Geodesic
Investigation and reduction of variance of a weighted estimate in numerical statistical simulation
Žurnal vyčislitelʹnoj matematiki i matematičeskoj fiziki, Tome 46 (2006) no. 8, pp. 1519-1536 
I. N. Medvedev; G. A. Mikhailov. Investigation and reduction of variance of a weighted estimate in numerical statistical simulation. Žurnal vyčislitelʹnoj matematiki i matematičeskoj fiziki, Tome 46 (2006) no. 8, pp. 1519-1536. http://geodesic.mathdoc.fr/item/ZVMMF_2006_46_8_a12/
@article{ZVMMF_2006_46_8_a12,
     author = {I. N. Medvedev and G. A. Mikhailov},
     title = {Investigation and reduction of variance of a~weighted estimate in numerical statistical simulation},
     journal = {\v{Z}urnal vy\v{c}islitelʹnoj matematiki i matemati\v{c}eskoj fiziki},
     pages = {1519--1536},
     year = {2006},
     volume = {46},
     number = {8},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/ZVMMF_2006_46_8_a12/}
}
TY  - JOUR
AU  - I. N. Medvedev
AU  - G. A. Mikhailov
TI  - Investigation and reduction of variance of a weighted estimate in numerical statistical simulation
JO  - Žurnal vyčislitelʹnoj matematiki i matematičeskoj fiziki
PY  - 2006
SP  - 1519
EP  - 1536
VL  - 46
IS  - 8
UR  - http://geodesic.mathdoc.fr/item/ZVMMF_2006_46_8_a12/
LA  - ru
ID  - ZVMMF_2006_46_8_a12
ER  - 
%0 Journal Article
%A I. N. Medvedev
%A G. A. Mikhailov
%T Investigation and reduction of variance of a weighted estimate in numerical statistical simulation
%J Žurnal vyčislitelʹnoj matematiki i matematičeskoj fiziki
%D 2006
%P 1519-1536
%V 46
%N 8
%U http://geodesic.mathdoc.fr/item/ZVMMF_2006_46_8_a12/
%G ru
%F ZVMMF_2006_46_8_a12

Voir la notice de l'article provenant de la source Math-Net.Ru

The efficiency of the “value” and “partial value” modeling related to the construction of a modeling distribution for an auxiliary random variable by multiplying the initial density by a value function is investigated. The value function usually corresponds to a solution of the adjoint equation. Conditions under which the value modeling of the initial distribution reduces the variance compared to the direct simulation are obtained. It is proved that the variance of the weighted estimate is bounded in the case of the partial value modeling. This proposition provides a basis for a method for determining whether or not the variance of the weighted estimate is bounded. This method uses the majorizing adjoint equation. Using a practically important problem in transport theory as an example, the asymptotic optimization of the distribution of the mean free path is presented. The application of the proposed method of the investigation of the variance boundedness for the analysis of the classical exponential transformation method of simulating the mean free path of a particle in the one-dimensional and the spherical variants is discussed.

[1] Ermakov S. M., Mikhailov G. A., Statisticheskoe modelirovanie, Nauka, M., 1982 | MR

[2] Frolov A. C., Chentsov H. H., “Reshenie trekh tipichnykh zadach teorii perenosa metodom Monte-Karlo”, Metod Monte-Karlo v probleme perenosa izlucheniya, Atomizdat, M., 1967, 25–52

[3] Mikhailov G. A., Optimizatsiya vesovykh metodov Monte-Karlo, Nauka, M., 1987 | MR

[4] Kalos M. H., “Monte-Carlo integration of the adjoint gamma-ray transport equation”, Nucl. Sci. and Engng., 1968, 284–290

[5] Mikhailov G. A., “Postroenie vesovykh metodov Monte-Karlo na osnove uvelicheniya razmernosti fazovogo prostranstva”, Dokl. RAN, 389:4 (2003), 461–464 | MR | Zbl

[6] Mikhailov G. A., Medvedev H. H., “Optimizatsiya vesovykh metodov Monte-Karlo po vspomogatelnym peremennym”, Sibirskii matem. zhurnal, 45:2 (2004), 399–409 | MR | Zbl

[7] Devison B., Teoriya perenosa neitronov, Atomizdat, M., 1960

[8] Marchuk G. I., Metody rascheta yadernykh reaktorov, Atomizdat, M., 1961