Efficient two-dimensional smoothing with PP-spline ANOVA mixed models and nested bases

Low-rank smoothing techniques have gained much popularity in non-standard regression modeling. In particular, penalized splines and tensor product smooths are used as flexible tools to study non-parametric relationships among several covariates. The use of standard statistical software facilitates their use for several types of problems and applications. However, when interaction terms are considered in the modeling, and multiple smoothing parameters need to be estimated standard software does not work well when datasets are large or higher-order interactions are included or need to be tested. In this paper, a general approach for constructing and estimating bivariate smooth models for additive and interaction terms using penalized splines is proposed. The formulation is based on the mixed model representation of the smooth-ANOVA model by Lee and Durban (in?press), and several nested models in terms of random effects components are proposed. Each component has a clear interpretation in terms of function shape and model identifiability constraints. The term P S -ANOVA is coined for this type of models. The estimation method is relatively straightforward based on the algorithm by Schall (1991) for generalized linear mixed models. Further, a simplification of the smooth interaction term is used by constructing lower-rank basis (nested basis). Finally, some simulation studies and real data examples are presented to evaluate the new model and the estimation method.

[1]  Fabian Scheipl,et al.  Straightforward intermediate rank tensor product smoothing in mixed models , 2012, Statistics and Computing.

[2]  Zehua Chen.  Fitting Multivariate Regression Functions by Interaction Spline Models , 1993 .

[3]  M. Durbán,et al.  Generalized linear array models with applications to multidimensional smoothing , 2006 .

[4]  M. Wand,et al.  Smoothing with Mixed Model Software , 2004 .

[5]  M. Crawley.  Mixed‐Effects Models , 2007 .

[6]  Dae-Jin Lee,et al.  P-spline ANOVA-type interaction models for spatio-temporal smoothing , 2011 .

[7]  Yuedong Wang.  Smoothing Spline ANOVA , 2011 .

[8]  R. Tibshirani,et al.  Linear Smoothers and Additive Models , 1989 .

[9]  N. Breslow,et al.  Approximate inference in generalized linear mixed models , 1993 .

[10]  S. Lang,et al.  Bayesian P-Splines , 2004 .

[11]  R. Tibshirani,et al.  Generalized additive models for medical research , 1986, Statistical methods in medical research.

[12]  J. Nelder,et al.  Generalized Linear Models with Random Effects: Unified Analysis via H-likelihood , 2006 .

[13]  R. Tibshirani,et al.  Varying‐Coefficient Models , 1993 .

[14]  Paul H. C. Eilers,et al.  Smoothing and forecasting mortality rates , 2004 .

[15]  Paul H. C. Eilers,et al.  Fast and compact smoothing on large multidimensional grids , 2006, Comput. Stat. Data Anal..

[16]  H. Akaike.  Maximum likelihood identification of Gaussian autoregressive moving average models , 1973 .

[17]  Paul H. C. Eilers,et al.  Flexible smoothing with B-splines and penalties , 1996 .

[18]  A. Bowman,et al.  Applied smoothing techniques for data analysis : the kernel approach with S-plus illustrations , 1999 .

[19]  Brian D Marx,et al.  Generalized Linear Additive Smooth Structures , 2002 .

[20]  R. Todd Ogden,et al.  Smoothing parameter selection for a class of semiparametric linear models , 2009 .

[21]  Pravin K. Trivedi,et al.  Regression Analysis of Count Data , 1998 .

[22]  S. Wood.  Low‐Rank Scale‐Invariant Tensor Product Smooths for Generalized Additive Mixed Models , 2006, Biometrics.

[23]  Susan A. Murphy,et al.  Monographs on statistics and applied probability , 1990 .

[24]  R. Schall.  Estimation in generalized linear models with random effects , 1991 .

[25]  Otis Dudley Duncan,et al.  A socioeconomic index for all occupations. , 1996 .

[26]  S. Wood.  Fast stable restricted maximum likelihood and marginal likelihood estimation of semiparametric generalized linear models , 2011 .

[27]  D. Titterington,et al.  Discussion: Linear Smoothers and Additive Models , 1989 .

[28]  G. Wahba.  Spline models for observational data , 1990 .

[29]  Stefan Lang,et al.  Simultaneous selection of variables and smoothing parameters in structured additive regression models , 2008, Comput. Stat. Data Anal..

[30]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[31]  Helmut Küchenhoff,et al.  Size and power of tests for a zero random effect variance or polynomial regression in additive and linear mixed models , 2008, Comput. Stat. Data Anal..