A novel model of multidimensional risk is proposed. A Stochastic system of model is described as a set of independent Gaussian systems, and a fraction of each component is defined or set as probability of presence in studied population. The case when the sample is formed from a union of two Gaussian systems is considered in details. The results of testing on model and real data are presented.
REFERENCES
1.
2.
3.
4.
V.A.
Akimov
, V.V.
Lesnykh
, N. N.
Radaev
. Risks in nature, technosphere, society and economy
. (Moscow
, Delovoy Express
, 2004
). p. 352
5.
Tyrsin
A. N.
, Surina
A. A.
, “A risk modeling in multidimensional stochastic systems,” Tomsk State University Bulletin
. Journal of Control and computer science. №
2
(39
), 65
–72
(2017
).6.
Tyrsin
A. N.
, Surina
A. A.
, “A risk management models in Gaussian stochastic systems
,” Informatics and applications.
12
(2
), 50
–59
, (2018
).7.
Hosmer
D.W.
, Lemeshow
S.
, Sturdivant
R.X.
Applied Logistic Regression
. 3rd Edition. (Wiley
, 2013
).8.
Dempster
A.
, Laird
N.
, Rubin
D.
“Maximum likelihood from incomplete data via the EM algorithm
,” Journal of the Royal Statistical Society, Series B
, 39
(1
). pp. 1
–38
(1977
).9.
Jordan
M.I.
, Xu
L.
Convergence results for the EM algorithm to mixtures of experts architectures
(Tech. Rep. A.I. Memo №1458, MIT, MA
, 1993
).10.
N. G.
Zagoruyko
. An applied methods of analysis data and knowledge
. (Novosibirsk
, Institute of mathematics press
, 1999
). p. 270
.
This content is only available via PDF.
© 2020 Author(s).
2020
Author(s)
You do not currently have access to this content.