Zusammenfassung
Bisher vorgeschlagene Methoden für die sequentielle Zuordnung bzw. Prognosestellung (z.B. bei Patienten) unter Verwendung wiederholter Messungen werden skizziert. Zur Beurteilung dieser Methoden wird das Zuordnungsproblem in einem allgemeinen parametrischen Rahmen formuliert. Es zeigt sich, daß ein Bayes’scher Zugang der natürlichste ist und die Diskriminanzfunktion auf einem Filtersystem basiert. Für die Verlaufskurven wird eine Modellklasse zugrundegelegt, welches den von Laird & Ware (1982) beschriebenen Modellen für Repeated Measurements verwandt ist. Es wird ein sequentieller Diskriminanzanalyse - Algorithmus entwickelt, der auf einem nichtlinearen (adaptiven) Filter für das Trainings - Sample und einer Kombination von zwei Kaiman - Filtern für die Diskriminanzfunktion beruht. Schließlich analysieren wir ein biologisches Beispiel.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Referenzen
Afifi, A. A., Sacks, S. T., Liu, V. Y., Weil, M. H. and Shubin, H. (1971). Accumulative prognostic index for patients with barbiturate, glutethimide and meprobamate intoxication. New England Journal of Medicine 285, 1497.
Albert, A. (1983). Discriminant analysis based on multivariate response curves: a descriptive approach to dynamic allocation. Statistics in Medicine 2, 95–106.
Albert, A., Chapelle, J. P. and Bourguignat, A. (1984). Dynamic outcome prediction from repeated laboratory measurements made on intensive care unit patients. I. Statistical aspects and logistic models. Scand. J. Clin. Lab. Invest. 44, suppl. 171, 259–268.
Altham, P. M. E. (1984). Improving the precision of estimation by fitting a model. J. R. Statist. Soc. B, 46, 118–119.
Anderson, B. D. O. and Moore, J. B. (1979). Optimal Filtering. Englewood Cliffs, N. J.: Prentice-Hall.
Azen, S. P. and Afifi, A. A. (1972a). Two models for assessing prognosis on the basis of successive observations. Math. Biosci. 14, 169.
Azen, S. P. and Afifi, A. A. (1972b). Asymptotic and small-sample behavior of estimated Bayes rules for classifying time-dependent observations. Biometrics 28, 989–998.
Azen, S. P., Garcia-Pena, J. and Afifi, A. (1975). Classification of time-dependent observations: The exponential model and the robustness of the linear model. Biom. J. 17, 203–212.
Browdy, B. L. (1978). A comparison of procedures for the classification of multivariate time-dependent data. Ph. D. Thesis, Univ. of California, Los Angeles.
Browdy, B. L. and Chang, P. C. (1982). Bayes procedures for the classification of multiple polynomial trends with dependent residuals. J. Amer. Statist. Assoc. 77, 483–487.
Chi, E. M. and Reinsei, G. C. (1989). Models for longitudinal data with random effects and AR(1) errors. J. Amer. Statist Assoc. 84, 452–459.
Christi, H. L. (1976). Time dependence and Bayesian approach. In de Dombal, F. T. and Gremy, F. (eds.) Decision Making and Medical Care. 467–476. Amsterdam: North-Holland Publishing Company.
Crowder, M. J. and Hand, D. J. (1990). Analysis of Repeated Measures. London: Chapman and Hall.
De Jong, P. (1988). The likelihood for a state space model. Biometrika 75, 165–169.
Dennis, J. E., Gay, D. M. and Welsch, R. E. (1981). An adaptive nonlinear least-squares algorithm. ACM Transactions on Mathematical Software 7, 348–383.
Diggle, P. J. (1988). An approach to the analysis of repeated measurements. Biometrics 44, 959–971.
Diggle, P. J. (1990). Time series: a bio statistical introduction. Oxford: Oxford Univ. Press.
Ferrante, M. and Runggaldier, W. J. (1990). On necessary conditions for the existence of finite-dimensional filters in discrete time. Systems & Control Letters 14, 63–69.
Geary, D. N. (1989). Modelling the covariance structure of repeated measurements. Biometrics 45, 1183–1195.
Goodrich, R. L. and Caines, P. E. (1979). Linear system identification from nonstatio-nary cross-sectional data. IEEE Trans, on Automatic Control 24, 403–411.
Grossmann, W. (1985). Diskrimination und Klassifikation von Verlaufskurven. In: Neuere Verfahren der nichtparametrischen Statistik. G. C. Pflug (Ed.) ( Medizin. Inform, und Statistik, Vol. 60 ). Berlin: Springer.
