Full-text resources of CEJSH and other databases are now available in the new Library of Science.
Visit https://bibliotekanauki.pl

PL EN


2020 | 2 | 347 | 71-90

Article title

A Critical Study of Usefulness of Selected Functional Classifiers in Economics

Content

Title variants

Krytyczna analiza wybranych klasyfikatorów dla danych funkcjonalnych w kontekście ich zastosowań w ekonomii

Languages of publication

EN

Abstracts

EN
In this paper we conduct a critical analysis of the most popular functional classifiers. Moreover, we propose a new classifier for functional data. Some robustness properties of the functional classifiers are discussed as well. We can use an approach worked out in this paper to predict the expected state of the economy from aggregated Consumer Confidence Index (CCI, measuring consumers optimism) and Industrial Price Index (IPI, reflecting a degree of optimism in industry sector) exploiting not only scalar values of the indices but also the trajectories/shapes of functions describing the indices. Thus our considerations may be helpful in constructing a better economic barometer. As far as we know, this is the first comparison of functional classifiers with respect to a criterion of their usefulness in economic applications. The main result of the paper is a presentation of how a small fraction of outliers in a training sample, which are linearly independent from the training sample, consisting of almost linearly dependent functions, corrupt all analysed classifiers.
PL
W artykule przeprowadzono krytyczną analizę najbardziej znanych klasyfikatorów dla danych funkcjonalnych. Ponadto zaproponowano nowy klasyfikator dla danych funkcjonalnych. Przedyskutowano pewne, związane z odpornością, własności rozważanych klasyfikatorów. Wypracowane w artykule podejście może zostać użyte do przewidywania stanu gospodarki na podstawie indeksu mierzącego optymizm konsumentów – CCI (Consumer Confidence Index) oraz indeksu odzwierciedlającego optymizm w sektorze przemysłowym – IPI (Industrial Price Index), przy czym wykorzystuje się nie tylko skalarne wartości indeksu, lecz także całą trajektorię/kształt funkcji opisującej dany indeks. W związku z tym nasze rozważania mogą być pomocne w skonstruowaniu lepszego barometru stanu gospodarki. O ile wiadomo autorom, jest to pierwsze porównanie klasyfikatorów dla danych funkcjonalnych ze względu na kryterium ich użyteczności aplikacyjnej w ekonomii. Głównym celem artykułu jest zaprezentowanie, jak mała frakcja obserwacji nietypowych w próbce uczącej, będących liniowo niezależnymi z próbką uczącą, która z kolei składa się z funkcji prawie liniowo zależnych, jest w stanie poważnie zaburzyć wyniki klasyfikacji dla wszystkich rozpatrywanych klasyfikatorów.

Year

Volume

2

Issue

347

Pages

71-90

Physical description

Dates

published
2020-04-03

Contributors

  • Cracow University of Economics, Department of Statistics
  • AGH University of Science and Technology, Faculty of Applied Mathematics, Department of Mathematical Analysis, Computational Mathematics and Probability Methods
  • AGH University of Science and Technology, Faculty of Applied Mathematics, Department of Financial Mathematics

