Home

# Stochastic monotonicity and conditional Monte Carlo for likelihood ratios

## Abstract

Likelihood ratios are used in computer simulation to estimate expectations with respect to one law from simulation of another. This importance sampling technique can be implemented with either the likelihood ratio at the end of the simulated time horizon or with a sequence of likelihood ratios at intermediate times. Since a likelihood ratio process is a martingale, the intermediate values are conditional expectations of the final value and their use introduces no bias.

We provide conditions under which using conditional expectations in this way brings guaranteed variance reduction. We use stochastic orderings to get positive dependence between a process and its likelihood ratio, from which variance reduction follows. Our analysis supports the following rough statement: for increasing functionals of associated processes with monotone likelihood ratio, conditioning helps. Examples are drawn from recursively defined processes, Markov chains in discrete and continuous time, and processes with Poisson input.

## References

Hide All
[1] Asmussen, S. and Rubinstein, R. Y. (1992) The efficiency and heavy traffic properties of the score function method in sensitivity analysis of queueing models. Adv. Appl. Prob. 24, 172201.
[2] Brémaud, P. (1981) Point Processes and Queues. Springer-Verlag, New York.
[3] Brown, M., Solomon, H. and Stephens, M. A. (1981) Monte Carlo simulation of the renewal function. J. Appl. Prob. 18, 426434.
[4] Daley, D. (1968) Stochastically monotone Markov chains. Z. Wahrscheinlichkeitsth. 10, 305317.
[5] Esary, J. D., Proschan, F. and Walkup, D. W. (1967) Association of random variables. Ann. Math. Statist. 38, 14661474.
[6] Glasserman, P. (1992) Processes with associated increments. J. Appl. Prob. 29, 313333.
[7] Glynn, P. W. and Iglehart, D. L. (1988) Simulation methods for queues: an overview. QUESTA 3, 221256.
[8] Glynn, P. W. and Iglehart, D. L. (1989) Importance sampling for stochastic simulations. Management Sci. 35, 13671392.
[9] Harris, T. E. (1977) A correlation inequality for Markov processes on partially ordered spaces. Ann. Prob. 5, 451454.
[10] Heidelberger, G. and Iglehart, D. L. (1979) Comparing stochastic systems using regenerative simulation and common random numbers. Adv. Appl. Prob. 11, 804819.
[11] Kamae, T., Krengel, U. and O'Brien, G. L. (1977) Stochastic inequalities on partially ordered spaces. Ann. Prob. 5, 899912.
[12] Karlin, S. and Rinott, Y. (1980) Classes of orderings of measures and related correlation inequalities: I. multivariate totally positive distributions. J. Multivarate Anal. 10, 467498.
[13] Keilson, J. and Kester, A. (1977) Monotone matrices and monotone Markov chains. Stoch. Proc. Appl. 5, 231241.
[14] Lehmann, E. L. (1966) Some concepts of dependence. Ann. Math. Statist. 37, 11371153.
[15] Liggett, T. M. (1985) Interacting Partial Systems. Springer-Verlag, New York.
[16] Lindqvist, B. H. (1988) Association of probability measures on partially ordered sets. J. Multivariate Anal. 26, 111132.
[17] Marshall, A. W. and Olkin, I. (1979) Inequalities: Theory of Majorization and its Applications. Academic Press, New York.
[18] Massey, W. A. (1987) Stochastic orderings for Markov processes on partially ordered spaces. Math. Operat. Res. 12, 350367.
[19] Ross, S. M. (1988) Simulating average delay—variance reduction by conditioning, Prob. Eng. Inf. Sci. 2, 309312.
[20] Shaked, M. and Shanthikumar, J. G. (1988) Temporal stochastic convexity and concavity. Stoch. Proc. Appl. 27, 120.
[21] Whitt, W. (1982) Multivariate monotone likelihood ratio and uniform conditional stochastic order. J. Appl. Prob. 19, 695701.

# Stochastic monotonicity and conditional Monte Carlo for likelihood ratios

## Metrics

### Full text viewsFull text views reflects the number of PDF downloads, PDFs sent to Google Drive, Dropbox and Kindle and HTML full text views.

Total number of HTML views: 0
Total number of PDF views: 0 *