• 응용통계연구
• /
• 제25권4호
• /
• pp.605-612
• /
• 2012

Multivariate data are often generated with multiple outcomes in various fields. Multiple outcomes could be mixed as continuous and discrete. Because of their complexity, the data are often dealt with by separately applying regression analysis to each outcome even though they are associated the each other. This univariate approach results in the low efficiency of estimates for parameters. We study the efficiency gains of the multivariate approaches relative to the univariate approach with the mixed data that include continuous and binary outcomes. All approaches yield consistent estimates for parameters with complete data. By jointly estimating parameters using multivariate methods, it is generally possible to obtain more accurate estimates for parameters than by a univariate approach. The association between continuous and binary outcomes creates a gap in efficiency between multivariate and univariate approaches. We provide a guidance to analyze the mixed data.

• 한국정보시스템학회지:정보시스템연구
• /
• 제32권3호
• /
• pp.19-39
• /
• 2023

Purpose This study aims to identify user experience factors that can enhance both metaverse utilization and satisfaction based on the honeycomb model. For this we presented two research questions: first, what are the experience factors of metaverse users? Second, do metaverse user experience factors impact satisfaction? Design/methodology/approach To address these questions, a mixed-methodology approach is employed, including text mining techniques to analyze online reviews and quantitative econometric analysis to reveal the relationship between user experience factors and satisfaction. A total of 69,880 reviews and ratings data were collected. Findings The analysis revealed eight metaverse user experience factors: entertainment, operability, virtual reality, immersion, economic activity, visual performance, avatar, and sociality, all of which were found to have a positive impact on user satisfaction.

• 응용통계연구
• /
• 제28권2호
• /
• pp.175-188
• /
• 2015

본 논문에서는 집단 약동/약력학 모형 추정을 위한 다양한 추정방법들을 이론적으로 비교, 분석하였다. 특히 확률적 표본을 이용한 방법들인 IMP, IMPMAP, SAEM 방법과 베이지안 방법의 이론적 배경과 이들의 성능을 자세히 살펴보고, 기존의 선형근사를 이용한 FO, FOCE 등의 방법과 비교 분석하였다. 확률적 표본을 이용한 추정방법들이 추정에 많은 시간이 소요된다는 문제점을 개선하기 위하여 좀 더 좋은 초기치를 찾는 방안으로 상대적으로 짧은 시간에 정확한 추정치를 계산해주는 ITS 방법을 이용하였다.

• Journal of Mechanical Science and Technology
• /
• 제19권11호
• /
• pp.2016-2024
• /
• 2005

In this work, a mixed beam approach that combines both the stiffness and the flexibility methods has been performed to analyze the coupled composite blades with closed, two-cell cross-sections. The Reissner's semi-complementary energy functional is used to derive the beam force-displacement relations. Only the membrane part of the shell wall is taken into account to make the analysis simple and also to deliver a clear picture of the mixed method. All the cross section stiffness coefficients as well as the distribution of shear across the section are evaluated in a closed-form through the beam formulation. The theory is validated against experimental test data, detailed finite element analysis results, and other analytical results for coupled composite blades with a two-cell airfoil section. Despite the simple kinematic model adopted in the theory, an accuracy comparable to that of two-dimensional finite element analysis has been obtained for cases considered in this study.

• 한국수학교육학회지시리즈C:초등수학교육
• /
• 제20권2호
• /
• pp.177-192
• /
• 2017

본 연구는 수학교육연구에서 적용되고 있는 혼합연구법이 질적연구와 양적연구를 어떻게 결합하여 활용하고 있는가를 탐색해 보고자 한다. 구체적으로 수학교육분야에서 질적연구와 양적연구의 혼합이 방법론적으로 어떠한 시사점과 과제를 줄 수 있는가를 탐구하고자 한다. 이와 같은 연구 목적을 달성하기 위하여, 본 연구에서는 한국초등수학교육학회에서 발간하는 '초등수학교육학회지'에 2015년 게재된 전체 32편의 논문 중, 혼합연구법을 적용한 4편의 논문을 분석 대상으로 선정하였다. 기존의 선행연구들에서는 혼합연구에 대한 분석 결과를, 일반적인 양적연구의 결과와 유사하게 비교 항목별로 수치화시키며 양적인 정보를 중심으로 간략하게 설명하는 경향이 있어 왔다. 이와는 대조적으로, 본 연구에서는 질적 연구자의 관점에서 질적연구와 양적연구의 장점을 최적화할 수 있는 방안을 상세하게 논의하는 형식으로 분석 결과와 시사점을 제시하고 있다.

