• Proceedings of the Korea Society for Simulation Conference
• /
• 1999.04a
• /
• pp.70-79
• /
• 1999

Importance Sampling (IS) has been applied to accelerate the occurrence of rare events. However, it has a drawback of effective biasing scheme to make the estimator from IS unbiased. Adaptive Importance Sampling (AIS) employs an estimated sampling distribution of IS to the systems of interest during the course of simulation. We propose Nonparametric Adaptive Importance Sampling (NAIS) technique which is nonparametrically modified version of AIS and test it to estimate a probability of rare event in M/M/1 queueing model. Comparing with classical Monte Carlo simulation, the computational efficiency and variance reductions gained via NAIS are substantial. A possible extension of NAIS regarding with random number generation is also discussed.

• The Korean Journal of Applied Statistics
• /
• v.27 no.2
• /
• pp.277-290
• /
• 2014

We analyzed binary landslide data from the Boeun area with logistic regression. Since the number of landslide occurrences is only 9 out of 5000 observations, this can be regarded as a rare event data. The main issue of logistic regression with the rare event data is a serious bias problem in regression coefficient estimates. Two bias correction methods were proposed before and we quantitatively compared them via simulation. Firth (1993)'s approach outperformed and provided the most stable results for analyzing the rare-event binary data.

• The KIPS Transactions:PartD
• /
• v.16D no.5
• /
• pp.691-700
• /
• 2009

An event means a flow which has a time attribute such as the a symptom of patients, an interval event has the time period between the start-time-point and the end-time-point. Although there are many studies for temporal data mining, they do not deal with discovering knowledge from interval event such as patient histories and purchase histories. In this paper, we suggest a method of temporal data mining that finds association rules of event causal relationships and predicts an occurrence of effect event based on discovered rules. Our method can predict the occurrence of an event by summarizing an interval event using the time attribute of an event and finding the causal relationship of event. As a result of simulation, this method can discover better knowledge than others by considering a lot of supports of an event and finding the significant rare relation on interval events which means an essential cause of an event, regardless of an occurrence support of an event in comparison with conventional data mining techniques.

• Journal of the Korea Society for Simulation
• /
• v.8 no.3
• /
• pp.77-89
• /
• 1999

Simulating rare events, such as probability of cell loss in ATM networks, machine failure in highly reliable systems, requires huge simulation efforts due to the low chance of occurrence. Importance Sampling (IS) has been applied to accelerate the occurrence of rare events. However, it has a drawback of effective biasing scheme to make the estimator of IS unbiased. Adaptive Importance Sampling (AIS) employs an estimated sampling distribution of IS to the system of interest during the course of simulation. We propose Nonparametric Adaptive Importance Sampling (NAIS) technique which is nonparametrical version of AIS. We test NAIS to estimate a probability of rare event in M/M/1 queueing model. Comparing with classical Monte Carlo simulation, the computational efficiency and variance reductions gained via NAIS are substantial. A possible extension of NAIS regarding with random number generation is also discussed.

• Communications for Statistical Applications and Methods
• /
• v.7 no.2
• /
• pp.499-511
• /
• 2000

We consider a stable tandem network which consists of two M/M/1 nodes and study the probability that the total backlog exceeds a large level N. Since the excessive backlog is a rare event, it is difficult to estimate this probability efficiently by using the crude Monte Carlo simulation. Instead we perform the ;$h$-transform proposed by McDonald(1999) to obtain the twisted network, in which the node with the larger load is overloaded. Then we use it to run the fast simulation.

• Communications for Statistical Applications and Methods
• /
• v.31 no.1
• /
• pp.65-85
• /
• 2024

The tail probability of a function of a multivariate random variable is not easy to estimate by the crude Monte Carlo simulation. When the occurrence of the function value over a threshold is rare, the accurate estimation of the corresponding probability requires a huge number of samples. When the explicit form of the cumulative distribution function of each component of the variable is known, the inverse transform likelihood ratio method is directly applicable scheme to estimate the tail probability efficiently. The method is a type of the importance sampling and its efficiency depends on the selection of the importance sampling distribution. When the cumulative distribution of the multivariate random variable is represented by a copula and its marginal distributions, we develop an iterative algorithm to find the optimal importance sampling distribution, and show the convergence of the algorithm. The performance of the proposed scheme is compared with the crude Monte Carlo simulation numerically.

