Statistical procedures for the market graph construction

Koldanov, A. P.; Koldanov, Petr A.; Kalyagin, V. A.; Pardalos, Pãnos M.

doi:10.1016/j.csda.2013.06.005

Cited by 32 publications

(20 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, in Koldanov et al Koldanov et al (2013) the construction of sample market graphs for a financial network (as in our analysis) is the procedure of the identification of the true market graph, and this identification problem is treated as a multiple decision problem of the selection of one from a set of hypotheses.…”

Section: Discussionmentioning

confidence: 99%

“…Koldanov et al Koldanov et al (2013) compute a simulation study in which the random vector of random variables representing the daily returns of a stock are distributed according to a multivariate normal distribution or a multivariate Student-t distribution. The main results from the study are that the method of market graph construction is i) "optimal in the class of all unbiased statistical procedures if, for the generating hypotheses testing, one uses the tests of the Neyman structures"; ii) "optimal in a restricted class of unbiased statistical procedures if, for the generating hypotheses testing, one uses the classical Pearson correlation tests" (Koldanov et al Koldanov et al (2013)).…”

Section: Discussionmentioning

confidence: 99%

“…The main results from the study are that the method of market graph construction is i) "optimal in the class of all unbiased statistical procedures if, for the generating hypotheses testing, one uses the tests of the Neyman structures"; ii) "optimal in a restricted class of unbiased statistical procedures if, for the generating hypotheses testing, one uses the classical Pearson correlation tests" (Koldanov et al Koldanov et al (2013)). In the former case, edges connect two stocks (i, j) if the sample correlation s i,j exceeds a predetermined threshold c i,j .…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

A statistical analysis of UK financial networks

Chu

Nadarajah

2017

Physica A: Statistical Mechanics and its Applications

View full text Add to dashboard Cite

In recent years, with a growing interest in big or large datasets, there has been a rise in the application of large graphs and networks to financial big data. Much of this research has focused on the construction and analysis of the network structure of stock markets, based on the relationships between stock prices. Motivated by Boginski et al. Boginski et al. (2005), who studied the characteristics of a network structure of the US stock market, we construct network graphs of the UK stock market using same method. We fit four distributions to the degree density of the vertices from these graphs, the Pareto I, Fréchet, lognormal, and generalised Pareto distributions, and assess the goodness of fit. Our results show that the degree density of the complements of the market graphs, constructed using a negative threshold value close to zero, can be fitted well with the Fréchet and lognormal distributions.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A statistical analysis of UK financial networks

Chu

Nadarajah

2017

Physica A: Statistical Mechanics and its Applications

View full text Add to dashboard Cite

show abstract

“…Proof We prove optimality in three steps. First we prove that under symmetry conditions (14) each individual test (10) is uniformly most powerful (UMP) in the class of tests based on u i (t), u j (t) only for individual hypothesis testing…”

Section: Multiple Decision Procedures Based On Simultaneous Inference mentioning

confidence: 99%

“…Class of optimal statistical procedures for the identification of market graph in Pearson correlation based network were introduced and investigated in [14]. One can see from numerical experiments in [14] that the value of the risk function of the procedures of this class essentially depends on the assumptions on multivariate distributions of stocks attributes. Taking this into account it is of interest to investigate a distribution free identification statistical procedures.…”

Section: Introductionmentioning

confidence: 99%

Optimal decision for the market graph identification problem in a sign similarity network

Kalyagin

Koldanov

et al. 2017

Ann Oper Res

View full text Add to dashboard Cite

Investigation of the market graph attracts a growing attention in market network analysis. One of the important problem connected with market graph is to identify it from observations. Traditional way for the market graph identification is to use a simple procedure based on statistical estimations of Pearson correlations between pairs of stocks. Recently a new class of statistical procedures for the market graph identification was introduced and optimality of these procedures in Pearson correlation Gaussian network was proved. However the obtained procedures have a high reliability only for Gaussian multivariate distributions of stocks attributes. One of the way to correct this drawback is to consider a different networks generated by different measures of pairwise similarity of stocks. A new and promising model in this context is the sign similarity network. In the present paper the market graph identification problem in sign similarity network is considered. A new class of statistical procedures for the market graph identification is introduced and optimality of these procedures is proved. Numerical experiments detect essential difference in quality of optimal procedures in sign similarity and Pearson correlation networks. In particular it is observed that the quality of optimal identification procedure in sign similarity network is not sensitive to the assumptions on distribution of stocks attributes.

show abstract