• The Korean Journal of Applied Statistics
• /
• v.35 no.2
• /
• pp.217-227
• /
• 2022

Quantile regression is widely used in many fields based on the advantage of providing an efficient tool for examining complex information latent in variables. However, modern large-scale and high-dimensional data makes it very difficult to estimate the quantile regression model due to limitations in terms of computation time and storage space. Divide-and-conquer is a technique that divide the entire data into several sub-datasets that are easy to calculate and then reconstruct the estimates of the entire data using only the summary statistics in each sub-datasets. In this paper, we studied on a variable selection method using Bayes information criteria by applying the divide-and-conquer technique to the penalized quantile regression. When the number of sub-datasets is properly selected, the proposed method is efficient in terms of computational speed, providing consistent results in terms of variable selection as long as classical quantile regression estimates calculated with the entire data. The advantages of the proposed method were confirmed through simulation data and real data analysis.

• Proceedings of the KSME Conference
• /
• 2005.11a
• /
• pp.214.2-214.2
• /
• 2005

• Journal of the Korean Statistical Society
• /
• v.6 no.2
• /
• pp.103-115
• /
• 1977

A strategy for selecting subsets of variables from a given linear model in a mixture system is discussed. The purpose is to achieve better fitting surfaces for estimation of the response in an experimental region of interest. A criterion is proposed for screening variables and illustrated with an example.

• Communications for Statistical Applications and Methods
• /
• v.24 no.4
• /
• pp.325-337
• /
• 2017

In this paper, we proposed a new long-term lifetime distribution with four parameters inserted in a risk competitive scenario with decreasing, increasing and unimodal hazard rate functions, namely the Weibull-Poisson long-term distribution. This new distribution arises from a scenario of competitive latent risk, in which the lifetime associated to the particular risk is not observable, and where only the minimum lifetime value among all risks is noticed in a long-term context. However, it can also be used in any other situation as long as it fits the data well. The Weibull-Poisson long-term distribution is presented as a particular case for the new exponential-Poisson long-term distribution and Weibull long-term distribution. The properties of the proposed distribution were discussed, including its probability density, survival and hazard functions and explicit algebraic formulas for its order statistics. Assuming censored data, we considered the maximum likelihood approach for parameter estimation. For different parameter settings, sample sizes, and censoring percentages various simulation studies were performed to study the mean square error of the maximum likelihood estimative, and compare the performance of the model proposed with the particular cases. The selection criteria Akaike information criterion, Bayesian information criterion, and likelihood ratio test were used for the model selection. The relevance of the approach was illustrated on two real datasets of where the new model was compared with its particular cases observing its potential and competitiveness.

• Asian-Australasian Journal of Animal Sciences
• /
• v.32 no.2
• /
• pp.183-191
• /
• 2019

Objective: The purpose of this study was to compare intended and actual yearly genetic gains for milk production and conformation traits and to investigate the simple selection criterion practiced among milk production and conformation traits during the last two decades in Japan. Learning how to utilize the information on intended and actual genetic gains during the last two decades into the genomic era is vital. Methods: Genetic superiority for each trait for four paths of selection (sires to breed bulls [SB], sires to breed cows [SC], dams to breed bulls [DB], and dams to breed cows [DC]) was estimated. Actual practiced simple selection criteria were investigated among milk production and conformation traits and relative emphasis on milk production and conformation traits was compared. Results: Selection differentials in milk production traits were greater than those of conformation traits in all four paths of selection. Realized yearly genetic gain was less than that intended for milk production traits. Actual annual genetic gain for conformation traits was equivalent to or greater than intended. Retrospective selection weights of milk production and conformation traits were 0.73:0.27 and 0.56:0.44 for intended and realized genetic gains, respectively. Conclusion: Selection was aimed more toward increasing genetic gain in milk production than toward conformation traits over the past two decades in Japan. In contrast, actual annual genetic gain for conformation traits was equivalent to or greater than intended. Balanced selection between milk production and conformation traits tended to be favored during actual selection. Each of four paths of selection (SB, SC, DB, and DC) has played an individual and important role. With shortening generation interval in the genomic era, a young sire arises before the completion of sire's daughters' milk production records. How to integrate these four paths of selection in the genomic era is vital.

