Questionable multivariate statistical inference in wildlife habitat and community studies: A reply

Eric A. Rexstad; Drik D. Miller; Curtis H. Flather; Eric M. Anderson; Jerry W. Hupp; David R. Anderson

Treesearch

Questionable multivariate statistical inference in wildlife habitat and community studies: A reply

Formally Refereed

Authors:

Eric A. Rexstad, Drik D. Miller, Curtis H. Flather, Eric M. Anderson, Jerry W. Hupp, David R. Anderson

Year:

1990

Type:

Scientific Journal

Station:

Rocky Mountain Research Station

Source:

The Journal of Wildlife Management. 54(1): 189-193.

Download (PDF 792 KB)

Download (PDF 792 KB): https://research.fs.usda.gov/download/treesearch/59196.pdf

Abstract

We substantiate our contention that our multivariate analyses (Rexstad et al. 1988) mimic analyses found in the wildlife literature. We caution users of multivariate techniques that data collected in our discipline are unlikely to meet the restrictive assumptions of these techniques. Even if assumptions are met, we contend interpretation of the results is likely to lead to invalid inferences.

Keywords

wildlife habitat, multivariate analyses

Citation

Rexstad, Eric A.; Miller, Drik D.; Flather, Curtis H.; Anderson, Eric M.; Hupp, Jerry W.; Anderson, David R. 1990. Questionable multivariate statistical inference in wildlife habitat and community studies: A reply. The Journal of Wildlife Management. 54(1): 189-193.