Estimating Uncertainty

All data contains a variety of different types of "errors" of different magnitudes. The challenge is to estimate the amount of uncertainty in a data set and then report this uncertainty.

Learning Outcomes

This learning module will enable you to:

• Design methods for estimating uncertainty in your response and predictor variables and your model outputs
• Quantify errors from interpolated surfaces
• Quantify errors from remotely sensed surfaces
• Create functions in R
• Use Monte Carlo methods to generate measures of uncertainty
• Use Raster data within R

Activities

• Presentation: Uncertainty

Lab

• See section 8 of the R for Spatial Statistics website for information on the methods for completing this lab

Optional Readings

• Reading (optional): Microclimates
• Reading (optional): Effects of Errors and Gaps in Spatial Data Sets on Assessment of Conservation Progress, Visconti, 2013
• Reading (optional): Physiographically sensitive mapping of climatological temperature and precipitation across the conterminous United States, Daly, 2008

Old

Estimating Uncertainty in Predictor Variables