Kelly J. Iknayan Gurutzeta Guillera-Arroita Elise Zipkin Robert Dorazio J. Andrew Royle Marc Kery Steven R. Beissinger 2016 <p><span>Warton </span><i>et al.</i> <span id="bbib0065"><a id="ancbbib0065" class="intra_ref" href="http://www.sciencedirect.com/science/article/pii/S0169534716301173#bib0065" data-mce-href="http://www.sciencedirect.com/science/article/pii/S0169534716301173#bib0065">[1]</a></span><span> advance community ecology by describing a statistical framework that can jointly model abundances (or distributions) across many taxa to quantify how community properties respond to environmental variables. This framework specifies the effects of both measured and unmeasured (latent) variables on the abundance (or occurrence) of each species. Latent variables are random effects that capture the effects of both missing environmental predictors and correlations in parameter values among different species. As presented in Warton </span><i>et al.</i><span>, however, the joint modeling framework fails to account for the common problem of detection or measurement errors that always accompany field sampling of abundance or occupancy, and are well known to obscure species- and community-level inferences.</span></p> application/pdf 10.1016/j.tree.2016.07.009 en Elsevier Incorporating imperfect detection into joint models of communites: A response to Warton <i>et al.</i> article