Bootstrap Approximation to Prediction MSE for State–Space Models with Estimated Parameters

We propose simple parametric and nonparametric bootstrap methods for estimating the prediction mean square error (PMSE) of state vector predictors that use estimated model parameters. As is well known, substituting the model parameters by their estimates in the theoretical PMSE expression that assumes known parameter values results in underestimation of the true PMSE. The parametric method consists of generating parametrically a large number of bootstrap series from the model fitted to the original series, re-estimating the model parameters for each series using the same method as used for the original series and then estimating the separate components of the PMSE. The nonparametric method generates the series by bootstrapping the standardized innovations estimated for the original series. The bootstrap methods are compared with other methods considered in the literature in a simulation study that also examines the robustness of the various methods to non-normality of the model error terms. Application of the bootstrap method to a model fitted to employment ratios in the USA that contains 18 unknown parameters, estimated by a three-step procedure yields unbiased PMSE estimators. Copyright 2005 Blackwell Publishing Ltd.

[1]  James D. Hamilton.  A standard error for the estimated state vector of a state-space model , 1986 .

[2]  Siem Jan Koopman,et al.  Time Series Analysis of Non-Gaussian Observations Based on State Space Models from Both Classical and Bayesian Perspectives , 1999 .

[3]  D. Stoffer,et al.  Bootstrapping State-Space Models: Gaussian Maximum Likelihood Estimation and the Kalman Filter , 1991 .

[4]  Benoit Quenneville,et al.  Bayesian Prediction Mean Squared Error for State Space Models with Estimated Parameters , 2000 .

[5]  Danny Pfeffermann,et al.  Estimation of Autocorrelations of Survey Errors with Application to Trend Estimation in Small Areas , 1998 .

[6]  David A. Harville,et al.  Best Linear Recursive Estimation for Mixed Linear Models , 1981 .

[7]  John Tsimikas,et al.  Reml and best linear unbiased prediction in state space models , 1994 .

[8]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1972 .

[9]  J. Angus.  Forecasting, Structural Time Series and the Kalman Filter , 1992 .

[10]  Norio Watanabe.  NOTE ON THE KALMAN FILTER WITH ESTIMATED PARAMETERS , 1985 .

[11]  Jiming Jiang,et al.  Mixed model prediction and small area estimation , 2006 .

[12]  D. Pfeffermann.  Small Area Estimation‐New Developments and Directions , 2002 .

[13]  P. Lahiri,et al.  Hierarchical Bayes Estimation of Unemployment Rates for the States of the U.S. , 1999 .

[14]  Robert Kohn,et al.  Prediction mean squared error for state space models with estimated parameters , 1986 .

[15]  P. Hall,et al.  On bootstrap resampling and iteration , 1988 .

[16]  David S. Stoffer,et al.  State Space and Unobserved Component Models: Resampling in state space models , 2004 .

[17]  P. D. Jong.  Smoothing and Interpolation with the State-Space Model , 1989 .

[18]  D. Pfeffermann,et al.  Bayesian versus frequentist measures of error in small area estimation , 1998 .

[19]  Siem Jan Koopman,et al.  Stamp 5.0 : structural time series analyser, modeller and predictor , 1996 .

[20]  M. Chavance.  [Jackknife and bootstrap]. , 1992, Revue d'epidemiologie et de sante publique.