Performance of several variable‐selection methods applied to real ecological data

Murtaugh, Paul A.

doi:10.1111/j.1461-0248.2009.01361.x

Cited by 315 publications

(237 citation statements)

References 26 publications

Supporting

Mentioning

228

Contrasting

Order By: Relevance

“…Models obtained through stepwise regression have been shown to have higher predictive power than regression trees and similar predictive power to models obtained through exhaustive subset search and stepwise elimination using Akaike information criterion. 53 Although stepwise regression can lead to bias in coefficients when predictor variables are correlated, the alternative, including nonsignificant and possibly spurious variables can lead to overfitting. In our analyses, coefficients of predictors in reduced models were very similar to those estimated for the full models, suggesting that bias in coefficients due to variable selection was minor.…”

Section: Methodsmentioning

confidence: 99%

Estimating Burdens of Neglected Tropical Zoonotic Diseases on Islands with Introduced Mammals

Wit

Croll

Tershy

et al. 2017

The American Society of Tropical Medicine and Hygiene

View full text Add to dashboard Cite

Abstract. Many neglected tropical zoonotic pathogens are maintained by introduced mammals, and on islands the most common introduced species are rodents, cats, and dogs. Management of introduced mammals, including control or eradication of feral populations, which is frequently done for ecological restoration, could also reduce or eliminate the pathogens these animals carry. Understanding the burden of these zoonotic diseases is crucial for quantifying the potential public health benefits of introduced mammal management. However, epidemiological data are only available from a small subset of islands where these introduced mammals co-occur with people. We examined socioeconomic and climatic variables as predictors for disease burdens of angiostrongyliasis, leptospirosis, toxoplasmosis, toxocariasis, and rabies from 57 islands or island countries. We found strong correlates of disease burden for leptospirosis, Toxoplasma gondii infection, angiostrongyliasis, and toxocariasis with more than 50% of the variance explained, and an average of 57% (range = 32-95%) predictive accuracy on out-of-sample data. We used these relationships to provide estimates of leptospirosis incidence and T. gondii seroprevalence infection on islands where nonnative rodents and cats are present. These predicted estimates of disease burden could be used in an initial assessment of whether the costs of managing introduced mammal reservoirs might be less than the costs of perpetual treatment of these diseases on islands.

show abstract

Section: Methodsmentioning

confidence: 99%

Estimating Burdens of Neglected Tropical Zoonotic Diseases on Islands with Introduced Mammals

Wit

Croll

Tershy

et al. 2017

The American Society of Tropical Medicine and Hygiene

View full text Add to dashboard Cite

show abstract

“…Data collection methods and sampling patterns also need to align with the goals and needs of the mapping exercise, or, in other words, the intended use of the map. In terms of the map production approach, it has been shown in many studies that given the same context and data, using different mapping and modeling techniques produces different outcomes (e.g., Keil and Hawkins, 2009;Marmion et al, 2009;Murtaugh, 2009), which can inform conservation and management differently (Jones-Farrand et al, 2011). While the type of approach is selected based on the objectives of the maps and the available data , the specific method is open to subjectivity from mapmakers or modelers.…”

Section: Marine Habitat Mappingmentioning

confidence: 99%

On the Use of Maps and Models in Conservation and Resource Management (Warning: Results May Vary)

Lecours

2017

Front. Mar. Sci.

View full text Add to dashboard Cite

Conservation planning and management typically require accurate and spatially explicit data at scales that are relevant for conservation objectives. In marine conservation, these data are often combined with spatial analytical techniques to produce marine habitat maps. While marine habitat mapping is increasingly used to inform conservation efforts, this field is still relatively young and its methods are rapidly evolving. Because conservation efforts do not always specify standards or guidelines for the production of habitat maps, results can vary dramatically. As representations of real environmental characteristics, habitat maps are highly sensitive to how they are produced. In this review paper, I present four concepts that are known to cause variation in spatial representation and prediction of habitats: the methodology used, the quality and scale of the data, and the choice of variables in regards to fitness for use. I then discuss the potential antinomy associated with the use of habitat maps in conservation: while habitat maps have become an invaluable tool to inform and assist decision-making, maps of the same area built using different methods and data may provide dissimilar representations, thus providing different information and possibly leading to different decisions. Exploring the theories and methods that have proved effective in terrestrial conservation and the spatial sciences, and how they can be integrated in marine habitat mapping practices, could help improve maps used to support marine conservation efforts and result in more reliable products to inform conservation decisions. Having a strong, consistent, transparent, repeatable, and science-based protocol for data collection and mapping is essential for effectively supporting decision-makers in developing conservation and management plans. The development of user-friendly tools to assist in the application of such protocol is crucial to a widespread improvement in practices. I discuss the potential to use interactive and collaborative Geographic Information Systems (GIS) to encourage the conservation and management community, from data collectors and mapmakers to decision-makers, to move toward a digital resilience and to develop such science-based protocol. Until standards and protocols are developed, habitat maps should always be interpreted with care, and the methods and metadata associated with their production should always be explicitly stated.

show abstract

“…We applied backward stepwise model selection based on the P < 0.05 criterion. There are several model selection approaches available, but this one is generally considered as a conservative choice (Murtaugh, 2009). We first removed the nonsignificant interactions in the order of decreasing P value and then did the same with the single effects.…”

Section: Statistical Analysesmentioning

confidence: 99%

Escape strategy of Schreiber’s green lizards (Lacerta schreiberi) is determined by environment but not season or sex

Kopena

Herczeg

López

et al. 2015

Behav

View full text Add to dashboard Cite

Antipredator escape behaviour shows great variation with well-established sources of variation being the physical environment and the ecological context. However, the relative roles of these sources are rarely assessed together. We measured the distance that Schreiber's green lizards, Lacerta schreiberi allowed a simulated predator to approach before fleeing (flight initiation distance; FID) to know which are the main determinants of escape decisions. The environment had direct effects on the lizards' escape strategy; FID showed strong positive relationship with distance to refuge on grassy, but not on rocky substrates. Furthermore, refuge distance and the escape angle had a complex, substrateindependent, interaction effect: either short refuge distances or large escape angles resulted in short FIDs. In contrast, neither season (reproductive vs. nonreproductive), nor sex affected FID. We suggest that the escape strategy of this lizard is determined mainly by the environmental settings, irrespective of the ecological context or sexual roles.

show abstract

Performance of several variable‐selection methods applied to real ecological data

Cited by 315 publications

References 26 publications

Estimating Burdens of Neglected Tropical Zoonotic Diseases on Islands with Introduced Mammals

Estimating Burdens of Neglected Tropical Zoonotic Diseases on Islands with Introduced Mammals

On the Use of Maps and Models in Conservation and Resource Management (Warning: Results May Vary)

Escape strategy of Schreiber’s green lizards (Lacerta schreiberi) is determined by environment but not season or sex

Contact Info

Product

Resources

About