• The Korean Journal of Applied Statistics
• /
• v.23 no.1
• /
• pp.207-218
• /
• 2010

Generalized additive model(GAM) is the statistical model that resolves most of the problems existing in the traditional linear regression model. However, overfitting phenomenon can be aroused without applying any method to reduce the number of independent variables. Therefore, variable selection methods in generalized additive model are needed. Recently, Lasso related methods are popular for variable selection in regression analysis. In this research, we consider Group Lasso and Elastic net models for variable selection in GAM and propose an algorithm for finding solutions. We compare the proposed methods via Monte Carlo simulation and applying auto insurance data in the fiscal year 2005. lt is shown that the proposed methods result in the better performance.

• Genomics & Informatics
• /
• v.10 no.2
• /
• pp.81-87
• /
• 2012

Large-scale copy number variants (CNVs) in the human provide the raw material for delineating population differences, as natural selection may have affected at least some of the CNVs thus far discovered. Although the examination of relatively large numbers of specific ethnic groups has recently started in regard to inter-ethnic group differences in CNVs, identifying and understanding particular instances of natural selection have not been performed. The traditional $F_{ST}$ measure, obtained from differences in allele frequencies between populations, has been used to identify CNVs loci subject to geographically varying selection. Here, we review advances and the application of multinomial-Dirichlet likelihood methods of inference for identifying genome regions that have been subject to natural selection with the $F_{ST}$ estimates. The contents of presentation are not new; however, this review clarifies how the application of the methods to CNV data, which remains largely unexplored, is possible. A hierarchical Bayesian method, which is implemented via Markov Chain Monte Carlo, estimates locus-specific $F_{ST}$ and can identify outlying CNVs loci with large values of FST. By applying this Bayesian method to the publicly available CNV data, we identified the CNV loci that show signals of natural selection, which may elucidate the genetic basis of human disease and diversity.

• The Korean Journal of Applied Statistics
• /
• v.14 no.1
• /
• pp.161-175
• /
• 2001

Meta-analysis refers to quantitative methods for combining results from independent studies in order to draw overall conclusions. Hierarchical models including selection models are introduced and shown to be useful in such Bayesian meta-analysis. Semiparametric hierarchical models are proposed using the Dirichlet process prior. These rich class of models combine the information of independent studies, allowing investigation of variability both between and within studies, and weight function. Here we investigate sensitivity of results to unobserved studies by considering a hierachical selection model with including unknown weight function and use Markov chain Monte Carlo methods to develop inference for the parameters of interest. Using Bayesian method, this model is used on a meta-analysis of twelve studies comparing the effectiveness of two different types of flouride, in preventing cavities. Clinical informative prior is assumed. Summaries and plots of model parameters are analyzed to address questions of interest.

• Animal Bioscience
• /
• v.37 no.3
• /
• pp.461-470
• /
• 2024

Objective: The objective of this study was to investigate the genetic diversity, population structure and whole-genome selection signatures of Luxi cattle to reveal its genomic characteristics in terms of meat and carcass traits, skeletal muscle development, body size, and other traits. Methods: To further analyze the genomic characteristics of Luxi cattle, this study sequenced the whole-genome of 16 individuals from the core conservation farm in Shandong region, and collected 174 published genomes of cattle for conjoint analysis. Furthermore, three different statistics (pi, F_st, and XP-EHH) were used to detect potential positive selection signatures related to selection in Luxi cattle. Moreover, gene ontology and Kyoto encyclopedia of genes and genomes pathway enrichment analyses were performed to reveal the potential biological function of candidate genes harbored in selected regions. Results: The results showed that Luxi cattle had high genomic diversity and low inbreeding levels. Using three complementary methods (pi, F_st, and XP-EHH) to detect the signatures of selection in the Luxi cattle genome, there were 2,941, 2,221 and 1,304 potentially selected genes identified, respectively. Furthermore, there were 45 genes annotated in common overlapping genomic regions covered 0.723 Mb, including PLAG1 zinc finger (PLAG1), dedicator of cytokinesis 3 (DOCK3), ephrin A2 (EFNA2), DAZ associated protein 1 (DAZAP1), Ral GTPase activating protein catalytic subunit alpha 1 (RALGAPA1), mediator complex subunit 13 (MED13), and decaprenyl diphosphate synthase subunit 2 (PDSS2), most of which were enriched in pathways related to muscle growth and differentiation and immunity. Conclusion: In this study, we provided a series of genes associated with important economic traits were found in positive selection regions, and a scientific basis for the scientific conservation and genetic improvement of Luxi cattle.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.4
• /
• pp.466-471
• /
• 2006

IAn important problem of pattern recognition is to extract or select feature set, which is included in the pre-processing stage. In order to extract feature set, Principal component analysis has been usually used and SFS(Sequential Forward Selection) and SBS(Sequential Backward Selection) have been used as a feature selection method. This paper applies genetic algorithm which is a popular method for nonlinear optimization problem to the feature selection problem. So, we call it Genetic Algorithm Feature Selection(GAFS) and this algorithm is compared to other methods in the performance aspect.

