A protocol for data exploration to avoid common statistical problems

7,388 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Short-term survival of discarded target fish and non-target invertebrate species in the “eurocutter” beam trawl fishery of the southern North Sea (2014, methodology): “Collinear explanatory variables were removed from the analysis according to a variance inflating factor (VIF) of two, to enable the detection of weak ecological signals (Zuur et al., 2010).”
Biodiversity consequences of land-use change and forest disturbance in the Amazon:a multi-scale assessment using ant communities (2016, background): “Canopy cover and tree species richness were highly correlated with percentage of primary forest cover at both transect and catchment scales (Pearson ρ > 0.73), and therefore they were removed from analyses (Zuur et al. 2010).”
Non-bee insects are important contributors to global crop pollination (2015, neutral): “5, indicating no multicollinearity (85).”
Climate change may drive cave spiders to extinction (2018, methodology): “Prior to model computing, we investigated multi-collinearity among covariates via Pearson r correlation (Zuur et al. 2009, 2010), selecting a final set of uncorrelated bioclimatic variables (r < ±0.7) (Table 1).”