References

  • Arribas‑Gil A., Romo J. (2013), Shape Outlier Detection and Visualization for Functional Data: the Outliergram, “Biostatistics”, vol. 15, issue 4, pp. 603–619.
  • Berlinet A., Thomas‑Agnan C. (2004), Reproducing Kernel Hilbert Spaces in Probability and Statistics, Kluwer, Dordrecht. https://doi.org/10.1007/978-1-4419-9096-9
  • Białek J. (2012), Proposition of the general formula for price indices, “Communications in Statistics: Theory and Methods”, vol. 41, issue 5, pp. 943–952.
  • Bosq D. (2000), Linear Processes in Function Spaces, Springer, New York. https://doi.org/10.1007/978-1-4612-1154-9
  • Christmann A., Van Messem A. (2008), Bouligand Derivatives and Robustness of Support Vector Machines for Regression, “Journal of Machine Learning Research”, vol. 9, pp. 915–936.
  • Christmann A., Salibian‑Barrera M., Van Aelst S. (2013), Qualitative Robustness of Bootstrap Approximations for Kernel Based Methods, [in:] C. Becker, R. Fried, S. Kuhnt (eds.), Robustness and Complex Data Structures, Springer, Berlin–Heidelberg, pp. 263–278. https://doi.org/10.1007/978-3-642-35494-6_16
  • Cuevas A. (1988), Qualitative robustness in abstract inference, “Journal of Statistical Planning and Inference”, vol. 18, issue 3, pp. 277–289.
  • Cuevas A., Fraiman R. (2009), On depth measures and dual statistics. A methodology for dealing with general data, “Journal of Multivariate Analysis”, vol. 100, issue 4, pp. 753–766.
  • Cuevas A., Febrero‑Bande M., Fraiman R. (2007), Robust estimation and classification for functional data via projection‑based depth notions, “Computational Statistics”, vol. 22, issue 3, pp. 481–496.
  • Devroye L., Gyorfi L., Lugosi G. (1996), A Probabilistic Theory of Pattern Recognition, Springer, New York. https://doi.org/10.1007/978-1-4612-0711-5
  • Febrero‑Bande M. O., Fuente M. de la (2012), Statistical computing in functional data analysis: the R package fda.usc, “Journal of Statistical Software”, vol. 51, issue 4, pp. 1–28.
  • Ferraty F., Vieu P. (2006), Nonparametric Functional Data Analysis: Theory and Practice, Spring‑ er, Berlin.
  • Górecki T., Krzyśko M., Wołyński W. (2018), Independence test and canonical correlation analysis based on the alignment between kernel matrices for multivariate functional data, “Artificial Intelligence Review”, https://doi.org/10.1007/s10462-018-9666-7
  • Górecki T., Krzyśko M., Waszak Ł., Wołyński W. (2018), Selected Statistical Methods of Data Analysis for Multivariate Functional Data, “Statistical Papers”, vol. 59, issue 1, pp. 153–182.
  • Haykin S. (2009), Neural networks and learning machines, Prentice Hall, New Jersey.
  • Horváth L., Kokoszka P. (2012), Inference for functional data with applications, Springer, New York. https://doi.org/10.1007/978-1-4614-3655-3
  • Hubert M., Van Driessen K. (2004), Fast and robust discriminant analysis, “Computational Statistics & Data Analysis”, vol. 45, issue 2, pp. 301–320.
  • Hubert M., Rousseeuw P., Segaert P. (2016), Multivariate and functional classification using depth and distance, “Advances in Data Analysis and Classification”, vol. 11, issue 3, pp. 445–466.
  • Kosiorowski D. (2016), Dilemmas of robust analysis of economic data streams, “Journal of Mathematical Sciences”, vol. 218, issue 2, pp. 167–181.
  • Kosiorowski D., Zawadzki Z. (2019), DepthProc: An R package for robust exploration of multidimensional economic phenomena, “Journal of Statistical Software” (forthcoming).
  • Kosiorowski D., Mielczarek D., Rydlewski J. P. (2017), SVM classifiers for functional data in monitoring of the Internet users behavior, [in:] M. Papież, S. Śmiech (eds.), The 11th Professor A. Zeliaś International Conference on Modelling and Forecasting of Socio‑Economic Phenomena, Conference Proceedings, Zakopane, pp. 143–152.
  • Kosiorowski D., Mielczarek D., Rydlewski J. P. (2018), New proposal of robust classifier for functional data, [in:] M. Papież, S. Śmiech (eds.), The 12th Professor A. Zeliaś International Conference on Modelling and Forecasting of Socio‑Economic Phenomena, Conference Proce‑ edings, Zakopane, pp. 200–208.
  • Kosiorowski D., Rydlewski J. P., Snarska M. (2019), Detecting a structural change in functional time series using local Wilcoxon statistic, “Statistical Papers”, vol. 60, pp. 1677–1698, http://dx.doi.org/10.1007/s00362-017-0891-y
  • Kosiorowski D., Rydlewski J. P., Zawadzki Z. (2018), Functional outliers detection by the example of air quality monitoring, “Statistical Review”, vol. 65, no. 1, pp. 81–98.
  • Li J., Cuesta‑Albertos J. A., Liu R. Y. (2012), DD‑Classifier: Nonparametric Classification Procedure Based on DD‑Plot, “Journal of the American Statistical Association”, vol. 107, issue 498, pp. 737–753.
  • OECD (2018), Consumer confidence index (CCI) (indicator), http://dx.doi.org/10.1787/46434d78-en
  • Preda C. (2007), Regression models for functional data by reproducing kernel Hilbert spaces methods, “Journal of Statistical Planning and Inference”, vol. 137, issue 3, pp. 829–840.
  • Ramsay J. O., Silverman B. W. (2005), Functional data analysis, Springer, Berlin.
  • Ramsay J. O., Hooker G., Graves S. (2009), Functional data analysis with R and Matlab, Springer, New York.
  • Schölkopf B., Smola A. J. (2002), Learning with Kernels, MIT Press, Cambridge.
  • Steinwart I., Christmann A. (2008), Support Vector Machines, Springer, New York.
  • Tarabelloni N. (2017), Robust Statistical Methods in Functional Data Analysis, Doctoral thesis and R package roahd, Politecnico di Milano, Milano.
  • Vencálek O. (2013), Depth‑based Modification of the k‑nearest Neighbour Method, “SOP Transactions on Statistics and Analysis”, vol. 1, no. 2, pp. 131–138.
  • Vencálek O., Pokotylo O. (2018), Depth‑weighted Bayes classification, “Computational Statistics and Data Analysis”, vol. 123, pp. 1–12.

Document Type

Publication order reference

Identifiers

YADDA identifier

bwmeta1.element.ojs-doi-10_18778_0208-6018_347_05
JavaScript is turned off in your web browser. Turn it on to take full advantage of this site, then refresh the page.