×

Equivalency between vertices and centers-coupled-with-radii principal component analyses for interval data. (English) Zbl 1328.62374

Summary: Centers and vertices principal component analyses are common methods to explain variations within multivariate interval data. We introduce multivariate equicorrelated structures to vertices’ covariance. Assuming the structure, we show equivalence between centers and vertices methods by proving their eigensystems proportional.

MSC:

62H25 Factor analysis and principal components; correspondence analysis
62H12 Estimation in multivariate analysis
PDF BibTeX XML Cite
Full Text: DOI

References:

[1] Arnold, S. F., Linear models with exchangeably distributed errors, J. Amer. Statist. Assoc., 74, 194-199, (1979) · Zbl 0431.62044
[2] Bertrand, P., Goupil, F., 2000. Exploratory methods for extracting statistical information from complex data. In: Bock and Diday: Analysis of Symbolic Data.
[3] Billard, L., 2008. Sample covariance functions for complex quantitative data. In: Proceedings, World Conferences International Association of Statistical Computing.
[4] Billard; Guo, J. H.; Xu, W., Maximum likelihood estimators for bivariate interval-valued data. technical report, (2011), University of Georgia
[5] Bock, H. H.; Diday, E., Analysis of symbolic data: exploratory methods for extracting statistical information from complex data, (2000), Springer Heidelberg · Zbl 1039.62501
[6] Cazes, P.; Chouakria, A.; Diday, E.; Schektman, Y., Extensions de l’analyse en composantes principales a des donnees de type intervalle, Rev. Stat. Appl., 24, 5-24, (1997)
[7] Chouakria, A.; Diday, E.; Cazes, P., An improved factorial representation of symbolic objects, in knowledge extraction from statistical data, Luxembourg: Eur. Comm. Eurostat., 301-305, (1999)
[8] Douzal-Chouakria, A.; Billard, L.; Diday, E., Principal component analysis for interval-valued observations, Stat. Anal. Data Min.: ASA Data Sci. J., 4, 2, 229-246, (2011)
[9] Giordani, P.; Kiers, H. A.L., A comparison of three methods for principal component analysis of fuzzy interval data, Comput. Statist. Data Anal., 51, 379-397, (2006) · Zbl 1157.62426
[10] Lauro, C. N.; Palumbo, F., Principal component anaysis of interval data: a symbolic data analysis approach, Comput. Statist., 15, 73-87, (2000) · Zbl 0953.62058
[11] Leiva, R., Linear discrimination with equicorrelated training vectors, J. Multivariate Anal., 98, 384-409, (2007) · Zbl 1112.62057
[12] Le-Rademacher, J.; Billard, L., Likelihood functions and some maximum likelihood estimators for symbolic data, J. Statist. Plann. Inference, 141, 1593-1602, (2011) · Zbl 1204.62026
[13] Le-Rademacher, J.; Billard, L., Symbolic covariance principal component analysis and visualization for interval-valued data, J. Comput. Graph. Statist., 21, 2, 413-432, (2012)
[14] Palumbo, F.; Lauro, C. N., A PCA for interval-valued data based on midpoints and radii, (Yanai, H.; Okada, A.; Shigemasu, K.; Kano, Y.; Meulman, J., New Developments in Psychometrics, (2003), Springer Tokyo), 641-648
[15] Roy, A., 2014. A two-stage principal component analysis of symbolic data using equicorrelated and jointly equicorrelated covariance structures. Working Paper Series: WP 0006MSS-253-2014, College of Business, The University of Texas at San Antonio, Currently, (submitted for publication), to a journal.
[16] Roy, A.; Leiva, R., Estimating and testing a structured covariance matrix for three-level multivariate data, Comm. Statist. Theory Methods, 40, 11, 1945-1963, (2011) · Zbl 1216.62095
[17] Roy, A.; Leiva, R.; Žežula, I.; Klein, D., Testing the equality of mean vectors for paired doubly multivariate observations in blocked compound symmetric covariance matrix setup, J. Multivariate Anal., 137, 50-60, (2015) · Zbl 1329.62251
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.