Recursive residuals and model diagnostics for normal and non-normal state space models

Model diagnostics for normal and non-normal state space models are based on recursive residuals which are defined from the one-step ahead predictive distribution. Routine calculation of these residuals is discussed in detail. Various diagnostic tools are suggested to check, for example, for wrong observation distributions and for autocorrelation. The paper also discusses such topics as model diagnostics for discrete time series and model discrimination via Bayes factors. The case studies cover environmental applications such as analysing a time series of the number of daily rainfall occurrences and a time series of daily sulfur dioxide emissions.

[1]  Chris Chatfield,et al.  The Analysis of Time Series , 1990 .

[2]  George E. P. Box,et al.  Sampling and Bayes' inference in scientific modelling and robustness , 1980 .

[3]  D. Spiegelhalter,et al.  Bayes Factors for Linear and Log‐Linear Models with Vague Prior Information , 1982 .

[4]  Ludwig Fahrmeir,et al.  REGRESSION MODELS FOR NON‐STATIONARY CATEGORICAL TIME SERIES , 1987 .

[5]  S. Zeger,et al.  Markov regression models for time series: a quasi-likelihood approach. , 1988, Biometrics.

[6]  A. C. Davison,et al.  Deviance residuals and normal scores plots , 1989 .

[7]  G. Kitagawa.  Non-Gaussian State—Space Modeling of Nonstationary Time Series , 1987 .

[8]  Andrew Harvey,et al.  Forecasting, Structural Time Series Models and the Kalman Filter. , 1991 .

[9]  Jim Q. Smith,et al.  Diagnostic checks of non‐standard time series models , 1985 .

[10]  C. D. Kemp,et al.  Kendall's Advanced Theory of Statistics, Volume 1, Distribution Theory. , 1988 .

[11]  J. Durbin,et al.  Techniques for Testing the Constancy of Regression Relationships Over Time , 1975 .

[12]  Andrew Harvey,et al.  Time Series Models for Count or Qualitative Observations , 1989 .

[13]  A. Hedayat,et al.  Independent Stepwise Residuals for Testing Homoscedasticity , 1970 .

[14]  Sylvia Schnatter.  Integration-based Kalman-filtering for a dynamic generalized linear trend model , 1992 .

[15]  Sylvia Frühwirth-Schnatter.  Monitoring von ökologischen und biometrischen Prozessen mit statistischen Filtern , 1991 .

[16]  M. West,et al.  Dynamic Generalized Linear Models and Bayesian Forecasting , 1985 .

[17]  Reinhold Hatzinger,et al.  Single and twin-heaps as natural data structures for percentile point simulation algorithms , 1993 .

[18]  G. Kitagawa.  Non-Gaussian state space modeling of time series , 1987, 26th IEEE Conference on Decision and Control.

[19]  L. Fahrmeir.  Posterior Mode Estimation by Extended Kalman Filtering for Multivariate Dynamic Generalized Linear Models , 1992 .

[20]  Irene A. Stegun,et al.  Handbook of Mathematical Functions. , 1966 .

[21]  S. Geisser,et al.  A Predictive Approach to Model Selection , 1979 .

[22]  D. Pregibon.  Logistic Regression Diagnostics , 1981 .

[23]  A. P. Dawid,et al.  Present position and potential developments: some personal views , 1984 .

[24]  E. S. Pearson,et al.  Tests for departure from normality: Comparison of powers , 1977 .

[25]  D. Spiegelhalter,et al.  Bayes Factors and Choice Criteria for Linear Models , 1980 .

[26]  David R. Cox.  The analysis of binary data , 1970 .

[27]  S. Frühwirth-Schnatter.  Applied state space modelling of non-Gaussian time series using integration-based Kalman filtering , 1994 .

[28]  A. C. Atkinson,et al.  Two graphical displays for outlying and influential observations in regression , 1981 .

[29]  J. Berger,et al.  Testing Precise Hypotheses , 1987 .

[30]  Wolfgang Schneider,et al.  Der Kalmanfilter als Instrument zur Diagnose und Schätzung variabler Parameter in ökonometrischen Modellen , 1986 .

[31]  M. Rosenblatt.  Remarks on a Multivariate Transformation , 1952 .

[32]  John Hinde,et al.  Statistical Modelling in GLIM. , 1990 .

[33]  L. Fahrmeir,et al.  Smoothing in dynamic generalized linear models by Gibbs sampling , 1992 .

[34]  L. Shenton,et al.  Omnibus test contours for departures from normality based on √b1 and b2 , 1975 .

[35]  S. Frühwirth-Schnatter.  Bayesian Model Discrimination and Bayes Factors for Linear Gaussian State Space Models , 1995 .

[36]  Anthony C. Atkinson,et al.  Regression Diagnostics, Transformations and Constructed Variables , 1982 .

[37]  M. Kendall,et al.  Kendall's Advanced Theory of Statistics: Volume 1 Distribution Theory , 1987 .

[38]  Mark Sharefkin,et al.  Uncertainty and Forecasting of Water Quality: Reflections of an Ignorant Bayesian , 1983 .