Accounting for uncertainty in ecological analysis: the strengths and limitations of hierarchical statistical modeling.

By Noel Cressie, Catherine A. Calder, James S. Clark, Jay M. Ver Hoef, Christopher K. Wikle. Ecological Applications, 2009

569 citations recorded by the source corpus.

Subfields: Environmental Chemistry, Environmental Engineering, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/7adea6af2b02c9f49275d59d123bac7a3fd1c77b

How researchers see this paper

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

In Environmental Chemistry

In Environmental Engineering

In Nature and Landscape Conservation

Citations in the corpus

Modeling Species Distribution and Change Using Random Forest (2011, background): “The issue of machine learning in ecology is as contentious as the frequentists/ Bayesian debate (Cressie et al. 2009; Lele and Dennis 2009).”
High‐dimensional coexistence based on individual variation: a synthesis of evidence (2010, background): “As described by Berliner (1996, see also Ver Hoef and Frost 2003, Wikle 2003, Clark 2005, Wikle and Berliner 2005, Clark and Gelfand 2006, Royle and Dorazio 2008, Cressie et al. 2009), data at different scales can be coherently assimilated in hierarchical models.”
A climate of uncertainty: accounting for error in climate variables for species distribution models (2015, background): “Hierarchical models, which are constructed as joint conditional probabilities of the underlying process, are commonly used when accounting for different sources of uncertainty in an ecological setting (Cressie et al. 2009). This ideology falls quite naturally in our framework, such that the uncertai”
A guide to Bayesian model selection for ecologists (2015, methodology): “Model selection and Bayesian statistics have become increasingly important tools in the field of ecology (Johnson and Omland 2004, Clark 2005, Cressie et al. 2009, Hobbs 2009).”
Effects of spatial autocorrelation and imperfect detection on species distribution models (2018, methodology): “An explicit modelling of both mechanisms in spatial N- mixture models with CAR or spline spatial processes significantly improved the maps and, at the same time, yielded a more honest assessment of the estimation uncertainty (Cressie et al., 2009).”
Trend estimation in populations with imperfect detection (2009, methodology): “As the quantities in our model have an explicit biological meaning, our model is an explicit, or mechanistic, hierarchical model (Royle & Dorazio 2008), in contrast to the mechanistically more implicit hierarchical models of Link & Sauer (2002), Lande et al. (2003), Dennis et al. (2006), Ver Hoef & ”
Quantifying Vegetation Biophysical Variables from Imaging Spectroscopy Data: A Review on Retrieval Methods (2018, background): “The characterization of uncertainty is a fundamental requirement for postulating correct scientific conclusions from results and for assimilating results into statistical or mechanistic higher-level models (Cressie et al. 2009).”
Geostatistical estimation of forest biomass in interior Alaska combining Landsat-derived tree cover, sampled airborne lidar and field observations (2017, background): “In a hierarchical modeling context, coregionalization frameworks can be constructed using random effects that arise from spatially correlated Gaussian processes and partition variability into spatial and non-spatial components (Banerjee et al., 2014; Cressie et al., 2009).”
Model‐based inference for estimating shifts in species distribution, area occupied and centre of gravity (2016, background): “by maximizing the marginal likelihood of the data without explicitly estimating the sampling process P during parameter estimation (Cressie et al. 2009).”
Hierarchical Species Distribution Models (2016, background): “Hierarchical models are widely used in ecology [14, 15].”
So Many Variables: Joint Modeling in Community Ecology. (2015, background): “This has been driven by the advent of sophisticated hierarchical modeling tools, a watershed for complex problems that arise in ecology [18].”
A structured and dynamic framework to advance traits-based theory and prediction in ecology. (2010, methodology): “In other applications, this has been referred to as using a deterministic process model within a multilevel (hierarchical) statistical model (Cressie et al. 2009).”
Understanding what controls the spatial distribution of fish populations using a multi-model approach (2011, methodology): “…based on AIC criteria, as advocated in Burnham and Anderson (2002) but alternative promising approaches such as Bayesian based methods and hierarchical modelling are available (Soetaert and Herman, 2009, Cressie et al., 2009, Thuiller et al., 2008) albeit only seldom used in marine ecology yet.”