Summary
Noisy data such as outliers cause difficulty in any model selection procedure. We present two general procedures. The first extends any model selection technique such as maximum likelihood or method of moments estimation to a procedure for obtaining mixture models. The second procedure makes a model selection technique more robust by weighting with members of the model family. Finally, we show how to combine these two procedures to obtain a robust, mixture modeling method
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
REDNER, R. A. and WALKER, H. F. (1984): Mixture densities, maximum likelihood and the EM algorithm. SIAM Review, 26, 195–239.
WINDHAM, M. P. (1993): Robust model selection. Utah State University, Mathematics and Statistics Research Report 6/93/67.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Windham, M.P., Cutler, A. (1994). Mixture Analysis with Noisy Data. In: Diday, E., Lechevallier, Y., Schader, M., Bertrand, P., Burtschy, B. (eds) New Approaches in Classification and Data Analysis. Studies in Classification, Data Analysis, and Knowledge Organization. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-51175-2_17
Download citation
DOI: https://doi.org/10.1007/978-3-642-51175-2_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-58425-4
Online ISBN: 978-3-642-51175-2
eBook Packages: Springer Book Archive