real valued time series when domain expertise and external information are limited. mvgam is designed for the opposite (challenging series with missing data, multi series clustering, detection error etc...: nicholasjclark.github.io/physalia-forecasting-course/day1/lecture_1_slidedeck#1)

    • @ahmed007Jaber
      @ahmed007Jaber 8 วันที่ผ่านมา

      @@NJ_Clark oh I see. i will have to investigate. what i mentioned came up on my radar as I would like to aggregate daily date into quarterly and monthly time serites and try to forecast until i feel confident enough if data works to forecast daily i am new into all of this time-series analysis and they are on my priority list to learn and experiment with

  • @SimonTallowin-qw4vg
    @SimonTallowin-qw4vg 11 วันที่ผ่านมา

    Thanks for the great introduction. Looking forward to the next in the series!