Search

Computational algorithm and software development have attempted to resolve the computational burden for Bayesian inference (Lunn I et al i ., [5]), including the development of the integrated nested Laplace approximation (INLA) method. The theory of INLA is presented in chapter 2, with an emphasis on latent Gaussian models, Gaussian Markov random fields, and the approximation method itself of INLA. 6 Martino, S. and Rue, H. (2009) Implementing Approximate Bayesian Inference Using Integrated Nested Laplace Approximation: A Manual for the INLA Program. [Extracted from the article]

During the last two decades, we have witnessed the data science revolution which resulted, among other things, in the abundance of statistical and, more general, data science literature aiming at developing methodologies for analysing massive and/or complex data. As mentioned before, I hope that in the future this website may gather a set of exercises/labs/data sets that would enhance the text into a textbook for in-class use. I Readership: i Statisticians, applied mathematicians and practitioners interested in learning the fundamentals of penalty-driven methods of spline smoothing, but also graduate and advanced undergraduate students taking a course in nonparametric regression methods. [Extracted from the article]

The book I Nonparametric Models for Longitudinal Data with Implementation in R i written by Dr. Colin Wu and Dr. Xin Tian contains 15 Chapters categorized in five Parts. The authors systematically discuss the one-step kernel and local polynomial smoothing methods, and then they introduce two-step smoothing methods and provide the rationales for two-step smoothing methods. The authors can add "one-step kernel log likelihood method" for smoothing estimation of time-variant parametric models between Chapters 7 and 8. [Extracted from the article]

Reviews the book "Smoothing Methods in Statistics," by Jeffrey S. Simonoff.