• Communications for Statistical Applications and Methods
• /
• v.16 no.3
• /
• pp.479-485
• /
• 2009

When a part of data is unobserved the marginal likelihood of parameters given the observed data often involves analytically intractable high dimensional integral and hence it is hard to find the maximum likelihood estimate of the parameters. Simulated maximum likelihood(SML) method which estimates the marginal likelihood via Monte Carlo importance sampling and optimize the estimated marginal likelihood has been used in many applications. A key issue in SML is to find a good proposal density from which Monte Carlo samples are generated. The optimal proposal density is the conditional density of the unobserved data given the parameters and the observed data, and attempts have been given to find a good approximation to the optimal proposal density. Algorithms which adaptively improve the proposal density have been widely used due to its simplicity and efficiency. In this paper, we describe a fully adaptive algorithm which has been used by some practitioners but has not been well recognized in statistical literature, and evaluate its estimation performance and robustness via a simulation study. The simulation study shows a great improvement in the order of magnitudes in the mean squared error, compared to non-adaptive or partially adaptive SML methods. Also, it is shown that the fully adaptive SML is robust in a sense that it is insensitive to the starting points in the optimization routine.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2003.11a
• /
• pp.340-343
• /
• 2003

This study presents a practical procedure for the Bayesian inversion of geophysical data by Markov chain Monte Carlo (MCMC) sampling and geostatistics. We have applied geostatistical techniques for the acquisition of prior model information, and then the MCMC method was adopted to infer the characteristics of the marginal distributions of model parameters. For the Bayesian inversion of dipole-dipole array resistivity data, we have used the indicator kriging and simulation techniques to generate cumulative density functions from Schlumberger array resistivity data and well logging data, and obtained prior information by cokriging and simulations from covariogram models. The indicator approach makes it possible to incorporate non-parametric information into the probabilistic density function. We have also adopted the MCMC approach, based on Gibbs sampling, to examine the characteristics of a posteriori probability density function and the marginal distribution of each parameter. This approach provides an effective way to treat Bayesian inversion of geophysical data and reduce the non-uniqueness by incorporating various prior information.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.1
• /
• pp.191-202
• /
• 2009

In this study, we drive the one dimensional marginal transform function, probability density function and probability distribution function for the random variables $T_{{\xi}N}$ (Time taken by the servers during the vacations), ${\xi}_N$(Number of vacations taken by the servers) and ${\eta}_N$(Number of customers or units arrive in the system) by controlling the variability of two random variables simultaneously.

• Journal of the Korean Statistical Society
• /
• v.29 no.3
• /
• pp.307-313
• /
• 2000

Suppose we have a set of data X1, ···, Xn and employ kernel density estimator to estimate the marginal density of X. in this article bandwith selection problem for kernel density estimator is examined closely. In particular the Kullback-Leibler method (a bandwith selection methods based on average square error (ASE)) is considered.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.1
• /
• pp.207-215
• /
• 2017

In this paper we study pooling effects in Bayesian testing procedures of independence for contingency tables from small areas. In small area estimation setup, we typically use a hierarchical Bayesian model for borrowing strength across small areas. This techniques of borrowing strength in small area estimation is used to construct a Bayes test of independence for contingency tables from small areas. In specific, we consider the methods of direct or indirect pooling in multinomial models through Dirichlet priors. We use the Bayes factor (or equivalently the ratio of the marginal likelihoods) to construct the Bayes test, and the marginal density is obtained by integrating the joint density function over all parameters. The Bayes test is computed by performing a Monte Carlo integration based on the method proposed by Nandram and Kim (2002).

• East Asian Economic Review
• /
• v.22 no.2
• /
• pp.141-176
• /
• 2018

The paper analyzes and compares the effects of domestic monetary policy using DSGE, DSGE-VAR, and VAR based on a two-country open economy model of Korea and the U.S. According to impulse response analysis, a domestic interest rate hike raises won value in the case of DSGE and DSGE-VAR models, while in the case of the unrestricted VAR model, it lowers won value. In the marginal data density standard, DSGE-VAR (${\mu}=1$) is superior to DSGE or Bayesian VAR over the sample period. Conversely, in the in-sample RMSE criterion, especially for the won/dollar exchange rate, VARs are superior to DSGE or DSGE-VAR. It is necessary to study further if these differences are caused by model misspecification or omitted variable bias.

• The Korean Journal of Applied Statistics
• /
• v.28 no.6
• /
• pp.1191-1208
• /
• 2015

Most statistical methods are dependent on the summary statistic. However, with graphical approaches, it is easier to identify the characteristics of the data and detect information that cannot be obtained by the summary statistic. We present various graphical methods to assess the adequacy of models in logistic regression that include checking log-density ratio, structural dimension, marginal model plot, chi-residual plot, and CERES plot. Through simulation data, we investigate and compare the results of graphical approaches under diverse conditions.

