inqua23
Slides and code for my session keynote at INQUA 2023
Science Score: 49.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 3 DOI reference(s) in README -
✓Academic publication links
Links to: zenodo.org -
○Committers with academic emails
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (12.8%) to scientific vocabulary
Repository
Slides and code for my session keynote at INQUA 2023
Basic Info
- Host: GitHub
- Owner: gavinsimpson
- License: cc-by-4.0
- Language: R
- Default Branch: main
- Homepage: https://gavinsimpson.github.io/inqua23/slides/
- Size: 11.6 MB
Statistics
- Stars: 4
- Watchers: 2
- Forks: 0
- Open Issues: 0
- Releases: 3
Metadata Files
README.md
Applying statistical thinking to palaeo data through GAMs
This repo contains the slide deck and R code for my session keynote at INQUA 2023 in Roma.
Rendered slides: HTML Slide Deck
Gavin Simpson
Department of Animal and Veterinary Sciences, Aarhus University, Denmark
Abstract
Palaeoecological and palaeoenvironmental stratigraphic data exhibit a number of features that make them complex to analyse; for example they
- are autocorrelated in time (and, potentially, also in space),
- are generally irregularly spaced in time, and
- have complex variance properties due to time averaging and sampling processes.
This complexity has some unfortunate consequences. All too often, data are not subject to any form of statistical analysis, and, when they are, often that analysis uses inappropriate statistical methods. Furthermore, analysts will often invent their own ad hoc approaches to get answers to their specific questions. The statistical properties of such ad hoc approaches are rarely known, however.
A number statistical methods have been developed over recent years and decades that can handle the complex needs of palaeo data. Among these methods is the generalized additive model (GAM) and related extensions. The use of GAMs to model temporal trends in palaeo data has increased steadily in recent years, thanks, in part, to the availability of high quality, open source software like the R package mgcv. GAMs are relatively simple models that will be familiar to anyone who has taken a graduate course in ecological statistics, and yet GAMs are incredibly versatile models that can be adapted to suit many pressing questions that palaeo scientists wish to address.
In this talk I will briefly introduce GAMs and show how penalised splines, which underpin the GAM, work, before moving on to cover some recent developments from my own work that extend GAMs to new areas and questions. In particular, I will discuss;
i. models that go beyond the mean to investigate trends in other moments, such as variances of palaeo time series, ii. using derivatives of splines fitted in a GAM as estimates of rates of change in palaeo time series, and iii. copula GAMs that can estimate how the correlation between two variables itself changes over time.
In each case I present a relevant motivating example and supplement the talk with fully worked examples in R that are available on GitHub.
Citation
Please cite as:
Simpson, Gavin L. (2023, July 13-20) Applying statistical thinking to palaeo data through GAMs [Session keynote]. XXI Congress of the International Union for Quaternary Research (INQUA), Rome, Italy. 10.5281/zenodo.8186141
Owner
- Name: Gavin Simpson
- Login: gavinsimpson
- Kind: user
- Location: Denmark
- Company: Aarhus University
- Website: fromthebottomoftheheap.net
- Twitter: ucfagls
- Repositories: 194
- Profile: https://github.com/gavinsimpson
GitHub Events
Total
Last Year
Committers
Last synced: 12 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| Gavin Simpson | u****s@g****m | 9 |
Issues and Pull Requests
Last synced: 12 months ago
All Time
- Total issues: 0
- Total pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Total issue authors: 0
- Total pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0