Improving data analysis in herpetology: using Akaike's Information Criterion (AIC) to assess the strength of biological hypotheses

Abstract

In ecology, researchers frequently use observational studies to explain a given pattern, such as the number of individuals in a habitat patch, with a large number of explanatory (i.e., independent) variables. To elucidate such relationships, ecologists have long relied on hypothesis testing to include or exclude variables in regression models, although the conclusions often depend on the approach used (e.g., forward, backward, stepwise selection). Though better tools have surfaced in the mid 1970's, they are still underutilized in certain fields, particularly in herpetology. This is the case of the Akaike information criterion (AIC) which is remarkably superior in model selection (i.e., variable selection) than hypothesisbased approaches. It is simple to compute and easy to understand, but more importantly, for a given data set, it provides a measure of the strength of evidence for each model that represents a plausible biological hypothesis relative to the entire set of models considered. Using this approach, one can then compute a weighted average of the estimate and standard error for any given variable of interest across all the models considered. This procedure, termed model-averaging or multimodel inference, yields precise and robust estimates. In this paper, I illustrate the use of the AIC in model selection and inference, as well as the interpretation of results analysed in this framework with two real herpetological data sets. The AIC and measures derived from it is should be routinely adopted by herpetologists.

Development of Northern White-Cedar (Thuja occidentalis L.) Plantations within and outside Deer Yards

“…In order to determine the most appropriate competition index (CI) for cedar diameter growth prediction, multiple linear mixed models were compared using the second-order Akaike information criterion corrected for small samples (AICc [43,44]). Nine distance-independent CI which proved satisfactory in other studies (Table 2) and the measured canopy closure were evaluated in models to determine which metric(s) to include in the growth model.…”

The importance of phenotypic diversity in conservation: Resilience of palmate newt morphotypes after fish removal in Larzac ponds (France)

“…Finally, we used the modelaveraging function from the AIC analyses. This model-averaging procedure consists of making inferences based on the set of candidate models (with a delta AICc < 4), instead of basing the conclusions only on the single best model (Mazerolle 2006). This procedure computes a weighted mean of the parameter estimates to be calculated, such that little weight is given to parameter estimates from models that contribute little information about the variance of the response variable (Grueber et al 2011).…”

“…This procedure computes a weighted mean of the parameter estimates to be calculated, such that little weight is given to parameter estimates from models that contribute little information about the variance of the response variable (Grueber et al 2011). Once the model-averaged estimates are calculated, the 95% confidence intervals are used to assess the magnitude of the effect: there is a strong effect when the confidence interval excludes zero (Mazerolle 2006).…”

Male calling activity in syntopic populations ofRana latasteiandRana dalmatina(Amphibia: Anura)

“…In these analyses, we considered cosine models up to and including the fifth harmonic frequency. The better model was selected using the Akaike's Information Criterion (AIC) model selection (Burnham & Anderson 2002;Mazerolle 2006). Days with no calling activity were removed from the series, so analyses were done on the sub-series 8 March-1 April for R. latastei, and on the sub-series 11 to 29 March for R. dalmatina.…”