zbMATH — the first resource for mathematics

Data analysis for numerical and categorical individual time-series. (English) Zbl 0587.62172
Principal components analysis and correspondence analysis may be generalized to handle time-dependent data. For real-valued data the basic tool is the Karhunen-Loève decomposition. For categorical processes harmonic analysis is presented in terms of reciprocal averaging. Details are given for approximated and interpolated solutions.

62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)
62H25 Factor analysis and principal components; correspondence analysis
Full Text: DOI
[1] ’Méthodes statistiques et numériques de l’analyse harmonique’, Annales de l’INSEE no. 15, 3–101 (1974).
[2] and , ’Les analyses factorielles en calcul des probabilités et en statistique’, Thèse, Université Paul Sabatier, Toulouse, 1976.
[3] ’Echantillonnage dans une population de variables aléatoires réelles’, Thése, Université de Montpellier, 1970.
[4] ’Etude descriptive d’un processus. Approximation et interpolation’, Thése 3è cycle. Université Paul Sabatier, Toulouse, 1979.
[5] ’Méthodes exploratoires d’analyse de données temporelles’, Cahiers du Buro no. 37–38, Paris, 1981.
[6] Ramsay, Psychometrika 47 pp 379– (1982)
[7] ’Analyse des données chronologiques qualitatives’, Annales de l’INSEE no. 45, 45–104 (1982).
[8] and , ’Analyse harmonique qualitative’ in (ed.), Data Analysis and Informatics North-Holland, Amsterdam, 1979, pp. 375–389.
[9] Deville, Journal of Econometrics 22 pp 169– (1983)
[10] De Leeuw, Methods of operations Research 50 pp 299– (1985)
[11] Analysis of Categorical Data: Dual Scaling and its Applications, University of Toronto Press, 1980. · Zbl 0487.62001
[12] and Multivariate Descriptive Statiscal Analysis, Wiley, New York, 1984.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.