• Geophysics and Geophysical Exploration
• /
• v.5 no.4
• /
• pp.262-271
• /
• 2002

This study presents a practical procedure for the Bayesian inversion of geophysical data. We have applied geostatistical techniques for the acquisition of prior model information, then the Markov Chain Monte Carlo (MCMC) method was adopted to infer the characteristics of the marginal distributions of model parameters. For the Bayesian inversion of dipole-dipole array resistivity data, we have used the indicator kriging and simulation techniques to generate cumulative density functions from Schlumberger array resistivity data and well logging data, and obtained prior information by cokriging and simulations from covariogram models. The indicator approach makes it possible to incorporate non-parametric information into the probabilistic density function. We have also adopted the MCMC approach, based on Gibbs sampling, to examine the characteristics of a posteriori probability density function and the marginal distribution of each parameter.

• Journal of the Korean earth science society
• /
• v.33 no.6
• /
• pp.554-566
• /
• 2012

High-density temperature and salinity profiles from the successful international Argo project made it possible to reproduce the three-dimensional global ocean state in near-real time, which also increased much attention on the data analysis studies of global ocean. This paper reviewed several important issues on the recent data analysis studies such as systematic biases of XBT (eXpendable BathyThermograph) and Argo data, sea level budget discrepancy between steric height and satellite observed data, heat content change, and the current status of the development of objective analysis fields. This study also emphasized that it is required to carry out very cautious ocean data quality control and understand global-scale ocean variability prior to analyzing the regional-scale ocean climate change, particularly, in the East Asian marginal Seas.

• The Korean Journal of Ecology
• /
• v.21 no.5_3
• /
• pp.649-663
• /
• 1998

The clarify the ecological properties, and to predict change of understory vegetation of mt. Nam Park, population dynamics and interspecific competition of D. smilacinum and D. viridescens, which grow in understory of deciduous broad-leaved forest and pseudo-annuals, were studied from May 20 to May 30 1998. The depth of litter layer, soil moisture content, soil organic matter and soil texture were surveyed in 18 populations (15 D. smilacinum populations and 3 D. viridescens populations). Mean litter layer of d. smilacimum population was thinner than that of D. viridescens populations). Mean litter layer of D. smilacnum population was thinner than that of D. viridescens population. The contents of soil moisture and organic matter of D. smilacinum population were lower than that of D. viridescens population. The D. smilacinum growed in broad range of soil texture but D. viridescens in loamy soil. Because D. smilacinum could tolerate more broad range of soil moisture and soil texture than D. viridescens, the former covered the herb layer in earlier stage and the latter introduced in later stage when rhizome could grow easily. The numbers of individual in two marginal parts were smaller than that in center in same D. smilacinum patch. And the total numbers of individuals grown in (10 ${\times}$ 10)cm were from 0 to 12. The rhizome (subterranean runner) weight, rhizome length, root weight, shoot weight, lea weight and leaf number per subquadrat (cell) increased along the number of individual, that is, increased from marginal part to center. But rhizome weight and rhizome length per individual were vice versa. Therefore, the individuals in marginal part reproduced longer and stronger asexual propagules than that in center. The distribution pattern of D. smilacinum was contageous and that of D. viridescens was random or regular. Therefore, population growth of former was independent on density and that of latter was dependent on density. The distributions of size-class showed normal curves in two population, but the curves based on data of total dry weight showed positive skewness and those of leaf number showed negative skewness The correlation coefficient (CC) values between the properties of each organ were high in two population and significant at 0.1% level. The CC values of D. viridescens were higher of the two. Therefore, the former allocated the energy to each organ stable. The rhizome depth of d. viridescens was 2 times deeper than that of D. smilacinum. And rhizome length and weight of D. viridescens were longer (2 times) or heavier (4 times) than those of D. smilacinum. The patch size of D. viridescens increased 60 cm per year and that of D. smilacinum 30 cm. On this results, the intrinsic increase velocity of d. viridescens patch was 2 times faster than that of d. smilacinum, therefore, on the competition, the former had an advantage over D. smilacinum. The reason why d. viridescens defeated D. smilacinum resulted from that the leaf area of former was 4 times broader than that of latter. in Mt. Nam Park, it was thought that two disporum Population would change with the 3 thpes of environmental change as followings. First, no human impact and increase of soil moisture content resulted in increase of D. viridescens population. Second, mild human impact and similar condition of soil moisture content resulted in slow increase or no changes of D. smilacinum and d. viridescens population. Third, severe human impact and dry condition resulted in decrease or vanishment of two disporum populations.