• Korean Management Science Review
• /
• v.11 no.3
• /
• pp.1-11
• /
• 1994

Recent advances in linear programming solution methodology have focused on interior point methods. This powerful new class of methods achieves significant reductions in computer time for large linear programs and solves problems significantly larger than previously possible. These methods can be examined from points of Fiacco and McCormick's barrier method, Lagrangian duality, Newton's method, and others. This study presents a primal-dual log barrier algorithm of interior point methods for linear programming. The primal-dual log barrier method is currently the most efficient and successful variant of interior point methods. This paper also addresses a Cholesky factorization method of symmetric positive definite matrices arising in interior point methods. A special structure of the matrices, called supernode, is exploited to use computational techniques such as direct addressing and loop-unrolling. Two dense matrix handling techniques are also presented to handle dense columns of the original matrix A. The two techniques may minimize storage requirement for factor matrix L and a smaller number of arithmetic operations in the matrix L computation.

• Bulletin of the Korean Mathematical Society
• /
• v.51 no.1
• /
• pp.83-98
• /
• 2014

During the last decade, several papers have focused on linear q-difference equations of the form ${\sum}^n_{j=0}a_j(z)f(q^jz)=a_{n+1}(z)$ with entire or meromorphic coefficients. A tool for studying these equations is a q-difference analogue of the lemma on the logarithmic derivative, valid for meromorphic functions of finite logarithmic order ${\rho}_{log}$. It is shown, under certain assumptions, that ${\rho}_{log}(f)$ = max${{\rho}_{log}(a_j)}$ + 1. Moreover, it is illustrated that a q-Casorati determinant plays a similar role in the theory of linear q-difference equations as a Wronskian determinant in the theory of linear differential equations. As a consequence of the main results, it follows that the q-gamma function and the q-exponential functions all have logarithmic order two.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.1
• /
• pp.107-113
• /
• 2011

We present methods for studying the log-density ratio, which allow us to select which predictors are needed, and how they should be included in the logistic regression model. Under multivariate normal distributional assumptions, we investigate the form of the log-density ratio as a function of many predictors. The linear, quadratic and crossproduct terms are required in general. If two covariance matrices are equal, then the crossproduct and quadratic terms are not needed. If the variables are uncorrelated, we do not need the crossproduct terms, but we still need the linear and quadratic terms.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.9
• /
• pp.5367-5370
• /
• 2013

Background: Having knowledge or estimation of cancer incidence is necessary for planning and implementation of any cancer prevention and control programs. Population-based registries provide valuable information to achieve these objectives but require extra techniques to estimate the incidence rate. The present study aimed to estimate the esophageal cancer incidence using a log-linear method based on Tehran population-based cancer registry data. Materials and Methods: New cases of esophageal cancer reported by three sources of pathology reports, medical records, and death certificates to Tehran Metropolitan Area Cancer Registry Center during 2002-2006 were entered into the study and the incidence rate was estimated based on log-linear models. We used Akaike statistics to select the best-fit model. Results: During 2002-2006, 1,458 new cases of esophageal cancer were reported by the mentioned sources to the population-based cancer registry. Based on the reported cases, cancer incidence was 4.5 per 100,000 population and this was estimated to be 10.5 per 100,000 by the log-linear method. Conclusions: Based on the obtained results, it can be concluded that an estimated incidence for 2004 of 8.3 per 100,000 population could be a good benchmark for the incidence of esophageal cancer in the population of Tehran metropolis.

• The Korean Journal of Applied Statistics
• /
• v.30 no.2
• /
• pp.259-269
• /
• 2017

Due to the nonnegativity of variance, most of nonparametric estimations of discontinuous variance function have used the Nadaraya-Watson estimation with residuals. By the modification of Chen et al. (2009) and Yu and Jones (2004), Huh (2014, 2016a) proposed the estimators of the log-variance function instead of the variance function using the local linear estimator which has no boundary effect. Huh (2016b) estimated the variance function using the adjusted squared residuals by the estimated jump size in the discontinuous variance function. In this paper, we propose an estimator of the discontinuous log-variance function using the local linear estimator with the adjusted log-squared residuals by the estimated jump size of log-variance function like Huh (2016b). The numerical work demonstrates the performance of the proposed method with simulated and real examples.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.2
• /
• pp.543-557
• /
• 2006

This paper is concerned with the applicability of the chi-square approximation to the six disparity statistics: the Pearson chi-square, the generalized likelihood ratio, the power divergence, the blended weight chi-square, the blended weight Hellinger distance, and the negative exponential disparity statistic. Three dimensional contingency tables of small and moderate sample sizes are generated to be fitted to all possible hierarchical log-linear models: the completely independent model, the conditionally independent model, the partial association models, and the model with one variable independent of the other two. For models with direct solutions of expected cell counts, point estimates and confidence intervals of the 90 and 95 percentage points of six statistics are explored. For model without direct solutions, the empirical significant levels and the empirical powers of six statistics to test the significance of the three factor interaction are computed and compared.

• The Korean Journal of Applied Statistics
• /
• v.18 no.2
• /
• pp.395-410
• /
• 2005

For the analysis of large tables formed by many categorical variables, we suggest a method to group the variables into several disjoint groups in which the variables are completely associated within the groups. We use a simple function of Kullback-Leibler divergence as a similarity measure to find the groups. Since the groups are complete hierarchical sets, we can identify the association structure of the large tables by the marginal log-linear models. Examples are introduced to illustrate the suggested method.

• Communications for Statistical Applications and Methods
• /
• v.5 no.3
• /
• pp.847-853
• /
• 1998

Suppose we want to compare following non-hierarchical log-linear models, $H_0:f(x, heta inTheta_a)$ vs H_1:g(x, heta inTheta_eta); for; Theta_a,;Theta_etasubsetTheta;such;that;Theta_$\alpha$/ Theta_eta$. The goodness of fit test using the likelihood ratio test statistic for comparing these models could not be acceptable. By using the polyhedrons plots of Choi and Hong (1995), we propose a method to decide a better model between two non-hierarchical log-linear models $f(x: heta inTheta_a) and g(x: heta inTheta_eta)$.

• Communications for Statistical Applications and Methods
• /
• v.13 no.2
• /
• pp.297-307
• /
• 2006

Most methods for describing the relationship among random variables require specific probability distributions and some assumptions of random variables. The mutual information based on the entropy to measure the dependency among random variables does not need any specific assumptions. And the redundancy which is a analogous version of the mutual information was also proposed. In this paper, the redundancy and mutual information are explored to multi-dimensional categorical data. It is found that the redundancy for categorical data could be expressed as the function of the generalized likelihood ratio statistic under several kinds of independent log-linear models, so that the redundancy could also be used to analyze contingency tables. Whereas the generalized likelihood ratio statistic to test the goodness-of-fit of the log-linear models is sensitive to the sample size, the redundancy for categorical data does not depend on sample size but its cell probabilities itself.

• Communications for Statistical Applications and Methods
• /
• v.10 no.2
• /
• pp.607-617
• /
• 2003

This paper offers a practical comparison of efficiency between local likelihood approach and conventional kernel approach in density estimation. The local likelihood estimation procedure maximizes a kernel smoothed log-likelihood function with respect to a polynomial approximation of the log likelihood function. We use two types of data driven bandwidths for each method and compare the mean integrated squares for several densities. Numerical results reveal that local log-linear approach with simple plug-in bandwidth shows better performance comparing to the standard kernel approach in heavy tailed distribution. For normal mixture density cases, standard kernel estimator with the bandwidth in Sheather and Jones(1991) dominates the others in moderately large sample size.