Skip to content

UCIDataScienceInitiative/SpaceTime

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Introduction to Spatial-Temporal Statistics

Instructors:
Gregory Britten ([email protected])
Yara Mohajerani ([email protected])
Department of Earth System Science
University of California, Irvine

Welcome!

This one-day workshop will introduce you to concepts from statistics that are most important for statistically analyzing spatial-temporal data. Motivated by datasets from the envrionmental sciences, we focus our study on two concepts: statistical autocorrelation and periodicity. The meaning of these terms will become clear as we work through the notebooks.

The workshop is divided in three basic parts: theory, software, and hands-on data analysis. The theory will build upon basic statistics to extend concepts to spatial-temporal properties. For software we'll use a few key R packages, along with Python functionality to access R packages from within Python.

The schedule of the course is as follows:

Pre-Install (before coming to workshop)

  • Intall instructions are available from the link above 'Intro : Requirements.ipynb'
  • PLEASE COME TO THE WORKSHOP ROOM EARLY (8:30) IF ANY PART OF THE INSTALL INSTRUCTIONS FAILS

Morning (pre-break)

  • Introduction to spatial-temporal statistics
  • Hands-on simulation to understand statistical concepts

Morning (post-break)

  • Applied time series analysis
  • Trend analysis, harmonic regression (for seasonality and other peiodicity), regression with covariates

Afternoon

  • Statistical model selection for time series
  • Extension of time series ideas to spatial analysis
  • Variogram functions
  • Spatial interpolation (Krigeing)
  • Spatial regression
  • Model selection for spatial models

GitHub Table of Contents

/R/ and /Python/

These folders contain the Jupyter notebooks. The notebooks contain notes to complement the slide presentation, along with executable code to implement the analyses we discuss. This is also the place where you will extend the analyses in hands-on exercises. The R and Python folders are effectively mirror copies of one another for the respective languages.

Data

  1. El Nino time series
  2. Orange County air quality time series
  3. Oregon climate station data

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published