• Journal of the Korean Data and Information Science Society
• /
• v.21 no.1
• /
• pp.51-59
• /
• 2010

In the case that the regression function has a discontinuity point in generalized linear model, Huh (2009) estimated the location and jump size using the log-likelihood weighted the one-sided kernel function. In this paper, we consider estimation of the unknown number of the discontinuity points in the regression function. The proposed algorithm is based on testing of the existence of a discontinuity point coming from the asymptotic distribution of the estimated jump size described in Huh (2009). The finite sample performance is illustrated by simulated example.

• Communications for Statistical Applications and Methods
• /
• v.19 no.1
• /
• pp.135-145
• /
• 2012

It is well known that the maximum likelihood estimator(MLE) in normal mixture models with unequal variances does not fall in the interior of the parameter space. Recently, a doubly smoothed maximum likelihood estimator(DS-MLE) (Seo and Lindsay, 2010) was proposed as a general alternative to the ordinary maximum likelihood estimator. Although this method gives a natural modification to the ordinary MLE, its computation is cumbersome due to intractable integrations. In this paper, we derive an EM algorithm for the DS-MLE under normal mixture models and propose a fast computational tool using a local quadratic approximation. The accuracy and speed of the proposed method is then presented via some numerical studies.

• Journal of information and communication convergence engineering
• /
• v.13 no.3
• /
• pp.152-158
• /
• 2015

We consider the problem of designing independently operating local quantizers at nodes in distributed estimation systems, where many spatially distributed sensor nodes measure a parameter of interest, quantize these measurements, and send the quantized data to a fusion node, which conducts the parameter estimation. Motivated by the discussion that the estimation accuracy can be improved by using the quantized data with a high probability of occurrence, we propose an iterative algorithm with a simple design rule that produces quantizers by searching boundary values with an increased likelihood. We prove that this design rule generates a considerably reduced interval for finding the next boundary values, yielding a low design complexity. We demonstrate through extensive simulations that the proposed algorithm achieves a significant performance gain with respect to traditional quantizer designs. A comparison with the recently published novel algorithms further illustrates the benefit of the proposed technique in terms of performance and design complexity.

• The Korean Journal of Applied Statistics
• /
• v.32 no.4
• /
• pp.561-572
• /
• 2019

We study false discovery rate segmentation (FDRSeg) and simultaneous multiscale change-point estimator (SMUCE) methods for multiscale multiple change-point estimation, and compare empirical behavior via simulation. FSRSeg is based on the control of a false discovery rate while SMUCE used for the multiscale local likelihood ratio tests. FDRSeg seems to work best if the number of change-points is large; however, FDRSeg and SMUCE methods can both provide similar estimation results when there are only a small number of change-points. As a real data application, multiple change-points estimation is done with the well-log data.

• The Korean Journal of Applied Statistics
• /
• v.21 no.5
• /
• pp.801-811
• /
• 2008

Modeling financial phenomena with diffusion processes is a commonly used methodology in the area of modern finance. Recently, various types of diffusion models have been suggested to explain the specific financial processes, and their related inference methodology have been also developed. In particular, likelihood methods for the efficient and accurate inference have been explored in various ways. In this paper, we review the mathematical properties of an approximated likelihood method, which is obtained by linearizing the drift coefficient of a diffusion process.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.6
• /
• pp.1627-1648
• /
• 2012

We propose an adaptive method for detecting plagiarized pairs from a large set of source code. This method is adaptive in that it uses an adaptive algorithm and it provides an adaptive threshold for determining plagiarism. Conventional algorithms are based on greedy string tiling or on local alignments of two code strings. However, most of them are not adaptive; they do not consider the characteristics of the program set, thereby causing a problem for a program set in which all the programs are inherently similar. We propose adaptive local alignment-a variant of local alignment that uses an adaptive similarity matrix. Each entry of this matrix is the logarithm of the probabilities of the keywords based on their frequency in a given program set. We also propose an adaptive threshold based on the local outlier factor (LOF), which represents the likelihood of an entity being an outlier. Experimental results indicate that our method is more sensitive than JPlag, which uses greedy string tiling for detecting plagiarism-suspected code pairs. Further, the adaptive threshold based on the LOF is shown to be effective, and the detection performance shows high sensitivity with negligible loss of specificity, compared with that using a fixed threshold.

• Journal of Korea Multimedia Society
• /
• v.23 no.7
• /
• pp.883-890
• /
• 2020

In this paper, we propose a variational expectation-maximization algorithm that computes posterior probabilities from Latent Dirichlet Allocation (LDA) model. The algorithm approximates the intractable posterior distribution of a document term matrix generated from a corpus made up by 50 papers. It approximates the posterior by searching the local optima using lower bound of the true posterior distribution. Moreover, it maximizes the lower bound of the log-likelihood of the true posterior by minimizing the relative entropy of the prior and the posterior distribution known as KL-Divergence. The experimental results indicate that documents clustered to image classification and segmentation are correlated at 0.79 while those clustered to object detection and image segmentation are highly correlated at 0.96. The proposed variational inference algorithm performs efficiently and faster than Gibbs sampling at a computational time of 0.029s.

• Communications of the Korean Mathematical Society
• /
• v.20 no.1
• /
• pp.145-159
• /
• 2005

In this paper we consider the problem of testing statistical hypotheses for unknown parameters in nonlinear regression models and propose three asymptotically equivalent tests based on regression quantiles estimators, which are Wald test, Lagrange Multiplier test and Likelihood Ratio test. We also derive the asymptotic distributions of the three test statistics both under the null hypotheses and under a sequence of local alternatives and verify that the asymptotic relative efficiency of the proposed test statistics with classical test based on least squares depends on the error distributions of the regression models. We give some examples to illustrate that the test based on the regression quantiles estimators performs better than the test based on the least squares estimators of the least absolute deviation estimators when the disturbance has asymmetric and heavy-tailed distribution.

• Journal of the Korean Data and Information Science Society
• /
• v.7 no.2
• /
• pp.257-262
• /
• 1996

When we are estimate the smoothing parameter in spline regression model, we deal the diagnostic of influence observations as posteriori analysis. When we use Generalized Maximum Likelihood Function as the estimation method of smoothing parameter, we propose the diagnostic measure for influencial observations in the obtained estimate, and we introduce the finding method of the proper smoothing parameter estimate.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.109.3-109
• /
• 2001

The so-called curse of dimensionality arises when Gaussian mixture is used on high-dimensional small-sample-size data, since the number of free elements that needs to be specied in each covariance matrix of Gaussian mixture increases exponentially with the number of dimension d. In this paper, by constraining the covariance matrix in its decomposed orthonormal form we get a local PCA model so as to reduce the number of free elements needed to be specified. Moreover, to cope with the small sample size problem, we adopt BYY data smoothing learning which is a regularization over maximum likelihood learning obtained from BYY harmony learning to implement this local PCA model.