• 산업공학
• /
• 제15권2호
• /
• pp.189-198
• /
• 2002

Simulated Annealing(SA) approach has been successfully applied to the combinatorial optimization problems with NP-hard complexity. To apply an SA algorithm to specific problems, generic parameters as well as problem-specific parameters must be determined. To overcome the embedded nature of SA, long computational time, some studies suggested the parameter design methods of determining SA related parameters. In this study, we propose a new parameter design approach based on robust design method. To show the effectiveness of the proposed method, the extensive computation experiments are conducted on the mixed-model sequencing problems.

• Communications for Statistical Applications and Methods
• /
• 제15권6호
• /
• pp.969-976
• /
• 2008

Mixed linear models have been widely used in various correlated data including multivariate survival data. In this paper we extend hierarchical-likelihood(h-likelihood) approach for mixed linear models with right censored data to that for left censored data. We also allow a general random-effect structure and propose the estimation procedure. The proposed method is illustrated using a numerical data set and is also compared with marginal likelihood method.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2002년도 추계 학술발표회 논문집
• /
• pp.141-146
• /
• 2002

In this article we consider the problem of constructing confidence intervals for a linear regression model with nested error structure. A popular approach is the likelihood-based method employed by PROC MIXED of SAS. In this paper, we examine the ability of MIXED to produce confidence intervals that maintain the stated confidence coefficient. Our results suggest the intervals for the regression coefficients work well, but the intervals for the variance component associated with the primary level cannot be recommended. Accordingly, we propose alternative methods for constructing confidence intervals on the primary level variance component. Computer simulation is used to compare the proposed methods. A numerical example and SAS code are provided to demonstrate the methods.

• 한국IT서비스학회지
• /
• 제21권4호
• /
• pp.105-122
• /
• 2022

NFTs, which guarantee ownership of digital files using blockchain technology, are the new field for the content industry. The NFT provided new opportunities for content creators to trade digital contents without going through mediation freely. Additionally, collectors and investors can safely and easily own their works without the threat of illegal copies. However, since only a limited number of content creators are participating in the NFT market, there needs to be an influx of various content creators and a process of popularization for this market to grow and develop into the main stage. Furthermore, research on NFT has been limited, and understanding the drivers of creators choosing to participate in NFT is insufficient. Thus, this study aims to identify the factors affecting content creators participating in NFT by applying a mixed-methods approach and presenting practical implications. Using topic modeling and in-depth interviews, this study derives the positive and negative factors and suggests strategies to activate content creators' participation in the NFT market. Through this, we can guide that management implication to reduce the risks and costs of participating in NFTs is needed to encourage the participation of creators. It will also provide insight into ways to develop the NFT content market.

• Communications for Statistical Applications and Methods
• /
• 제27권3호
• /
• pp.349-363
• /
• 2020

Penalized spline is a suitable nonparametric approach in estimating mean model in small area. However, application of the approach in informative sampling in a published article is uncommon. We propose a semiparametric mixed-model using penalized spline under informative sampling to estimate mean of small area. The response variable is explained in terms of mean model, informative sample effect, area random effect and unit error. We approach the mean model by penalized spline and utilize a penalized spline function of the inclusion probability to account for the informative sample effect. We determine the best and unbiased estimators for coefficient model and derive the restricted maximum likelihood estimators for the variance components. A simulation study shows a decrease in the average absolute bias produced by the proposed model. A decrease in the root mean square error also occurred except in some quadratic cases. The use of linear and quadratic penalized spline to approach the function of the inclusion probability provides no significant difference distribution of root mean square error, except for few smaller samples.