Local Statistical Modeling via Cluster-Weighted Approach with Elliptical Distributions
Cluster Weighted Modeling (CWM) is a mixture approach regarding the modelisation of the joint probability of data coming from a heterogeneous population. Under Gaussian assumptions, we investigate statistical properties of CWM from both the theoretical and numerical point of view; in particular, we show that CWM includes as special cases mixtures of distributions and mixtures of regressions. Further, we introduce CWM based on Student-t distributions providing more robust fitting for groups of observations with longer than normal tails or atypical observations. Theoretical results are illustrated using some empirical studies, considering both real and simulated data.
|Date of creation:||28 May 2011|
|Date of revision:|
|Contact details of provider:|| Postal: Via Bicocca degli Arcimboldi 8, 20126 Milano|
Web page: http://www.statistica.unimib.it
More information through EDIRC
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- Roman Liesenfeld & Robert C. Jung, 2000.
"Stochastic volatility models: conditional normality versus heavy-tailed distributions,"
Journal of Applied Econometrics,
John Wiley & Sons, Ltd., vol. 15(2), pages 137-160.
- Liesenfeld, Roman & Jung, Robert C., 1997. "Stochastic volatility models: Conditional normality versus heavy tailed distributions," Tübinger Diskussionsbeiträge 103, University of Tübingen, School of Business and Economics.
- Marco Riani & Anthony C. Atkinson & Andrea Cerioli, 2009.
"Finding an unknown number of multivariate outliers,"
Journal of the Royal Statistical Society Series B,
Royal Statistical Society, vol. 71(2), pages 447-466.
- Marco Riani & Anthony C. Atkinson & Andrea Cerioli, 2009. "Finding an unknown number of multivariate outliers," LSE Research Online Documents on Economics 30462, London School of Economics and Political Science, LSE Library.
- Francesca Greselin & Salvatore Ingrassia & Antonio Punzo, 2011. "Assessing the pattern of covariance matrices via an augmentation multiple testing procedure," Statistical Methods & Applications, Springer;Società Italiana di Statistica, vol. 20(2), pages 141-170, June.
- Ingrassia, Salvatore & Rocci, Roberto, 2007. "Constrained monotone EM algorithms for finite mixture of multivariate Gaussians," Computational Statistics & Data Analysis, Elsevier, vol. 51(11), pages 5339-5351, July.
- Wayne DeSarbo & William Cron, 1988. "A maximum likelihood methodology for clusterwise linear regression," Journal of Classification, Springer;The Classification Society, vol. 5(2), pages 249-282, September.
- Leisch, Friedrich, 2004. "FlexMix: A General Framework for Finite Mixture Models and Latent Class Regression in R," Journal of Statistical Software, Foundation for Open Access Statistics, vol. 11(i08).
- Cerioli, Andrea, 2010. "Multivariate Outlier Detection With High-Breakdown Estimators," Journal of the American Statistical Association, American Statistical Association, vol. 105(489), pages 147-156.
- Michel Wedel & Wayne DeSarbo, 1995. "A mixture likelihood approach for generalized linear models," Journal of Classification, Springer;The Classification Society, vol. 12(1), pages 21-55, March.
When requesting a correction, please mention this item's handle: RePEc:mis:wpaper:20111001. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Matteo Pelagatti)
If references are entirely missing, you can add them using this form.