Fast stable restricted maximum likelihood and marginal likelihood estimation of semiparametric generalized linear models
Reads0
Chats0
TLDR
In this article, a Laplace approximation is used to obtain an approximate restricted maximum likelihood (REML) or marginal likelihood (ML) for smoothing parameter selection in semiparametric regression.Abstract:
Summary. Recent work by Reiss and Ogden provides a theoretical basis for sometimes preferring restricted maximum likelihood (REML) to generalized cross-validation (GCV) for smoothing parameter selection in semiparametric regression. However, existing REML or marginal likelihood (ML) based methods for semiparametric generalized linear models (GLMs) use iterative REML or ML estimation of the smoothing parameters of working linear approximations to the GLM. Such indirect schemes need not converge and fail to do so in a non-negligible proportion of practical analyses. By contrast, very reliable prediction error criteria smoothing parameter selection methods are available, based on direct optimization of GCV, or related criteria, for the GLM itself. Since such methods directly optimize properly defined functions of the smoothing parameters, they have much more reliable convergence properties. The paper develops the first such method for REML or ML estimation of smoothing parameters. A Laplace approximation is used to obtain an approximate REML or ML for any GLM, which is suitable for efficient direct optimization. This REML or ML criterion requires that Newton–Raphson iteration, rather than Fisher scoring, be used for GLM fitting, and a computationally stable approach to this is proposed. The REML or ML criterion itself is optimized by a Newton method, with the derivatives required obtained by a mixture of implicit differentiation and direct methods. The method will cope with numerical rank deficiency in the fitted model and in fact provides a slight improvement in numerical robustness on the earlier method of Wood for prediction error criteria based smoothness selection. Simulation results suggest that the new REML and ML methods offer some improvement in mean-square error performance relative to GCV or Akaike's information criterion in most cases, without the small number of severe undersmoothing failures to which Akaike's information criterion and GCV are prone. This is achieved at the same computational cost as GCV or Akaike's information criterion. The new approach also eliminates the convergence failures of previous REML- or ML-based approaches for penalized GLMs and usually has lower computational cost than these alternatives. Example applications are presented in adaptive smoothing, scalar on function regression and generalized additive model selection.read more
Citations
More filters
Journal ArticleDOI
Genome sequence-based species delimitation with confidence intervals and improved distance functions
TL;DR: Despite the high accuracy of GBDP-based DDH prediction, inferences from limited empirical data are always associated with a certain degree of uncertainty, so it is crucial to enrich in-silico DDH replacements with confidence-interval estimation, enabling the user to statistically evaluate the outcomes.
Journal ArticleDOI
brms: An R Package for Bayesian Multilevel Models Using Stan
TL;DR: The brms package implements Bayesian multilevel models in R using the probabilistic programming language Stan, allowing users to fit linear, robust linear, binomial, Poisson, survival, ordinal, zero-inflated, hurdle, and even non-linear models all in a multileVEL context.
Journal ArticleDOI
Advanced Bayesian Multilevel Modeling with the R Package brms
TL;DR: Brms provides an intuitive and powerful formula syntax, which extends the well known formula syntax of lme4, which is introduced in detail and demonstrated its usefulness with four examples, each showing other relevant aspects of the syntax.
