Previous |  Up |  Next

Article

Title: Asymmetric recursive methods for time series (English)
Author: Cipra, Tomáš
Language: English
Journal: Applications of Mathematics
ISSN: 0862-7940 (print)
ISSN: 1572-9109 (online)
Volume: 39
Issue: 3
Year: 1994
Pages: 203-214
Summary lang: English
.
Category: math
.
Summary: The problem of asymmetry appears in various aspects of time series modelling. Typical examples are asymmetric time series, asymmetric error distributions and asymmetric loss functions in estimating and predicting. The paper deals with asymmetric modifications of some recursive time series methods including Kalman filtering, exponential smoothing and recursive treatment of Box-Jenkins models. (English)
Keyword: asymmetric recursive methods
Keyword: time series
Keyword: Kalman filter
Keyword: exponential smoothing
Keyword: asymmetric time series
Keyword: autoregressive model
Keyword: split-normal distribution
MSC: 60G35
MSC: 62M10
MSC: 62M20
MSC: 93E11
idZBL: Zbl 0806.62075
idMR: MR1273633
DOI: 10.21136/AM.1994.134253
.
Date available: 2009-09-22T17:43:50Z
Last updated: 2020-07-28
Stable URL: http://hdl.handle.net/10338.dmlcz/134253
.
Reference: [1] K. Campbell: Recursive computation of $M$-estimates for the parameters of a finite autoregressive process.Annals of Statistics 10 (1982), 442–453. Zbl 0492.62076, MR 0653519, 10.1214/aos/1176345785
Reference: [2] T. Cipra: Some problems of exponential smoothing.Aplikace matematiky 34 (1989), 161–169. Zbl 0673.62079, MR 0990303
Reference: [3] T. Cipra: Robust exponential smoothing.Journal of Forecasting 11 (1992), 57–69. 10.1002/for.3980110106
Reference: [4] T. Cipra and R. Romera: Robust Kalman filter and its application in time series analysis.Kybernetika 27 (1991), 481–494. MR 1150938
Reference: [5] T. Cipra and R. Romera: Recursive time series methods in $L_1$-norm.$L_1$-Statistical Analysis and Related Methods (Y. Dodge, ed.), North Holland, Amsterdam, 1992, pp. 233–243. MR 1214835
Reference: [6] T. Cipra, A. Rubio and L. Canal: Robustified smoothing and forecasting procedures.Czechoslovak Journal of Operations Research 1 (1992), 41–56.
Reference: [7] C. W. J. Granger: Prediction with a generalized cost of error function.Operational Research Quarterly 20 (1969), 199–207. Zbl 0174.21901, MR 0295497, 10.1057/jors.1969.52
Reference: [8] E. J. Hannan: Multiple Time Series.Wiley, New York, 1970. Zbl 0211.49804, MR 0279952
Reference: [9] P. Lefrançois: Allowing for asymmetry in forecast errors: Results from a Monte-Carlo study.International Journal of Forecasting 5 (1989), 99–110. 10.1016/0169-2070(89)90067-8
Reference: [10] W. K. Newey and J. L. Powell: Asymmetric least squares estimation and testing.Econometrica 55 (1987), 819–847. MR 0906565, 10.2307/1911031
Reference: [11] H. Robbins and D. Siegmund: A convergence theorem for non negative almost supermartingales and some applications.Optimizing Methods in Statistics (J. S. Rustagi, ed.), Academic Press, New York, 1971, pp. 233–257. MR 0343355
Reference: [12] K. Sejling, H. Madsen, J. Holst, U. Holst and J.-E. Englund: A method for recursive robust estimation of $AR$-parameters.Preprint, Technical University of Lyngby, Denmark and University of Lund, Sweden, 1990.
Reference: [13] M. J. Silvapulla: On $M$-method in growth curve analysis with asymmetric errors.Journal of Statistical Planning and Inference 32 (1992), 303–309. MR 1190200, 10.1016/0378-3758(92)90013-I
Reference: [14] W. E. Wecker: Asymmetric time series.Journal of the American Statistical Association 76 (1981), 16–21. 10.1080/01621459.1981.10477595
.

Files

Files Size Format View
AplMat_39-1994-3_3.pdf 1.141Mb application/pdf View/Open
Back to standard record
Partner of
EuDML logo