Harville, D. A. (1974). Bayesian inference for variance components using only error contrasts. Biometrika 61, 383–385.
Harville, D. A. (1976). Extensions of the Gauss-Markov theorem to include the estimation of random effects. Annals of Statistics 4, 384–395.
Harville, D. A. (1977). Maximum likelihood approaches to variance component estimation and to related problems. J. Amer. Statist. Assoc. 72, 320–340.
Jennrich, R. I. and Schluchter, M. D. (1986). Unbalanced repeated-measures models with structured covariance matrices. Biometrics 42, 805–820.
Jones, R. H. and Ackerson, L. M. (1990). Serial correlation in unequally spaced longitudinal data. Biometrika 77, 721–731.
Jones, R. H. and Boadi-Boateng, F. (1991). Unequally spaced longitudinal data with AR(1) serial correlation. Biometries 47, 161–175.
Kaiman, R. E. (1960). A new approach to linear filtering and prediction problems. Trans. ASME, J. Basic Engineering 82, 35–45.
Laird, N. M. and Ware, J. H. (1982). Random-effects models for longitudinal data. Biometrics 38, 963–974.
Lee, J. C. (1977). Bayesian classification of data from growth curves. South African Statist J. 11, 155–166.
Lee, J. C. (1982). Classification of growth curves. In: Krishnaiah, P. R. and Kanal, L. N. (eds.) Handbook of Statistics, 2, 121–137. Chichester: Wiley.
Mansour, H., Nordheim, E. V., and Rutledge, J. J. (1985). Maximum likelihood estimation of variance components in repeated measures designs assuming autoregressive errors. Biometrics 41, 287–294.
Maybeck, P. S. ( 1979, 1982). Stochastic Models, Estimation, and Control. Vol. 1, Vol. 2. New York: Academic Press.
Mehra, R. K. (1972). Approaches to adaptive filtering. IEEE Trans, on Autom. Control 17, 693–698.
Morrison, D. F. (1967). Multivariate statistical methods. New York: McGraw-Hill.
Nagel, P. J. A. and de Waal, D. J. (1979). Bayesian classification, estimation and prediction of growth curves. South African Statist. J. 13, 127–137.
Sallas, W. M. and Harville, D. A. (1981). Best linear recursive estimation for mixed linear models. J. Amer. Statist. Assoc. 76, 860–869.
Sallas, W. M. and Ilarville, D. A. (1988). Noninformative priors and restricted maximum likelihood estimation in the Kaiman filter. In: J. C. Spall (Ed.) Bayesian Analysis of Time Series and Dynamic Models. New York: Marcel Dekker.
Schnatter, S. (1988). Dynamische Bayes’sche Modelle und ihre Anwendung zur hydrologischen Kurzfristvorhersage. Dissertation. Technische Universität Wien.
Schneider, W. (1986). Der Kaimanfilter als Instrument zur Diagnose und Schätzung variabler Parameter in ökonometrischen Modellen. Heidelberg, Wien: Physica-Verlag.
Shumway, R. H. (1982). Discriminant analysis for time series. In: Krishnaiah, P. R. and Kanal, L. N. (eds.) Handbook of Statistics, 2, 1–46. Chichester: Wiley.
Ulm, K. (1984). Classification on the basis of successive observations. Biometrics 40, 1131–1136.
van Schuppen, J. H. (1979). Stochastic filtering theory: a discussion of concepts, methods, and results. In M. Kohlmann and W. Vogel, (eds.), Stochastic Control Theory and Stochastic Differential Systems, Lect. Notes in Control and Inform. Sei. No. 16, 209–226. Berlin: Springer.
Welch, M. E. (1987). Classification methods for linear dynamic models. Unpublished Ph. D. Thesis, Univ. of California, Los Angeles.
Wilson, P. D. (1988). Autoregressive growth curve and Kaiman filtering. Statistics in Medicine 7, 73–86.
Wilson, P. D., Hebel, J. R., and Sherwin, R. (1981). Screening and diagnosis when within-individual observations are Markov-dependent. Biometrics 37, 553–565.
Zeger, S. L., Liang, K. -Y. and Albert, P. S. (1988). Models for longitudinal data: a generalized estimating equation approach. Biometrics 44, 1049–1060.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Stronegger, WJ. (1991). Kalman Filter zur On-Line-Diskriminanz-Analyse von Verlaufskurven. In: Seeber, G.U.H., Minder, C.E. (eds) Multivariate Modelle. Medizinische Informatik, Biometrie und Epidemiologie, vol 74. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-95669-0_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-95669-0_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-54511-8
Online ISBN: 978-3-642-95669-0
eBook Packages: Springer Book Archive