• STI Policy Review
• /
• 제2권2호
• /
• pp.45-54
• /
• 2011

This paper develops a recursive multinomial probit model and describes its estimation method. The recursive multinomial probit model is an extension of a recursive bivariate probit model. The main difference between the two models is that a single decision among two or more alternatives can be considered in each choice equation in the proposed model. The recursive multinomial probit model is developed based on a standard framework of the multinomial probit model and a Bayesian approach with a Gibbs sampling is adopted for the estimation. The simulation exercise with artificial data sets is showed that the model performed well. Since the recursive multinomial probit model can be applied to analyze the causal relationship between discrete dependent variables with more than two outcomes, the model can play an important role in extending the methodology of the causal relationship analysis in innovation research.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2005년도 춘계 학술발표회 논문집
• /
• pp.239-244
• /
• 2005

In this paper, we examine the problem of estimating the sensitive characteristics and behaviors in a multinomial randomized response (RR) model. We analyze this problem through a Bayesian perspective and develop a Bayesian multinomial RR model in survey study. The Bayesian inference of multinomial RR model is a new approach to RR models.

• Communications for Statistical Applications and Methods
• /
• 제17권6호
• /
• pp.791-801
• /
• 2010

마이크로데이터 제공시 발생될 수 있는 노출(disclosure)과 노출위험을 나타내는데 사용되는 측도인 유일성(uniqueness) 그리고 모집단 유일성의 개수를 추정하기 위한 초모집단 모형으로 Multinomial-Dirichlet 모형, Takemura의 Poisson-Gamma 모형, Modified Multinomial-Dirichlet 모형, Bethlehem의 Poisson-Gamma 모형을 다룬다. 이 4개의 모형에 대해 마이크로데이터 제공에 따른 임계모집단 크기(critical population size)를 결정한다.

• Journal of the Korean Data and Information Science Society
• /
• 제10권2호
• /
• pp.465-472
• /
• 1999

We considered a bootstrap method for constructing confidenc intervals for a one parameter model using multinomial sampling. The convergence rates or the proposed bootstrap method are calculated for model-based maximum likelihood estimators(MLE) using multinomial sampling. Monte Carlo simulation was used to compare the performance of bootstrap methods with normal approximations in terms of the average coverage probability criterion.

• Communications for Statistical Applications and Methods
• /
• 제14권1호
• /
• pp.121-131
• /
• 2007

In this paper, we examine the problem of estimating the sensitive characteristics and behaviors in a multinomial randomized response model using Bayesian approach. We derived a posterior distribution for parameter of interest for multinomial randomized response model. Based on the posterior distribution, we also calculated a credible intervals and mean squared error (MSE). We finally compare the maximum likelihood estimator and the Bayes estimator in terms of MSE.

• 유통과학연구
• /
• 제14권11호
• /
• pp.61-73
• /
• 2016

Purpose - Marketing scholars have developed various types of mathematical models for describing marketing phenomenon, because there is no single model comprehensive enough to incorporate all the relevant marketing phenomena. This study tries to summarize the behavioral foundations and the mathematical derivations of the most widely used marketing models and discusses their strategic implications. This study selected four representative marketing models: multinomial logit(MNL) model, elimination-by-aspects(EBA) model, Hauser and Shugan model and Bass diffusion model. Especially, this study focuses on Hauser and Shugan(1983)'s Defender model and discusses the model's behavioral foundation and its implications. Research design, data, and methodology - Of the four selected model, the multinomial logit model is selected as the basic normative model and the other three models are described as descriptive models in contrast. Starting the discussion from the multinomial logit model, this study explains what important strategic variables are incorporated in each of the four models. The IIA(independence of irrelevant alternatives) axiom and Luce choice model is also discussed in relation to the multinomial logit model. The concept of 'efficient frontier' is discussed in relation to Hauser and Shugan's model. Graphs and tables are used to represent the key implications. No empirical study is included. Results - The analyses of the mathematical marketing models are shown to be very useful in understanding the essence of positioning strategy. The multinomial logit model implies the importance of increasing utility or consumer preference level. The EBA model implies the importance of lowering the inter-brand similarity and dominating the competitors. Hauser and Shugan model implies the importance of considering customer heterogeneity distribution in selecting the target market. Conclusions - It is shown that the concepts of 'efficient frontier' is useful in understanding the effectiveness of positioning strategy. Market positioning can be understood as occupying some place on the efficient frontier. The important strategic implications can be summarized as follows: Always try to increase customer preference by providing what they value, and differentiate from competing alternatives as much as possible. The best positioning strategy is to dominate all the competitors and the worst is to be dominated by the competitors.

