So Many Variables: Joint Modeling in Community Ecology.
Citations
632 citations
588 citations
Cites background or methods from "So Many Variables: Joint Modeling i..."
...If we exclude the environmental covariates X from the analysis, then the latent variables behind an association matrix can be viewed as a model-based ordination (Warton et al. 2015b)....
[...]
...To overcome these limitations, community ecologists are showing increasing interest in model-based approaches (Warton et al. 2015a,b)....
[...]
...To facilitate the estimation of such matrices, we use a latent variable approach, which allows a parameter-sparse representation of the matrix X through latent factors and their loadings (for mathematical details see Warton et al. 2015b; Ovaskainen et al. 2016a,b)....
[...]
...If environmental covariates are included in the analysis, then an association matrix corresponds to a residual ordination, which describes those co-occurrences that cannot be explained by shared responses to environmental covariates (Hui et al. 2015; Warton et al. 2015b)....
[...]
...Another way is the use of joint species distribution models, which explicitly acknowledge the multivariate nature of species assemblages, allowing one to gather more mechanistic and predictive insights into assembly processes (Warton et al. 2015b)....
[...]
332 citations
Cites background or methods from "So Many Variables: Joint Modeling i..."
...Although this argument may suggest that using models that account for environmental filtering is appropriate (e.g. JSDMs, Ovaskainen et al., 2010; Warton et al., 2015; D’Amen et al., 2018), it should not be interpreted this way....
[...]
...A potentially interesting way to approach this problem is to use latent variable models (e.g. Warton et al., 2015; Ovaskainen et al., 2017) because latent variables may be able to capture some unmeasured environmental variables....
[...]
..., 2014) were developed and predict the distribution of a set of species that are potentially interdependent based on abiotic factors using the entire incidence matrix (€ Ozesmi & € Ozesmi 1999; Latimer et al., 2009; Ovaskainen et al., 2010, 2016, 2017; Clark et al., 2014; Kaldhusdal et al., 2015; Warton et al., 2015; Hui, 2016; Clark et al., 2017; Staniczenko et al., 2017)....
[...]
...…are potentially interdependent based on abiotic factors using the entire incidence matrix (€Ozesmi & €Ozesmi 1999; Latimer et al., 2009; Ovaskainen et al., 2010, 2016, 2017; Clark et al., 2014; Kaldhusdal et al., 2015; Warton et al., 2015; Hui, 2016; Clark et al., 2017; Staniczenko et al., 2017)....
[...]
271 citations
Cites background from "So Many Variables: Joint Modeling i..."
...Climate, Ecology, and Environ‐ mental The analysis of noisy ecological data [25], variables in ecology modelling [26], number of counts termites [27], community ecology and integrating species, traits, environmental, space [28], parameter in rainfall forecasting [29, 30], global climate zone [31], local climate zone [32], environmental noise pollution [33], urban pollution [34, 35], rainfall spatial temporal [36], flash flood hazard [37, 38], landslide [39], earthquake damage detection using curvilinear features [40], earthquake classifiers using stochastic reconstruction [41] and tsunami [42]...
[...]
References
50,607 citations
"So Many Variables: Joint Modeling i..." refers methods in this paper
...This is not straightforward to implement (for lme4, using a modular approach as in [89])....
[...]
17,111 citations
"So Many Variables: Joint Modeling i..." refers background in this paper
...The generalized estimating equations (GEE) approach [40] can and has been used for a similar purpose [41], although it is best suited to situations where the correlation is treated as a nuisance rather than being of interest in itself [42]....
[...]
16,079 citations
"So Many Variables: Joint Modeling i..." refers background in this paper
...The most common approaches (as usual) are maximum likelihood [78] and Bayesian estimation [79]....
[...]
14,433 citations
12,328 citations