• Communications for Statistical Applications and Methods
• /
• v.11 no.1
• /
• pp.181-187
• /
• 2004

One of objectives in epidemiologic studies is to detect the amount of change caused by a specific risk factor. Risk ratio is one of the most useful measurements in epidemiology. When we perform the inference for this measurement with rare events, the standard approach based on the normal approximation may fail, in particular when there are no disease cases observed. In this paper, we discuss and evaluate several existing methods for constructing a confidence interval of risk ratio through simulation when the disease of interest is a rare event. The results in this paper provide guidance with how to construct interval estimates for risk difference and risk ratio when there are no disease cases observed.

• Nuclear Engineering and Technology
• /
• v.54 no.6
• /
• pp.2084-2093
• /
• 2022

Probabilistic safety assessment is widely used to quantify the risks of nuclear power plants and their uncertainties. When the lognormal distribution describes the uncertainties of basic events, the uncertainty of the top event in a fault tree is approximated with the sum of lognormal random variables after minimal cutsets are obtained, and rare-event approximation is applied. As handling complicated analytic expressions for the sum of lognormal random variables is challenging, several approximation methods, especially Monte Carlo simulation, are widely used in practice for uncertainty analysis. In this study, a theoretical approach for analyzing the sum of lognormal random variables using an efficient numerical integration method is proposed for uncertainty analysis in probability safety assessments. The change of variables from correlated random variables with a complicated region of integration to independent random variables with a unit hypercube region of integration is applied to obtain an efficient numerical integration. The theoretical advantages of the proposed method over other approximation methods are shown through a benchmark problem. The proposed method provides an accurate and efficient approach to calculate the uncertainty of the top event in probabilistic safety assessment when the uncertainties of basic events are described with lognormal random variables.

• Proceedings of the KSR Conference
• /
• 2007.11a
• /
• pp.371-376
• /
• 2007

This paper describes a study to determine proper escape way interval for the design phase of single bored double track tunnel. Among many methods which determine escape way interval, we choose a QRA(Quantitative Risk Analysis) method. But a different method must be chosen differ from other country because of special design situation of Korea. So, it is necessary to develop a method which considers a special design condition of Korea. Because fire accidents of railway tunnel are a rare event, simulated situation can be produced by CFD simulation and evacuation analysis simulation. However, it is generally difficult to estimate of fatalities from these methods, so a concept of FED is introduced to estimate of fatalities. Quantification process provides effective results for practical design stage and the result were employed in design.

• Proceedings of the Korea Society for Simulation Conference
• /
• 1996.05a
• /
• pp.9-9
• /
• 1996

광대역 종합정보 통신망의 핵심요소라 할 수 있는 ATM 스위치의 성능척도 중 가장 중요하게 다루어지고 있는 것은 셀 손실확률과 셀 전달지연시간이다. 이 중에서도 샐 손실확률기 추정에 대한 연구가 활발히 진행되고 있는데, ATM 스위치는 손실에 민감한 트래픽까지도 제대로 다루기 위하여 정도까지의 샐 손실확률을 보장할 수 있어야 한다. 이와같은 희소사건(rare event)의 확률 추정에 있어 원하는 정도의 precision을 가능한한 적은비용으로 얻어내기 위한 분산축소기법은 필수적이라 할 수 있다. Homogeneous 입력원을 갖는 ATM 스위치의 셀 손실확률 추정에 관련된 이전의 연구결과는 시뮬레이션과 분석적기법을 혼합시켜 얻어지는 새로운 개념의 추정치, 즉 hybrid 시뮬레이션 추정치의 도입을 통하여 상당한 정도의 분산축소 효과를 거둘 수 있음을 나타내주고 있다. 본 연구는 이에 대한 확장으로, 각각의 도착 프로세스가 서로 다른heterogeneous 입력원을 갖는 ATM 스위치의 셀 손실화률 추정에 적용될 수 있는 hybrid 시뮬레이션 기법을 개발하고자 한다. 사용된 모델은 이산시간대기모델()로 각입력원의 도착 프로세스는 Interrupted Bernoulli Process로 가정하였으며, 분석적 기법의 적용을 위한 입력원 통합(aggregation) 알고리듬과 실제 시뮬레이션 방법 등을 제시하였다. 또한 제시된 기법의 성능은 기존의 일반적인 시뮬레이션 추정치를 이용하여 얻어진 결과와의 비교를 통하여 분석되었다.