Fast stable restricted maximum likelihood and marginal likelihood estimation of semiparametric generalized linear models

By Simon N. Wood. 2011

7,019 citations recorded by the source corpus.

How researchers see this paper

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

In Statistics and Probability

Citations in the corpus

Generalized additive models for large data sets (2015, methodology): “For example Wood (2011) required storage of an n×p matrix for each smoothing parameter λj .”
Smoothing Parameter and Model Selection for General Smooth Models (2015, methodology): “sition of the block, can be used to make these blocks look like the previous type (by similarity transform). Again the rank is computed. 3. Multi-λblocks will require the reparameterization method of Wood (2011) appendix B to be applied for each new ρproposal, since the numerical problem that the re”
Spatial interpolation of monthly climate data for Finland: comparing the performance of kriging and generalized additive models (2013, methodology): “GAMs were fitted using the R statistical programming environment with package mgcv (Wood 2011).”
Testing the ability of species distribution models to infer variable importance (2019, methodology): “Poor calibration accuracy may be the result of regularization/shrinkage used by MAX and GAMs (Tibshirani 1996; Phillips et al. 2006; Wood 2011) and forward-stagewise-like variable selection in BRTs which functions similarly to the LASSO regularization procedure (Hastie et al. 2009, Ch. 16).”
Nitrogen deposition is negatively related to species richness and species composition of vascular plants and bryophytes in Swiss mountain grassland (2013, positive): “All analyses were done with the software R (R Development Core Team, 2012) using the packages ‘mgcv’ (Wood, 2011), ‘simba’ (Jurasinski and Retzer, 2012) and ‘AED’ (Zuur et al., 2009).”
Sentinel-2 cropland mapping using pixel-based and object-based time-weighted dynamic time warping analysis (2018, methodology): “We de ﬁ ned the temporal patterns using the function dtwSat::create-Patterns (Maus, 2016), which uses a Generalized Additive Model (GAM) (Wood, 2011) to create a smoothed temporal pattern for the NDVI.”
Massive Mortality of a Planktivorous Seabird in Response to a Marine Heatwave (2018, methodology): “Generalized additive models (counts modeled according to a negative binomial distribution; Wood, 2011) were fitted to these data to estimate the density of Cassin’s Auklets as a nonlinear function of distance from shore.”
Comparing the Performance of Statistical Models for Predicting PM10 Concentrations (2014, methodology): “‘mgcv’ package (Wood, 2011) and the ‘quantreg’ package (Koenker, 2013) for BRT, GAM and QRM, respectively.”
Best practice guidance for linear mixed-effects models in psychological science (2019, methodology): “Other named R packages were gamm4 (Wood & Scheipl, 2016), languageR (Baayen, 2013), lmerTest (Kuznetsova, Brockhoff & Christensen, 2016), mgcv (e.g., Wood, 2011), and nlme (Pinheiro et al., 2016).”
A continental‐scale analysis of feral cat diet in Australia (2015, methodology): “We used generalized additive mixed models (GAMMs) in the R package mgcv version 1.7-26 (Wood, 2011) to model the relationship between the FO of each food group as a function of trophic diversity, latitude, longitude, mean precipitation, mean temperature and mean environmental productivity…”
FWDselect : Variable selection algorithm in regression models (2013, neutral): “To estimate the model in (8), FWDselect allows penalised regression splines, implemented in the mgcv library (Wood, 2003, 2004, 2011).”
Seasonal habitat-based density models for a marine top predator, the harbor porpoise, in a dynamic environment (2016, methodology): “Restricted maximum likelihood (REML) with automatic term selection (Marra and Wood 2011) was used for smoothing parameter estimation.”
Match-mismatch dynamics and the relationship between ocean-entry timing and relative ocean recoveries of Central Valley fall run Chinook salmon (2014, methodology): “…of spring transition [τ]) is generalized as follows: log(μ) = log(Nh) + ƒ(t – τ,v) + γ y ƒ() is a smooth function of a generalized additive model (GAM; Wood 2011) allowing for nonlinear effects of release timing on survival with a maximum of ν degrees of freedom, where ν ranges from 1 to 5…”
The cave of Shadows. Addressing the human factor with generalized additive mixed models (2015, methodology): “The analyses in this study were carried out with the help of the mgcv package, version 1.8-12 (Wood, 2006, 2011) and the itsadug package (van Rij et al., 2016) for R (version 3.2.2, R Core Team, 2015).3 These analyses are all exploratory, in that a sequence of increasingly complex models was…”