Smoothing Spline Models with Correlated Random Errors

Abstract Spline-smoothing techniques are commonly used to estimate the mean function in a nonparametric regression model. Their performances depend greatly on the choice of smoothing parameters. Many methods of selecting smoothing parameters such as generalized maximum likelihood (GML), generalized cross-validation (GCV), and unbiased risk (UBR), have been developed under the assumption of independent observations. They tend to underestimate smoothing parameters when data are correlated. In this article, I assume that observations are correlated and that the correlation matrix depends on a parsimonious set of parameters. I extend the GML, GCV, and UBR methods to estimate the smoothing parameters and the correlation parameters simultaneously. I also relate a smoothing spline model to three mixed-effects models. These relationships show that the smoothing spline estimates evaluated at design points are best linear unbiased prediction (BLUP) estimates and that the GML estimates of the smoothing parameters an...

[1]  N. Aronszajn.  Theory of Reproducing Kernels. , 1950 .

[2]  G. Wahba,et al.  Some results on Tchebycheffian spline functions , 1971 .

[3]  T. W. Anderson,et al.  Statistical analysis of time series , 1972 .

[4]  David A. Harville,et al.  Extension of the Gauss-Markov Theorem to Include the Estimation of Random Effects , 1976 .

[5]  G. Wahba.  Bayesian "Confidence Intervals" for the Cross-validated Smoothing Spline , 1983 .

[6]  G. Wahba.  A Comparison of GCV and GML for Choosing the Smoothing Parameter in the Generalized Spline Smoothing Problem , 1985 .

[7]  J. Hart,et al.  Kernel Regression Estimation Using Repeated Measurements Data , 1986 .

[8]  R. Jennrich,et al.  Unbalanced repeated-measures models with structured covariance matrices. , 1986, Biometrics.

[9]  Grace Wahba,et al.  Testing the (Parametric) Null Model Hypothesis in (Semiparametric) Partial and Generalized Spline Models , 1988 .

[10]  B. Yandell.  Spline smoothing and nonparametric regression , 1989 .

[11]  M. C. Jones,et al.  Spline Smoothing and Nonparametric Regression. , 1989 .

[12]  M. Hutchinson,et al.  ON SPLINE SMOOTHING WITH AUTOCORRELATED ERRORS , 1989 .

[13]  J. Raz,et al.  Selecting the smoothing parameter for estimation of slowly changing evoked potential signals. , 1989, Biometrics.

[14]  Scott L. Zeger,et al.  A Frequency Domain Selection Criterion for Regression with Autocorrelated Errors , 1990 .

[15]  Naomi Altman,et al.  Kernel Smoothing of Data with Correlated Errors , 1990 .

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

[17]  Grace Wahba,et al.  Spline Models for Observational Data , 1990 .

[18]  R. Tibshirani,et al.  Generalized Additive Models , 1991 .

[19]  G. Robinson.  That BLUP is a Good Thing: The Estimation of Random Effects , 1991 .

[20]  Robert Kohn,et al.  The Performance of Cross-Validation and Maximum Likelihood Estimators of Spline Smoothing Parameters , 1991 .

[21]  J. Hart.  Kernel regression estimation with time series errors , 1991 .

[22]  Chong Gu,et al.  Cross-Validating Non-Gaussian Data , 1992 .

[23]  T. Gasser,et al.  Choice of bandwidth for kernel regression when residuals are correlated , 1992 .

[24]  R. Kohn,et al.  Nonparametric spline regression with autoregressive moving average errors , 1992 .

[25]  G. Wahba,et al.  Smoothing Spline ANOVA with Component-Wise Bayesian “Confidence Intervals” , 1993 .

[26]  Chong Gu,et al.  Smoothing spline density estimation: theory , 1993 .

[27]  B. Silverman,et al.  Nonparametric Regression and Generalized Linear Models: A roughness penalty approach , 1993 .

[28]  G. Wahba,et al.  Semiparametric Analysis of Variance with Tensor Product Thin Plate Splines , 1993 .

[29]  Jeffrey D. Hart,et al.  Automated Kernel Smoothing of Dependent Data by Using Time Series Cross‐Validation , 1994 .

[30]  B. Silverman,et al.  Nonparametric regression and generalized linear models , 1994 .

[31]  B. Silverman,et al.  Nonparametric Regression and Generalized Linear Models: A roughness penalty approach , 1993 .

[32]  Behavior near zero of the distribution of GCV smoothing parameter estimates , 1995 .

[33]  G. Wahba,et al.  Smoothing spline ANOVA for exponential families, with application to the Wisconsin Epidemiological Study of Diabetic Retinopathy : the 1994 Neyman Memorial Lecture , 1995 .