Multiple decision problem for stock selection in market network
Market graph is built on the basis of some similarity measure for financial asset returns. The paper considers two similarity measures: classic Pearson correlation and sign correlation. We study the associated market graphs and compare the conditional risk of the market graph construction for these two measures of similarity. Our main finding is that the conditional risk for the sign correlation is much better than for the Pearson correlation for larger values of threshold for several probabilistic models. In addition, we show that for some model the conditional risk for sign correlation dominates over the conditional risk for Pearson correlation for all values of threshold. These properties make sign correlation a more appropriate measure for the maximum clique analysis.
The paper presents the analysis of the network model referred to as market graph of the BRIC countries stock markets. We construct the stock market graph as follows: each vertex represents a stock, and the vertices are adjacent if the price correlation coefficient between them over a certain period of time is greater than or equal to specified threshold. The market graphs are constructed for different time periods to understand the dynamics of their characteristics such as correlation distribution histogram, mean value and standard deviation, size and structure of the maximum cliques. Our results show that we can split the BRIC countries into two groups. Brazil, Russia and India constitute the first group, China constitutes the second group.
Problem of construction of the market graph as a multiple decision statistical problem is considered. Detailed description of a optimal unbiased multiple decision statistical procedure is given. This procedure is constructed using the Lehmann’s theory of multiple decision statistical procedures and the conditional tests of the Neyman structures. The equations for thresholds calculation for the tests of the Neyman structure are presented and analyzed.