• Journal of the Korean Data and Information Science Society
• /
• 제15권2호
• /
• pp.339-345
• /
• 2004

This paper deals with a mixed logit model for ordered polytomous data. There are two types of factors affecting the response varable in this paper. One is a fixed factor with finite quantitative levels and the other is a random factor coming from an experimental structure such as a randomized complete block design. It is discussed how to set up the model for analyzing ordered polytomous data and illustrated how to estimate the paramers in the given model.

• 마케팅과학연구
• /
• 제15권2호
• /
• pp.141-159
• /
• 2005

본 연구에서는 신규서비스에 대한 수요를 분석하기 위한 설문에서 다점척도로 조사된 신규서비스에 대한 응답자들의 가입의향을 함께 조사된 응답자특성 및 대상 신규서비스와 관련된 속성/태도 등의 요인변수들을 이용하여 효과적으로 설명할 수 있는 순위반응모형(Ordered Response Model)을 통한 확산모형의 잠재시장규모 추정 방안을 제시하였다. 또한, 제시된 순위반응모형에 의한 신규서비스의 잠재시장규모 추정 방안을 곧 도입될 예정인 디지털멀티미디어방송(DMB)서비스에 대해 적용한 결과, DMB서비스의 잠재시장규모는 낙관적인 상황과 비관적인 상황으로 구분할 때 각각 이동전화가입자의 41.10% 및 14.83%로 추정되었다.

• Journal of the Korean Data and Information Science Society
• /
• 제17권1호
• /
• pp.123-130
• /
• 2006

This paper discusses about how to build up a mixed-effects model using cumulative logits when some factors are fixed and others are random. Location effects are considered as random effects by choosing them randomly from a population of locations. Estimation procedure for the unknown parameters in a suggested model is also discussed by an illustrated example.

• 한국데이터정보과학회:학술대회논문집
• /
• 한국데이터정보과학회 2004년도 춘계학술대회
• /
• pp.121-126
• /
• 2004

This paper discusses about how to build up a mixed-effects model using cumulative logits when there are some factors are fixed and others are random. Random factors are assumed to be coming from a two-way nested design for choosing individuals or experimental units to apply treatments. Estimation procedure for the unknown parameters in a suggested model is also discussed by an illustrated example.

• Journal of the Korean Data and Information Science Society
• /
• 제17권1호
• /
• pp.187-193
• /
• 2006

This paper shows how to use continuation-ratio logits for the analysis of structured polytomous data. Here, response categories are considered to have a nested binary structure. Thus, conditionally nested binary random variables can be defined in each step. Two types of factors are considered as independent variables affecting response probabilities. For the purpose of analyzing categorical data with binary nested strutures a continuation-ratio mixed model is suggested. Estimation procedure for the unknown parameters in a suggested model is also discussed in detail by an example.

• 산업경영시스템학회지
• /
• 제20권44호
• /
• pp.207-215
• /
• 1997

This paper deals with a comparison between Taguchi's accumulation analysis method and Nair test on the ordered categorical data from an industrial experiment for quality improvement. a result of Taguchi's accumulation analysis method is shown to have reasonable power for detecting location effects, while Nair test identifies the location and dispersion effects separately, Accordingly, Taguchi's accumulation analysis needs to develop methods for detecting dispersion effects as well as location effects. In addition this paper rewmmends models for analyzing ordered categorical data, for examples, the cumulative legit model, mean response model etc Successively simple, reasonable methods should be introduced more likely to be used by the practitioners.

• 한국초등과학교육학회지:초등과학교육
• /
• 제32권2호
• /
• pp.139-158
• /
• 2013

This study investigated elementary students' (grade 4~6) learning progressions for water cycling drawn from iterative assessments using ordered multiple-choice (OMC) items. An assessment system, which consisted of construct map, item design, outcome space, and measurement model, was employed in this study to examine children's learning progressions. At the first stage of the assessment system, a construct map was designed on which children's conceptual understandings from naive to most sophisticated were represented. At the item design stage, 8 OMC items were drawn from the construct map. Each item option of the OMC items was scored from 0 to 3 according to its level of understanding at the stage of outcome space. As a measurement model, Rasch model, a branch of item response theory, was applied to interpreting the outcomes of the OMC items. This cycle of assessment system was furtherly implemented iteratively in order to elaborate on the first version of water cycling learning progression. In conclusion, children's understanding of water cycling could be described in two aspects: water distribution and water movement. We identified children's conjectural developmental pathways about water cycling existed from superficial and naive accounts to more complex and abstract accounts.

• Journal of the Korean Data and Information Science Society
• /
• 제18권2호
• /
• pp.471-479
• /
• 2007

This paper discusses about how to build up mixed-effects model for analysing ordinal response data by using cumulative logits. Random factors are assumed to be coming from the designed sampling scheme for choosing observational units. Since the observed responses of individuals are ordinal, a proportional odds model with two random effects is suggested. Estimation procedure for the unknown parameters in a suggested model is also discussed by an illustrated example.

• 산업경영시스템학회지
• /
• 제32권3호
• /
• pp.135-141
• /
• 2009

A variety of statistical methods are applied to model and optimize responses, related to product or system's quality, in terms of control and noise factors at design and manufacturing stages. Most of them assume continuous response variables but, assessing the performance of a product or system often involves categorical observations, such as ratings and scores. Although most previous works to deal with the categorical data provide sorhisticated response models and ensure unbiased outcomes, they require heavy computation to estimate the model parameters, as well as enough replications. In this study, we present some practical approaches for optimal parameter design with ordered categorical response when only a few or no replication is available. Two real-life examples are given to illustrate the presented methods.

• 응용통계연구
• /
• 제25권2호
• /
• pp.363-376
• /
• 2012

순서적 다항 반응변수의 경우 종종 과도하게 많은 수의 관측치가 0 범주에서 발생하는 영 과잉 특성을 지닌다. 이러한 영 과잉 자료에서 0범주를 발생시키는 요인이 여러 개 존재할 때 일반적인 순서적 프로빗 모형은 자료를 설명함에 있어서 한계를 지닌다. 본 논문에서는 영 과잉 특성을 반영한 이 단계 영 과잉 순서적 프로빗 모형의 베이지안 분석기법을 제시하고 이를 2008년도 통계청에서 조사한 한국인의 음주소비 자료에 적용시킨다. 첫 번째 단계에서는 음주소비가 하나도 없다고 답한 0 범주에 속하는 비음주자들을 신념 또는 영구적 건강상의 문제 등으로 상황에 관계없이 음주를 하지 않는 절대적 비음주자(genuine non-drinker, non-participant)와 현재 소비가 없지만 상황에 따라 음주자가 될 가능성이 있는 잠재적 음주자(zero consumption potential drinker)로 구분하는 프로빗 모형을 적용시켜 분석한다. 두 번째 단계에서는 잠재적 음주자와 1 이상의 범주에 속하는 실제적 음주자를 합하여 음주자 집단으로 보고 이에 대하여 순서적 프로빗 모형을 적용하여 분석한다. 분석결과, 비음주자 중 약 30%가 절대적 비음주자로 음주자료가 일반적 순서적 자료에 비하여 뚜렷한 영 과잉 특성을 가짐을 알 수 있었다. 각 변수의 한계효과를 분석함으로써 같은 설명변수가 절대적 비음주자와 잠재적 음주자에 미치는 영향이 서로 반대로 나타날 수 있음을 발견하였고, 따라서 한국인의 음주자료에 대하여 제안된 영 과잉 순서적 프로빗 모형이 유용함을 보여주었다.