Fast Moment-Based Estimation for Hierarchical Models
- 20 March 2016
- journal article
- research article
- Published by Oxford University Press (OUP) in Journal of the Royal Statistical Society Series B: Statistical Methodology
- Vol. 79 (1) , 267-291
Abstract
Summary: Hierarchical models allow for heterogeneous behaviours in a population while simultaneously borrowing estimation strength across all subpopulations. Unfortunately, existing likelihood-based methods for fitting hierarchical models have high computational demands, and these demands have limited their adoption in large-scale prediction and inference problems. The paper proposes a moment-based procedure for estimating the parameters of a hierarchical model which has its roots in a method originally introduced by Cochran in 1937. The method trades statistical efficiency for computational efficiency. It gives consistent parameter estimates, competitive prediction error performance and substantial computational improvements. When applied to a large-scale recommender system application and compared with a standard maximum likelihood procedure, the method delivers competitive prediction performance while reducing the sequential computation time from hours to minutes.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Fitting parametric random effects models in very large data sets with application to VHA national dataBMC Medical Research Methodology, 2012
- Sparse variational analysis of linear mixed models for large data setsStatistics & Probability Letters, 2011
- Bias reduction in exponential family nonlinear modelsBiometrika, 2009
- Statistical Challenges in Internet Advertising2008
- Sampling for Bayesian Computation with Large DatasetsSSRN Electronic Journal, 2005
- Large sample inference in random coefficient regression modelsCommunications in Statistics - Theory and Methods, 1986
- Mean Squared Error Properties of Empirical Bayes Estimators in a Multivariate Random Effects General Linear ModelJournal of the American Statistical Association, 1985
- Parametric Empirical Bayes Inference: Theory and ApplicationsJournal of the American Statistical Association, 1983
- Estimation in Covariance Components ModelsJournal of the American Statistical Association, 1981
- The theory of least squares when the parameters are stochastic and its application to the analysis of growth curvesBiometrika, 1965