• Journal of Distribution Science
• /
• v.19 no.12
• /
• pp.45-56
• /
• 2021

Purpose: This study aims to introduce a hybrid MCDM model to support the selection of retail store location. Research design, data, and methodology: The hybrid approach of ANP and TOPSIS was used to address the location selection problem. The ANP technique was employed to compute the weights of the selection criteria, whilst the TOPSIS was used to rank alternatives. The proposed approach was then applied into a fashion company in Vietnam to select the best alternatives to be the retail store. Results: The results showed that Candidate 1 - Hai Ba Trung street is the most appropriate selection for locating retail stores. Conclusions: The proposed approach provides the decision makers with more useful methods than traditional ones. Therefore, the model can be applied to the location selection in all industries. In terms of academic contribution, the selection criteria proposed in the research can devote to the literature in the selection of location along with the concept of distribution channels. Additionally, the research also provides insight and guidelines for firms in making decision on retail store location based on limited resources to avoid the waste of funds. However, the results only answer to the context of Vietnam - a developing country. Thus, future research may be extended to developed countries where have better conditions.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.2
• /
• pp.499-510
• /
• 2016

It is very important to select relevant variables in regression models for survival analysis. In this paper, we introduce a penalized variable-selection procedure in multi-level frailty models based on the "frailtyHL" R package (Ha et al., 2012). Here, the estimation procedure of models is based on the penalized hierarchical likelihood, and three penalty functions (LASSO, SCAD and HL) are considered. The proposed methods are illustrated with multi-country/multi-center bladder cancer survival data from the EORTC in Belgium. We compare the results of three variable-selection methods and discuss their advantages and disadvantages. In particular, the results of data analysis showed that the SCAD and HL methods select well important variables than in the LASSO method.

• Journal of the Korea Institute of Building Construction
• /
• v.11 no.2
• /
• pp.108-115
• /
• 2011

This study investigates the construction management selection methods for fair competition within the construction management market by analyzing the current status of domestic construction management, the 2010 publication on the status of construction management, and the construction management evaluation criteria. Also, the 2009 publication of top CM service establishments, the average proportion of tender for 120 CM services from 2002 to 2010, and six assessment results which are open to the parties directly involved were statistically analyzed to review the adequacy of the evaluation criteria. This analysis shows that the evaluation criteria for the CM service impedes the development of the construction management industry and companies, since the criteria are decided by the service payment, and the technical skills assessed by technical proposals have no ties with contract prices. Therefore, this study proposes an improvement of the selection methods in accordance with the project characteristics and the technical requirements. However, more research is still needed to derive a detailed classification method of the technical requirement, the owner's evaluation criteria selection, and the preparation of an institutional foundation for the construction manager's post-evaluation.

• Journal of KIISE
• /
• v.42 no.12
• /
• pp.1551-1560
• /
• 2015

Software Reliability Growth Models (SRGMs) are used to quantitatively evaluate software reliability and to determine the software release date or additional testing efforts using software failure data. Because a single SRGM is not universally applicable to all kinds of software, the selection of an optimal SRGM suitable to a specific case has been an important issue. The existing methods for SRGM selection assess the goodness-of-fit of the SRGM in terms of the collected failure data but do not consider the accuracy of future failure predictions. In this paper, we propose a method for selecting SRGMs using the trend of failure data and failure prediction ability. To justify our approach, we identify problems associated with the existing SRGM selection methods through experiments and show that our method for selecting SRGMs is superior to the existing methods with respect to the accuracy of future failure prediction.

• The Korean Journal of Applied Statistics
• /
• v.35 no.2
• /
• pp.285-298
• /
• 2022

Continuous shrinkage priors, as well as spike and slab priors, have been widely employed for Bayesian inference about sparse regression coefficient vectors or covariance matrices. Continuous shrinkage priors provide computational advantages over spike and slab priors since their model space is substantially smaller. This is especially true in high-dimensional settings. However, variable selection based on continuous shrinkage priors is not straightforward because they do not give exactly zero values. Although few variable selection approaches based on continuous shrinkage priors have been proposed, no substantial comparative investigations of their performance have been conducted. In this paper, We compare two variable selection methods: a credible interval method and the sequential 2-means algorithm (Li and Pati, 2017). Various simulation scenarios are used to demonstrate the practical performances of the methods. We conclude the paper by presenting some observations and conjectures based on the simulation findings.