Arbeitspapier
Direct minimization of error rates in multivariate classification
We propose a computer intensive method for linear dimension reduction which minimizes the classification error directly. Simulated annealing (Bohachevsky et al 1986) as a modern optimization technique is used to solve this problem effectively. This approach easily allows to incorporate user requests by means of penalty terms. Simulations demonstrate the superiority of optimal classification to classical discriminant analysis (McLachlan 1992). Special emphasis is put on the case when discriminant analysis collapses.
- Language
-
Englisch
- Bibliographic citation
-
Series: Technical Report ; No. 1999,43
- Subject
-
classification
discriminant analysis
error rate
simulated annealing
user requests
- Event
-
Geistige Schöpfung
- (who)
-
Röhl, Michael C.
Weihs, Claus
- Event
-
Veröffentlichung
- (who)
-
Universität Dortmund, Sonderforschungsbereich 475 - Komplexitätsreduktion in Multivariaten Datenstrukturen
- (where)
-
Dortmund
- (when)
-
1999
- Handle
- Last update
-
10.03.2025, 11:42 AM CET
Data provider
This object is provided by:
ZBW - Deutsche Zentralbibliothek für Wirtschaftswissenschaften - Leibniz-Informationszentrum Wirtschaft. If you have any questions about the object, please contact the data provider.
ZBW - Deutsche Zentralbibliothek für Wirtschaftswissenschaften - Leibniz-Informationszentrum Wirtschaft. If you have any questions about the object, please contact the data provider.
Object type
- Arbeitspapier
Associated
- Röhl, Michael C.
- Weihs, Claus
- Universität Dortmund, Sonderforschungsbereich 475 - Komplexitätsreduktion in Multivariaten Datenstrukturen
Time of origin
- 1999
Other Objects (12)
Variance reduction with Monte Carlo estimates of error rates in multivariate classification
Multivariate classification of business phases
Business phase classification and prediction: how to compare interpretability of classification methods?
Stability of multivariate representation of business cycles over time
Prediction Optimal Classification of Business Phases
Classification and Clustering in Business Cycle Analysis
Dynamic Bayesian networks for classification of business cycles
Local Modelling in Classification on Different Feature Subspaces
Determination of optimal prediction oriented multivariate latent factor models using loss functions
A note on a multivariate analogue of the process capability index Cp
Importance Assessment of Correlated Predictors in Business Cycles Classification
Direct Minimization of Error Rates in Multivariate Classification
Variance reduction with Monte Carlo estimates of error rates in multivariate classification
Multivariate classification of business phases
Business phase classification and prediction: how to compare interpretability of classification methods?
Stability of multivariate representation of business cycles over time
Prediction Optimal Classification of Business Phases
Classification and Clustering in Business Cycle Analysis
Dynamic Bayesian networks for classification of business cycles
Local Modelling in Classification on Different Feature Subspaces
Determination of optimal prediction oriented multivariate latent factor models using loss functions
A note on a multivariate analogue of the process capability index Cp
Importance Assessment of Correlated Predictors in Business Cycles Classification
Direct Minimization of Error Rates in Multivariate Classification
Variance reduction with Monte Carlo estimates of error rates in multivariate classification
Multivariate classification of business phases
Business phase classification and prediction: how to compare interpretability of classification methods?
Stability of multivariate representation of business cycles over time
Prediction Optimal Classification of Business Phases
Classification and Clustering in Business Cycle Analysis
Dynamic Bayesian networks for classification of business cycles
Local Modelling in Classification on Different Feature Subspaces
Determination of optimal prediction oriented multivariate latent factor models using loss functions
A note on a multivariate analogue of the process capability index Cp
Importance Assessment of Correlated Predictors in Business Cycles Classification