Skip to Main Content
Curious or spurious correlations within a national-scale forest inventory?Author(s): Christopher W. Woodall; James A. Westfall
Source: In: McWilliams, Will; Roesch, Francis A. eds. 2012. Monitoring Across Borders: 2010 Joint Meeting of the Forest Inventory and Analysis (FIA) Symposium and the Southern Mensurationists. e-Gen. Tech. Rep. SRS-157. Asheville, NC: U.S. Department of Agriculture Forest Service, Southern Research Station. 39-43.
Publication Series: Paper (invited, offered, keynote)
Station: Southern Research Station
PDF: Download Publication (239.44 KB)
DescriptionForesters are increasingly required to assess trends not only in traditional forest attributes (e.g., growing-stock volumes), but also across suites of forest health indicators and site/climate variables. Given the tenuous relationship between correlation and causality within extremely large datasets, the goal of this study was to use a nationwide annual forest inventory to determine levels of correlation among a wide array of database fields to aid foresters in separating correlation from causality in comprehensive forest resource assessments. In examining more than 15,000 individual correlations, we found the overwhelming majority (> 85 percent) of correlation coefficients were under 0.1. Site variables (e.g., elevation) had the highest mean correlations, while tree variables (e.g., live aboveground biomass) had the lowest mean correlations with all other variables. Nearly all the high correlations (>0.6) were between variables substantially autocorrelated (e.g., site class code and site index). Given that most correlations within a large-scale forest inventory dataset are very low with the remainder being nonsensical or autocorrelates, finding a highly correlated pair of variables with no apparent autocorrelation deserves further exploration.
- You may send email to firstname.lastname@example.org to request a hard copy of this publication.
- (Please specify exactly which publication you are requesting and your mailing address.)
- We recommend that you also print this page and attach it to the printout of the article, to retain the full citation information.
- This article was written and prepared by U.S. Government employees on official time, and is therefore in the public domain.
CitationWoodall, Christopher W.; Westfall, James A. 2012. Curious or spurious correlations within a national-scale forest inventory? In: McWilliams, Will; Roesch, Francis A. eds. 2012. Monitoring Across Borders: 2010 Joint Meeting of the Forest Inventory and Analysis (FIA) Symposium and the Southern Mensurationists. e-Gen. Tech. Rep. SRS-157. Asheville, NC: U.S. Department of Agriculture Forest Service, Southern Research Station. 39-43.
- Association of weather and nest-site structure with reproductive success in California spotted owls
- Testing a Landsat-based approach for mapping disturbance causality in U.S. forests
- RCLUS, a new program for clustering associated species: A demonstration using a Mojave Desert plant community dataset
XML: View XML