Model Selection and Inference: A Practical Information-Theoretic Approach

By Paul Beier, K. Burnham, David R. Anderson. 2001

3,503 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/61f90bc3257634da7d333a076a70bad55b05d3ff

How researchers see this paper

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

In Artificial Intelligence

Citations in the corpus

Body size, niche breadth, and ecologically scaled responses to habitat fragmentation: mammalian predators in an agricultural landscape (2003, methodology): “Subsequently, we determined the relative likelihood that one model was better than another as wi/wj (Burnham and Anderson, 1998).”
Growing in Cities: An Urban Penalty for Wild Birds? A Study of Phenotypic Differences between Urban and Rural Great Tit Chicks (Parus major) (2017, positive): “Models were compared with Akaike’s Information Criterion (AIC), and the most parsimonious was retained (lowest AIC, Burnham and Anderson, 1998).”
Likelihood Cross-Validation Versus Least Squares Cross-Validation for Choosing the Smoothing Parameter in Kernel Home-Range Analysis (2006, methodology): “To determine consistency among home-range software in computing LSCVh, we used the test data associated with KERNELHR and calculated the 90% contour, with LSCVh smoothing, using our algorithm and 3 common home-range programs, Animal Movement, KERNEL HR, and HOME RANGE.”
Rotated sigmoid structures in managed uneven-aged northern hardwood stands: a look at the Burr Type III distribution (2008, methodology): “AIC takes a very simple form that is easy to calculate from the optimization results (Burnham and Anderson, 1998, p. 60): Table 3: AIC and RMSE (in trees per acre) values for the Burr and FMM fits by treatment in 1989 AIC RMSE Treatment FMM Burr Best fit FMM Burr 40:30 1399.3 1394.2 Burr 2.6 3.3…”
Assessing the suitability of central European landscapes for the reintroduction of Eurasian lynx (2002, methodology): “However, we did not want to exclude variables that may influence lynx presence or absence, such as agriculture, beforehand, as this would constitute data dredging (Burnham & Anderson 1998).”
Principles of Data Mining (2001, background): “General texts on mixture distributions include Everitt and Hand (1981), Titterington, Smith, and Makov (1985), McLachlan and Bàsford (1988), Böhning (1998), and McLachlan and Peel (2000). Diebolt and Robert (1994) provide an example of the general Bayesian approach to mixture modeling.”
Instrumentalism, Parsimony, and the Akaike Framework (2002, background): “My next example (for others, see Yoccuz 1991; Johnson 1995; Burnham and Anderson 1998) concerns hypotheses about a “molecular clock.”
Climatic effects on the breeding phenology and reproductive success of an arctic‐nesting goose species (2008, methodology): “We selected the best model among the set of candidate models based on the Aikaike Information Criterion (the best model had the lowest AIC value; Burnham & Anderson, 1998).”
Components of Grizzly Bear Habitat Selection: Density, Habitats, Roads, and Mortality Risk (2007, methodology): “The DAIC value for first and second-ranked plateau models was 0.32, indicating that support for either model was comparable (Burnham and Anderson 2002).”
Habitat heterogeneity affects population growth in goshawk Accipiter gentilis (2001, methodology): “To minimize the number of candidate two-way interaction terms, we used all the a priori information we had on goshawk biology (for including interaction terms see, e.g. Burnham & Anderson 1998).”
THESEUS: maximum likelihood superpositioning and analysis of macromolecular structures (2006, methodology): “tion. The overall absolute likelihood is produced, as well as likelihoodist model selection measures such as the Akaike Information Criterion (AIC) and the Bayesian Information Criterion (BIC) ( Burnham and Anderson, 1998 ).”
Poleward shifts in breeding bird distributions in New York State (2009, methodology): “Although the mixing of null hypothesis test results with information criteria is generally not recommended (Anderson et al., 2001b; Burnham & Anderson, 2002), we present the results of the ordinary least squares regression for purposes of comparison with past studies.”
Landscape genetics of the Alpine newt (Mesotriton alpestris) inferred from a strip-based approach (2011, background): “on significance, but on the calculated value of Akaike’s information criterion (AIC; Akaike 1974) as a measure of model fit (Burnham and Anderson 2002).”
Influence of genetic relatedness and spatial proximity on chronic wasting disease infection among female white-tailed deer (2010, background): “…and distance (see Results), and the distance where regular contact or range overlap are unlikely based on home range size ( to determine the relative importance and Akaike's weight of the competing models, and calculated modelaveraged coefficients and predictions (Burnham & Anderson 2002).”
Using pattern-oriented modeling for revealing hidden information: a key for reconciling ecological theory and application (2003, methodology): “Hilborn and Mangel (1997), Burnham and Anderson (1998) , Wood (2001) for methods), and under which model the patterns are most probable.”
Grizzly bears and forestry II. Distribution of grizzly bear foods in clearcuts of west-central Alberta, Canada (2004, methodology): “We evaluated model selection using Akaike’s information criteria (Burnham and Anderson, 1998; Anderson et al., 2000) with a small sample size correction (AICc).”
Consumer brand relationships: an investigation of two alternative models (2008, methodology): “Because, in general, the BRQ models are not nested, but rather use the same variance–covariance matrix, we employed the Akaike information criterion (AIC) and the second-order Akaike information criterion (AICc) to compare these models (Burnham and Anderson 1998).”