Journal ArticleDOI
The Allelic Landscape of Human Blood Cell Trait Variation and Links to Common Complex Disease
William J. Astle,Heather Elding,Heather Elding,Tao Jiang,Dave Allen,Dace Ruklisa,Dace Ruklisa,Alice L. Mann,Daniel Mead,Heleen J. Bouman,Fernando Riveros-Mckay,Myrto Kostadima,Myrto Kostadima,Myrto Kostadima,John J. Lambourne,John J. Lambourne,Suthesh Sivapalaratnam,Suthesh Sivapalaratnam,Kate Downes,Kate Downes,Kousik Kundu,Kousik Kundu,Lorenzo Bomba,Kim Berentsen,John Bradley,John Bradley,Louise C. Daugherty,Louise C. Daugherty,Olivier Delaneau,Kathleen Freson,Stephen F. Garner,Stephen F. Garner,Luigi Grassi,Luigi Grassi,Jose A. Guerrero,Jose A. Guerrero,Matthias Haimel,Eva M. Janssen-Megens,Anita Kaan,Mihir A Kamat,Bowon Kim,Amit Mandoli,Jonathan Marchini,Jonathan Marchini,Joost H.A. Martens,Stuart Meacham,Stuart Meacham,Karyn Megy,Karyn Megy,Jared O'Connell,Jared O'Connell,Romina Petersen,Romina Petersen,Nilofar Sharifi,S.M. Sheard,James R Staley,Salih Tuna,Martijn van der Ent,Klaudia Walter,Shuang-Yin Wang,Eleanor Wheeler,Steven P. Wilder,Valentina Iotchkova,Valentina Iotchkova,Carmel Moore,Jennifer G. Sambrook,Jennifer G. Sambrook,Hendrik G. Stunnenberg,Emanuele Di Angelantonio,Emanuele Di Angelantonio,Emanuele Di Angelantonio,Stephen Kaptoge,Stephen Kaptoge,Taco W. Kuijpers,Enrique Carrillo-de-Santa-Pau,David Juan,Daniel Rico,Alfonso Valencia,Lu Chen,Lu Chen,Bing Ge,Louella Vasquez,Tony Kwan,Diego Garrido-Martín,Stephen Watt,Ying Yang,Roderic Guigó,Stephan Beck,Dirk S. Paul,Dirk S. Paul,Tomi Pastinen,David Bujold,Guillaume Bourque,Mattia Frontini,Mattia Frontini,Mattia Frontini,John Danesh,David J. Roberts,David J. Roberts,Willem H. Ouwehand,Adam S. Butterworth,Adam S. Butterworth,Adam S. Butterworth,Nicole Soranzo +103 more
TL;DR: A genome-wide association analysis in the UK Biobank and INTERVAL studies is performed, providing evidence of shared genetic pathways linking blood cell indices with complex pathologies, including autoimmune diseases, schizophrenia, and coronary heart disease and evidence suggesting previously reported population associations betweenBlood cell indices and cardiovascular disease may be non-causal.
Journal ArticleDOI
Marine Taxa Track Local Climate Velocities
Malin L. Pinsky,Malin L. Pinsky,Boris Worm,Michael J. Fogarty,Jorge L. Sarmiento,Simon A. Levin +5 more
TL;DR: Using nearly 50 years of coastal survey data on >350 marine taxa, Pinsky et al. found that climate velocity was a much better predictor of patterns of change than individual species' characteristics or life histories.
References
More filters
BookDOI
Modern Applied Statistics with S
W. N. Venables,Brian D. Ripley +1 more
TL;DR: A guide to using S environments to perform statistical analyses providing both an introduction to the use of S and a course in modern statistical methods.
Journal ArticleDOI
Generalized Linear Models
TL;DR: This is the rst book on generalized linear models written by authors not mostly associated with the biological sciences, and it is thoroughly enjoyable to read.
Journal ArticleDOI
Generalized Linear Models
TL;DR: In this paper, the authors used iterative weighted linear regression to obtain maximum likelihood estimates of the parameters with observations distributed according to some exponential family and systematic effects that can be made linear by a suitable transformation.
Journal ArticleDOI
Random-effects models for longitudinal data
Nan M. Laird,James H. Ware +1 more
TL;DR: In this article, a unified approach to fitting two-stage random-effects models, based on a combination of empirical Bayes and maximum likelihood estimation of model parameters and using the EM algorithm, is discussed.
Book
Spline models for observational data
TL;DR: In this paper, a theory and practice for the estimation of functions from noisy data on functionals is developed, where convergence properties, data based smoothing parameter selection, confidence intervals, and numerical methods are established which are appropriate to a number of problems within this framework.