• Korean Journal of Agricultural Science
• /
• v.47 no.4
• /
• pp.1083-1096
• /
• 2020

Global attention to the greenhouse gas emissions from deforestation and forest degradation is increasing. There is a growing recognition of reducing emission from deforestation and forest degradation plus (REDD+) as an effective way to reduce greenhouse gas emissions in the forestry sector. The Republic of Korea is implementing REDD+ pilot projects in four Southeast Asian countries as part of its efforts to reduce greenhouse gas emissions. This study evaluates countries with the potential to become priority partner countries for Korea's REDD+ programs, using the following five criteria: The first criterion is that a country should include the forest sector and REDD+ in its national plan for reducing greenhouse gas (GHG) emissions. The second and third criteria refer to an average forest coverage rate of over 44% and a forest change rate of over - 0.1%, among the countries with forest cover of more than 10 million ha. The fourth criterion is that the country should meet the Forest Reference Emission Level requirements, one of the four elements of the Warsaw REDD+ Framework. The fifth criterion is that the country should have bilateral relations with the Republic of Korea in forestry while at the same time be a partner country for cooperation on climate change as well as a REDD+ pilot country. Based on our evaluation, we conclude that the first priority countries are Indonesia, Cambodia, and Myanmar. The second priority countries include Brazil, Ecuador, and Peru. Finally, the third priority countries are Columbia, Congo, and Mozambique. This study suggests that for the selection of priority partner countries, Korean REDD+ programs should center on existing REDD+ pilot countries.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.421-427
• /
• 2001

In this paper, a method for selection of the optimal feature vectors is proposed for the classification of closed 2D shapes using the bispectrum of a contour sequence. The bispectrum based on third order cumulants is applied to the contour sequences of the images to extract feature vectors for each planar image. These bispectral feature vectors, which are invariant to shape translation, rotation and scale transformation, can be used to represent two-dimensional planar images, but there is no certain criterion on the selection of the feature vectors for optimal classification of closed 2D images. In this paper, a new method for selecting the optimal bispectral feature vectors based on the variances of the feature vectors. The experimental results are presented using eight different shapes of aircraft images, the feature vectors of the bispectrum from five to fifteen and an weighted mean fuzzy classifier.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.1C
• /
• pp.22-27
• /
• 2011

This paper proposes an efficient user selection algorithm that provides a maximum 셀 용량 based Multi-user MIMO system based on zero-forcing criterion. The proposed scheme forms a primary group of users whose channel power exceeds a predetermined threshold. Through computer simulations, we have found that the proposed method outperforms the conventional scheme yielding a sum rate that is 0.33 bps/Hz higher when the total numbers of users and transmit antennas in the cell are 100 and 4, respectively.

• International journal of advanced smart convergence
• /
• v.9 no.1
• /
• pp.98-108
• /
• 2020

We consider transmit antenna selection combined with power allocation for quadrature spatial modulation (QSM) systems to improve the error rate performance. The Euclidean distance-based joint optimization criterion is presented for transmit antenna selection and power allocation in QSM. It requires an exhaustive search and thus high computational complexity. Thus its reduced-complexity algorithm is proposed with a strategy of decoupling, which is employed to successively find transmit antennas and power allocation factors. First, transmit antennas are selected without considering power allocation. After selecting transmit antennas, power allocation factors are determined. Simulation results demonstrate considerable performance gains with lower complexity for transmit antenna selected QSM systems with power allocation, which can be achieved with limited rate feedback.

• International Journal of Costume and Fashion
• /
• v.4
• /
• pp.47-61
• /
• 2004

This study analyzed the buying patterns of American and Korean female college students in terms of criteria for clothing selection； store preferences； criteria for store selection； fashion information sources； expressions of customer dissatisfaction； purchasing frequency and motivations for purchasing clothes. The study was implemented through self-administered questionnaires which were back translated for validity. The samples consisted of 730 female college students majoring in the fields related to clothing and textiles： 310 U.S. and 412 Korean students. Likert scales were used for most measures with 1＝never or very unimportant and 5＝always or very important. Data were analyzed by factor analysis, analysis of covariance, Duncans multiple comparison, and t-test. Results are as follows： 1) Design factor was the most important criteria in clothing selection with no differences between country groups. There were, however, significant differences for psychological exhibition factors, practical and economic factors. 2) Both groups preferred specialty and department stores, with department stores more popular in Korea. 3) Merchandise was the most important store selection criterion and fashion magazines and self-experience were rated as the most important information sources for the both groups. 4) Korean group expressed their dissatisfaction with and observable problem with a product before purchase more often than U.S. group, but the U.S. group was more vocal about color loss or shrinkage after care procedures. 5) Some clear differences between the two countries emerged. Marketers targeting American consumers should pay more attention to practicality and service； to Korean consumers more symbolic meaning of products.