On some statistical procedures for stock selection problem
- 167 Downloads
The problem of stock selection in market network is discussed from different points of view. Three different sequentially rejective statistical procedures for stock selection are described and compared: Holm multiple test procedure, maximin multiple test procedure and multiple decision procedure. Properties of statistical procedures are studied for different loss functions. It is shown that conditional risk for additive loss function essentially depends on correlation matrix for maximin procedure, and does not depend for multiple decision procedure. The dependence on correlation matrix is different for 0-1 (non additive) loss functions. Dependence of error probability and conditional risk on the selection threshold is studied as well.
KeywordsLarge scale networks Stock selection Multiple decision statistical procedures Multiple testing statistical procedures loss functions Conditional risk Probability of error
Mathematics Subject Classifications (2010)62-07 62C05 62P20
Unable to display preview. Download preview PDF.
- 7.Koldanov, P., Kalyagin, V.A., Koldanov, A.P., Zamaraev, V.A.: Market graph and Markowitz model. In: Optimization in Science and Engineering (In Honor of the 60th Birthday of Panos M. Pardalos), pp. 301–313. Springer Science, Business Media (2014)Google Scholar
- 8.Koldanov, P., Bautin, G.A.: Multiple decision problem for stock selection in market network. In: Pardalos, P.M., Resende, M., Vogiatzis, C., Walteros, J. (eds.) Learning and Intelligent Optimization, Lecture Notes in Computer Science, Vol. 8426, pp 98–110. Springer (2014)Google Scholar
- 9.Koldanov, A.P., Koldanov, P.A: Optimal multiple decision statistical procedure for inverse covariance matrix. In: Demyanov, V.F., Pardalos, P.M., Batsyn, M.V. (eds.) Constructive Nonsmooth Analysis and Related Topics, Springer Optimization and Its Applications, Vol. 87, pp 205–216 (2014)Google Scholar