• Journal of Korean Institute of Industrial Engineers
• /
• v.19 no.1
• /
• pp.61-71
• /
• 1993

We focus on a way of combining the Monte Calro methods of antithetic variates and control variates to reduce the variance of the estimator of the mean response in a simulation experiment. Combined Method applies antithetic variates (partially) for driving approiate stochastic model components to reduce the vaiance of estimator and utilizes the correlations between the response and control variates. We obtain the variance of the estimator for the response analytically and compare Combined Method with control variates method. We explore the efficiency of this method in reducing the variance of the estimator through the port operations model. Combined Method shows a better performance in reducing the variance of estimator than methods of antithetic variates and control variates in the range from 6% to 8%. The marginal efficiency gain of this method is modest for the example considered. When the effective set of control variates is small, the marginal efficiency gain may increase. Though these results are from the limited experiments, Combined Method could profitably be applied to large-scale simulation models.

• Journal of the Korea Society for Simulation
• /
• v.19 no.1
• /
• pp.133-141
• /
• 2010

This research suggests a unified scheme for using stratified sampling and control variates method to improve the efficiency of estimation for parameters in simulation experiments. We utilize standardized concomitant variables defined during the course of simulation runs. We first use these concomitant variables to counteract the unknown error of response by the method of control variates, then use a concomitant variable not used in the controlled response and stratify the response into appropriate strata to reduce the variation of controlled response additionally. In case that the covariance between the response and a set of control variates is known, we identify the simulation efficiency of suggested method using control variates and stratified sampling. We conjecture the simulation efficiency of this method is better than that achieved by separated application of either control variates or stratified sampling in a simulation experiments. We investigate such an efficiency gain through simulation on a selected model.

• Journal of the Korea Society for Simulation
• /
• v.5 no.1
• /
• pp.91-106
• /
• 1996

Control Variate (CV) is very useful technique for variance reduction in a wide class of queueing network simulations. However, the loss in variance reduction caused by the estimation of the optimum control coefficients is an increasing function of the number of control variables. Therefore, in some situations, it is required to select an optimal set of control variables to maximize the variance reduction . In this paper, we develop the Adaptive Control Variates (ACV) method which selects an optimal set of control variates during the simulation adatively. ACV is useful to maximize the simulation efficiency when we need iterated simulations to find an optimal solution. One such an example is the Simulated Annealing (SA) because, in SA algorithm, we have to repeat in calculating the objective function values at each temperature, The ACV can also be applied to the queueing network optimization problems to find an optimal input parameters (such as service rates) to maximize the throughput rate with a certain cost constraint.

• Journal of the Korea Society for Simulation
• /
• v.14 no.3
• /
• pp.129-136
• /
• 2005

We develop a variance reduction technique applicable in one simulation experiment whose purpose is to estimate the parameters of a first order linear model. This method utilizes the control variates obtained during the course of simulation run under Schruben and Margolin's method (S-M method). The performance of this method is shown to be similar in estimating the main effects, and to be superior to S-M method in estimating the overall mean response in a given model. We consider that a proposed method may yield a better result than S-M method if selected control variates are highly correlated with the response at each design point.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.1
• /
• pp.185-189
• /
• 2006

Time series analysis is a frequently effective method of constructing model and prediction in data processing of deformation monitoring. The monitoring data sample must to be as more as possible and time intervals are equal roughly so as to construct time series model accurately and achieve reliable prediction. But in the project practice of GPS deformation monitoring, the monitoring data sample can't be obtained too much and time intervals are not equal because of being restricted by all kinds of factors, and it contains many variates in the deformation model moreover. It is very important to study the data processing method for small samples and multi-variates time series in GPS deformation monitoring. A new method of establishing small samples and multi-variates deformation model and prediction model are put forward so as to resolve contradiction of small samples and multi-variates encountered in constructing deformation model and improve formerly data processing method of deformation monitoring. Based on the system theory, a deformation body is regarded as a whole organism; a time-dependence linear system model and a time-dependence bilinear system model are established. The dynamic parameters estimation is derived by means of prediction fit and least information distribution criteria. The final example demonstrates the validity and practice of this method.

• Journal of the Korean Statistical Society
• /
• v.26 no.1
• /
• pp.131-146
• /
• 1997

In this paper the problem of measuring the stochastic dependence among sets fo random variates is considered, and attention is specifically directed to forming a single well-defined measure of the dependence among sets of normal variates. A new information theoretic measure of the dependence called dependence index (DI) is introduced and its several properties are studied. The development of DI is based on the generalization and normalization of the mutual information introduced by Kullback(1968). For data analysis, minimum cross entropy estimator of DI is suggested, and its asymptotic distribution is obtained for testing the existence of the dependence. Monte Carlo simulations demonstrate the performance of the estimator, and show that is is useful not only for evaluation of the dependence, but also for independent model testing.

• Communications for Statistical Applications and Methods
• /
• v.11 no.1
• /
• pp.79-91
• /
• 2004

In this thesis, Bayesian parameter estimation procedure is discussed for the mean change model of multivariate normal random variates under the assumption of noninformative priors for all the parameters. Parameters are estimated by Gibbs sampling method. In Gibbs sampler, the change point parameter is generated by Metropolis-Hastings algorithm. We apply our methodology to numerical data to examine it.

• Communications for Statistical Applications and Methods
• /
• v.9 no.1
• /
• pp.129-139
• /
• 2002

Default Bayesian method for detecting the changes in sequences of independent exponential random variates and independent Poisson random variates is considered. Noninformative priors are assumed for all the parameters in both of change models. Default Bayes factors, AIBF, MIBF, FBF, to check whether there is any change or not on each sequence and the posterior probability densities of change at each time point are derived. Theoretical results discussed in this paper are applied to some numerical data.

• Communications for Statistical Applications and Methods
• /
• v.23 no.6
• /
• pp.517-529
• /
• 2016

This study compares the inverse transform and the composition methods for generating data from the Lindley distribution. The expression for the inverse of the distribution function for the Lindley distribution does not exist in closed form. Hence, authors of many empirical studies on the Lindley distribution used methods for generating Lindley variates other than the inverse transform. We generated data from the Lindley distribution using the inverse transform approach by obtaining the Lindley variates numerically; we also generated data from this distribution using the composition approach. Following the generation of the Lindley variates using these two methods, we compare some statistical properties of the estimates of the Lindley model parameters based on the generated data. We conclude that the two methods produce similar results.

• Journal of the Korea Society for Simulation
• /
• v.1 no.1
• /
• pp.1-16
• /
• 1992

This research develops two variance reduction methods for estimating the parameters of the experimental simulation model having multiple design points based on an approach focusing on reduction of the variances of the mean responses across multiple design points. The first method extends a combined approach of antithetic variates and control variates for a single design point to the multipopulation context with independent streams across the design points. The second method extends the same strategy in conjunction with the Schruben-Margolin method for improving the first method. We illustrate an example for implementing the second method. We expect these two approaches may improve the estimation of the parameters of interest compared with the control variates method.