• The Korean Journal of Applied Statistics
• /
• v.13 no.2
• /
• pp.563-573
• /
• 2000

In this paper, we propose three estimators of Kullback-Leibler Information functions using the data from accelerated life tesb. This acceleration model is assumed to be a tampered random variable model. Some asymptotic properties of proposed estimators are proved. Simulations are performed for comparing the small sample properties of the proposed estimators under use condition of accelerated life test.

• International Commerce and Information Review
• /
• v.9 no.4
• /
• pp.439-460
• /
• 2007

The purpose of this paper is to study on export factor of Korean into China by 31 Province and City. Using the panel data on Korean export factor in China for the years 1998-2005, we examined the factors determinants of import in China(by region)from Korean firms. This study based on Gravity Model to extend and fixed & random effect Model. The result of analysis is as follows : The effect of significant on Import from Korean is FDI from Korea, export into world, import from world, population in region. But per GRDP, consumption, FDI into world variable is statistically insignificant. Also coastal region variable is not a clear.

• Journal of KSNVE
• /
• v.6 no.6
• /
• pp.791-800
• /
• 1996

Linear LQG controller has been investigated to control flexible link manipulators. The performance and complexity of these depend largely on the model upon which the controller is designed. In this study, the flexible modes of the link manipulator are considered to have uncertain parameters, which can be represented by random variable and these parameters are reflected on the weighting of performance. In this method, the exact modelling for the flexible modes is not necessary. The order of the resulting controller is much lower than the one based on a full model. Through numerical study, it is shown that the performance and the stability-robustness of the proposed controller reaches reasonably the one based on the full model.

• Journal of Welding and Joining
• /
• v.19 no.6
• /
• pp.652-657
• /
• 2001

To analyze and predict crack initiation position and propagation directions on the spot welded area are very important for strength design of the automobile body structure. It is necessary to test by method considering random loads with variable amplitude for strength design of vehicle body structure, because driving cars are actually subjected to random loads with variable amplitude in the road. Although this condition, nearly all tests haute been performed under constant load conditions in the laboratory because it is impossible to replay like an actual conditions. In this study, using in-plane bending type specimens, the overload factor affecting on the fatigue strength, crack initiation and propagation directions of spot-welded specimens have been studied.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2184-2187
• /
• 2003

Quantizers for digital coding systems are usually optimized with respect to a model of the probability density function of the random variable to be quantized. Thus a mismatch of the quantizer relative to the actual statistics of the random variable may be unavoidable. This paper presents the results of an experimental investigation of mismatched quantizers. For the modeling of the source statistics, various types of the Weibull distribution are used, and the optimization of the quantizer is carried with respect to the minimum mean-square error (mse) criterion. The goal of this paper is to find an estimate formula for the mismatched quantizer on Weibull sources.

• Communications for Statistical Applications and Methods
• /
• v.16 no.1
• /
• pp.185-193
• /
• 2009

Machine learning methods such as support vector machines and random forests yield nonparametric prediction functions of the form y = $f(x_1,{\ldots},x_p)$. As a sequel to the previous article (Huh and Lee, 2008) for visualizing nonparametric functions, I propose more sensible graphs for visualizing y = $f(x_1,{\ldots},x_p)$ herein which has two clear advantages over the previous simple graphs. New graphs will show a small number of prototype curves of $f(x_1,{\ldots},x_{j-1},x_j,x_{j+1}{\ldots},x_p)$, revealing statistically plausible portion over the interval of $x_j$ which changes with ($x_1,{\ldots},x_{j-1},x_{j+1},{\ldots},x_p$). To complement the visual display, matching importance measures for each of p predictor variables are produced. The proposed graphs and importance measures are validated in simulated settings and demonstrated for an environmental study.

• School Mathematics
• /
• v.4 no.4
• /
• pp.677-688
• /
• 2002

The context and intuitive understanding is very important in Statistics Education. Especially, there is a need to mitigate student's difficulty in studying probability density function. One of teaching method this concept is to using relative frequency histogram. But, as using this method, we should know several problems included in that. This study investigate problems in the method for teaching probability density function as gradual meaning of histogram. Also, as alternative approach, this thesis introduce the density curve concept. The application of four methods to teach the concept of the probability density function and analysis of the survey result is done in this research.

• Journal of the Korea Safety Management & Science
• /
• v.4 no.3
• /
• pp.59-66
• /
• 2002

This paper presents accelerated life tests for Type I censoring data under probabilistic stresses. Probabilistic stress, S, is the random variable for stress influenced by test environments, test equipments, sampling devices and use conditions. The hazard rate, $\theta$ is a random variable of environments and a function of probabilistic stress. In detail, it is assumed that the hazard rate is linear function of the stress, the general stress distribution is a gamma distribution and the life distribution for the given hazard rate, $\theta$is an exponential distribution. Maximum likelihood estimators of model parameters are obtained, and the mean life in use stress condition is estimated. A hypothetical example is given to show its applicability.

• 한국데이터정보과학회:학술대회논문집
• /
• 2004.10a
• /
• pp.111-111
• /
• 2004

• 전기의세계
• /
• v.17 no.1
• /
• pp.48-50
• /
• 1968

The convergence rate of Bayes' learning process is investigated for a binomial random variable. A measure of the rate of convergence is proposed and it is found that such a measure can be approximated by an exponential function of the number of observations.