Reevaluating Europe’s other debt with improved statistical tools
Tóm tắt
Dullinger et al. (Proc Nat Acad Sci USA 110:7342–7347, 2013) showed that current proportions of threatened species in European countries are more correlated to socio-economic pressures calculated a century ago than to current socio-economic pressures. These results could have important impacts on future political decisions, yet the statistical analyses used may be strongly impacted by pseudo-replication and over-dispersion of data. I reanalysed Dullinger et al.’s data using generalised linear mixed models accounting for pseudo-replication and over-dispersion. These new statistical models indicated that socio-economic pressures had a much less clear impact on proportions of threatened species than indicated by Dullinger et al. In many cases, the effects of socio-economic pressures even vanished. Dullinger et al. (Proc Nat Acad Sci USA 110:7342–7347, 2013)’s results are actually much less “considerable” than their paper implies and therefore should be viewed with caution. Ecologists should more often incorporate pseudo-replication and overdispersion in their statistical analyses.
Tài liệu tham khảo
Dullinger S, Essl F, Rabitsch W, Erb KH, Gingrich S, Haberl H, Hülber K, Jarošík V, Krausmann F, Kuḧn I, Pergl J, Pyšek P, Hulme PE (2013) Europe’s other debt crisis caused by the long legacy of future extinctions. Proc Nat Acad Sci USA 110:7342–7347. doi:10.1073/pnas.1216303110
Hurlbert SH (1984) Pseudoreplication and the design of ecological field experiments. Ecol Monogr 54:187–211
Millar RB, Anderson MJ (2004) Remedies for pseudoreplication. Fish Res 70:397–407. doi:10.1016/j.fishres.2004.08.016
Noe DA, Bailer AJ, Noble RB (2010) Comparing methods for analyzing overdispersed count data in aquatic toxicology. Environ Toxicol Chem 29:212–219. doi:10.1002/etc.2
O’Hara RB, Kotze DJ (2010) Do not log-transform count data. Methods Ecol Evol 1:118–122. doi:10.1111/j.2041-210X.2010.00021.x
Spiegelhalter DJ, Best NG, Carlin JB, van der Linde A (2002) Bayesian measures of model complexity and fit (with Discussion). J R Stat Soc B 64:583–616. doi:10.1111/1467-9868.00353
Warton DI, Hui F (2011) The arcsine is asinine: the analysis of proportions in ecology. Ecology 92:3–10. doi:10.1890/10-0340.1
White GC, Bennetts RE (1996) Analysis of frequency count data using the negative binomial distribution. Ecology 77:2549–2557