Model Selection And Multimodel Inference

By Jana Vogel. 2016

3,461 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/c00409efa0b8efb86704c2f9409aff912ac270a2

How researchers see this paper

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

Citations in the corpus

Shifting perceptions of risk and reward: Dynamic selection for human development by black bears in the western United States (2015, methodology): “We fit models using maximum likelihood estimation and used minimum Akaike Information Criterion (AIC) scores to assess the relative support of models with different fixed effects (Burnham and Anderson, 2002).”
ldr: An R Software Package for Likelihood-Based Su?cient Dimension Reduction (2014, methodology): “The statistic Λ( d 0 ) is distributed asymptotically as a chi-squared random variable with degrees of freedom ( p − 1) d 0 ( d 0 + 1) / 2 + p ( p + 1) / 2, and h ( n ) is equal to log n for BIC and 2 for AIC.”
EDITOR'S CHOICE: Small‐scale restoration in intensive agricultural landscapes supports more specialized and less mobile pollinator species (2015, methodology): “We considered models with DAIC ≤4 to be equivalent (Burnham & Anderson 2002).”
Identification of transcription factor binding sites using ATAC-seq (2018, methodology): “This method requires the estimation of a multinomial distribution and is likely to suffer from overfitting for large k-mers [24].”
Underdispersion models: Models that are “under the radar” (2017, methodology): “Accordingly, the best model has = 0, while the other models have > 0 such that “models having i ≤ 2 have substantial support (evidence), those in which 4 ≤ i ≤ 7 have considerably less support, and models having i > 10 have essentially no support” (Burnham and Anderson 2002).”
Bayesian inference and model comparison for metallic fatigue data (2015, methodology): “Model comparison Using a classical approach, we compute some popular information criteria, such as Akaike information criterion (AIC) [18], Bayesian information criterion (BIC) [19, 20] and AIC with correction [21], which are based on the maximized log-likelihood values.”
A brief introduction to mixed effects modelling and multi-model inference in ecology (2018, methodology): “Where several models have similar support in the data, inference can be made from all models using model-averaging (Burnham & Anderson 2002; Johnson & Omand 2004; Grueber et al 2011 NHST have meant that the use of IT approaches in ecology and evolution has grown rapidly in recent years (Lindberg et…”
Leaf dry matter content is better at predicting above-ground net primary production than specific leaf area (2017, methodology): “The AICc statistic was used in light of the small sample size 289 (Burnham & Anderson 2002).”
Warmer winters reduce the advance of tree spring phenology induced by warmer springs in the Alps (2018, methodology): “We calculated Akaike’s Information Criterion corrected for small sample size (AICC) with the R function AIC to select the most parsimonious model (Burnham and Anderson, 2002).”
A new discrete probability distribution with integer support on (−∞, ∞) (2016, background): “AIC is defined as AIC = −2 log(L) + 2k, where k is the number of parameter(s) and log(L) is the maximum of logarithm of likelihood for a given data set (Burnham and Anderson, 2002, 2004).”
Marine biodiversity and ecosystem functioning: what’s known and what’s next? (2015, methodology): “Akaike weights were used to identify the most parsimonious model(s) for each response variable (Burnham and Anderson 2002).”
Tree‐to‐tree competition in mixed European beech–Scots pine forests has different impacts on growth and water‐use efficiency depending on site conditions (2018, methodology): “Fixed effects selection was based on the Akaike’s information criterion corrected for small sample size (AICc), and the models with the lowest AICc were selected, that is, those most parsimonious (Burnham & Anderson, 2002).”
Relationships between wild bees, hoverflies and pollination success in apple orchards with different landscape contexts (2016, methodology): “We followed an automatic model selection procedure based on corrected Akaike’s information criterion (AICc) values (Burnham & Anderson, 2002).”
A Meta-Analysis on the Effects of 2,4-D and Dicamba Drift on Soybean and Cotton (2014, methodology): “2005) using Akaike’s Information Criterion (Burnham and Anderson 2002) and t-tests of the Cedergreen f parameter (Cedergreen et al.”