• 품질경영학회지
• /
• 제29권1호
• /
• pp.11-23
• /
• 2001

This paper is concerned with suggesting a Bayesian method for variable selection in multinomial logit model. It is based upon an optimal rule suggested by use of Bayes rule which minimizes a risk induced by selecting the multinomial logit model. The rule is to find a subset of variables that maximizes the marginal likelihood of the model. We also propose a Laplace-Metropolis algorithm intended to suggest a simple method forestimating the marginal likelihood of the model. Based upon two examples, artificial data and empirical data examples, the Bayesian method is illustrated and its efficiency is examined.

• Industrial Engineering and Management Systems
• /
• 제11권2호
• /
• pp.148-154
• /
• 2012

Micro Electric Vehicles are considered as a solution for reducing $CO_2$ emissions, however, it is difficult to evaluate its impact in a local community when it has been introduced. In this study, we evaluated how to spread the Micro EV within the community, using the utility derived from a multinomial logit model, and analyze the effect on $CO_2$ emissions. The householder's utility model is based on an investigation about Kiryu citizen's activities of shopping, transportation methods, etc. Using the geographic information system, we get the distances of each householder and the stores, and estimate a multinomial logit model about the combination choices of shopping stores and transportation method.

• 응용통계연구
• /
• 제36권2호
• /
• pp.115-127
• /
• 2023

다항 프로빗 모형은 다중 분류와 선택 모형에서 흔히 사용하는 모형이다. 다항 프로빗 모형을 추정하기 위해 일반적으로 널리 사용하는 베이지안 접근법인 마르코프 연쇄 몬테카를로(MCMC) 방법은 계산 복잡도가 매우 높다는 문제점을 가지고 있다. 반면, 변분 베이즈 방법은 MCMC 방법보다 계산 복잡도는 낮으면서도 분류 성능적인 면에서 큰 차이가 나지 않아 더 효율적인 방법으로 알려져 있다. 본 연구에서는 가우시안 과정에 기반한 다항 프로빗 모형을 설명하고 해당 모형에 적용할 수 있는 변분 베이지안 근사법을 알아보고자 한다. 그리고 UCI에서 제공되는 쥐 단백질 발현 데이터에 가우시안 과정 분류에 대한 변분 베이지안 다항 프로빗 모형을 적용하여 그 성능을 확인하고 나이브 베이즈, K-최근접 이웃법, 서포트 벡터 머신 분류기의 성능과 비교한다.

• 자원ㆍ환경경제연구
• /
• 제16권3호
• /
• pp.427-449
• /
• 2007

본고는 수자원이 가지는 휴양가치를 분석하되 한탄강에서 시행되는 래프팅을 분석사례로 하여 수자원의 양, 즉 수량과 수질이 각각 래프탱이라는 대표적 수상 휴양행위로 인한 편익에 어떤 영향을 주는지를 평가하고자 한다. 본고는 선행연구들과는 달리 실제로 수자원을 휴양목적으로 활용하는 행위를 면밀히 검토하여 이를 반영하는 수자원 특성별 그리고 관리방안별 가치를 추정하며, 분석모형으로는 통상적인 조건부로짓모형은 물론 대안선택에 있어 보다 신축성을 부여하는 다항프로벗모형 (multinomial probit model)도 함께 사용한다. 본고는 대안선택행위에 대한 분석결과를 이용하여 수량 및 수질을 포함하는 래프팅 특성별 가치를 도출한다.