• Journal of Korean Society of Transportation
• /
• v.26 no.1
• /
• pp.113-126
• /
• 2008

This research aims to explore the effects of multicollinearity on the reliability and goodness of fit of logit model. To investigate the effects of multicollinearity on the multinominal logit model, numerical experiments are performed. The exploratory variables(attributes of utility functions) which have a certain degree of correlations from (rho=) 0.0 to (rho=) 0.9 are generated and rho-squares and t-statistics which are the indices of goodness of fit and reliability of logit model are traced. From the well designed numerical experiments, following findings are validated : 1) When a new exploratory variable is added, some of rho-squares increase while the others decrease. 2) The higher relations between generic variables lead a logit model worse with respect to goodness of fit. 3) Multicollinearity has a tendency to produce over-evaluated parameters. 4) The reliability of the estimated parameter has a tendency to decrease when the correlations between attributes are high. These results suggest that we have to examine the existence of multicollinearity and perform the proper treatments to diminish multicollinearity when we develop logit model.

• Journal of Korean Society of Rural Planning
• /
• v.5 no.2 s.10
• /
• pp.66-72
• /
• 1999

본 연구는 다음의 두 가지 목적이 있다. 첫째, 각종 실증분석에 있어서의 다중모형의 효율성에 대한 소개와, 둘째, 다중모형의 분석에 있어서 상위단계의 예측되는 가치를 측정하기 위한 새로운 통계를 소개하는 데 있다. 다중모형의 이론적 틀은 광범위하게 사용되는 기존의 1단계 모형의 통계적 문제점(이분산 등)을 보완하고, 현실을 더욱 실체적으로 파악한다는 측면에서 앞으로 지역분석의 중추적 틀로서 자리매김하리라 예상되고 있다. 본 연구는 이러한 다중모형의 효율성을 가상 자료가 아닌 실제 자료를 이용하여 검증하였으며, 특히 기존에 제시되지 않은 다중로짓모형에서의 상위수준의 잔차 또는 예측치를 계산하는 통계량을 제시하였다. 이 새로운 통계량은 실증분석에 있어서의 관찰치와의 상관관계와 그 분산의 분석에 있어서 잘 행위하고 있는 것으로 나타났다.

• The Korean Journal of Applied Statistics
• /
• v.21 no.4
• /
• pp.589-602
• /
• 2008

This article studies on disability pensioners' characteristic with multinomial logit and logistic regression model. Seven factors are examined on whether each factor is reflected in degree of disability in the disability pension. By incorporating multinomial logit and logistic regression model, effectiveness and characteristic of the seven factors are investigated on the degree of disability. Result shows all the seven factors are significant on the degree of disability, while among the seven, five factors, age, sex, type of coverage, type of category, insured duration show a trend in degree of disability and the other two, cause of disability and class of standard monthly income are not effective on trend in degree of disability. Results from analyses might be useful for disability pension management.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.5
• /
• pp.1-14
• /
• 2020

The aim of this study is to analyze effects of factors on the number of vehicles involved in traffic accidents on freeway sections. In previous studies about traffic accident severity, the analysis of accidents involving multiple vehicles was insufficient. However, multiple-vehicle accidents are likely to cause casualties and are the main reasons increasing accident duration and social costs. In this study, the number of vehicles involved in an accident was interpreted as the result of the accident, not as the cause of the accident, and the impacts of each accident factor were analyzed using a multinomial logit model. The results indicate that multiple-vehicle accidents are mainly related to following factors: nighttime, driver's faults, obstacles on the road, a downhill slope, heavy vehicles, and freeway mainline sections including tunnels and bridges.

• Proceedings of the KOR-KST Conference
• /
• 2007.05a
• /
• pp.108-117
• /
• 2007

• Journal of Korean Society of Transportation
• /
• v.18 no.2
• /
• pp.63-71
• /
• 2000

One Problem of the choice Property in logit model is interpreted as the Problem of common links and common nodes in choice set. Common node Problem Plays important role in deciding the efficiency of network loading and common link problem is connected with choice Problem, both of which are to be solved to improve the logit choice model. Although much need has been pointed out for research on the topic, however, no Paper as yet considers these two factors at the same time. In the Paper we develop a new logit formulation, which is able to ease the logit Problem, widely known as the Problem of IIA(Independence of Irrelevant Alternatives). An example network is used to assess the Proposed model and compare it with other conventional models. From the results, we find out that the model is superior to others.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2003.05a
• /
• pp.835-842
• /
• 2003

현행 기업신용평가모형에 관한 연구는 크게 부실예측모형 및 채권등급 평가모형으로 구분된다. 이러한 신응평가모형에 관한 연구는 단순히 부실여부 또는 이미 전문가 집단에 의해 사전에 정의된 등급체계만을 예측하는 데 초점을 맞추고 있었다. 그러나. 대부분의 금융기관에서 사용하는 신응평가모형은 기업의 부실여부만을 예측하거나 기존의 채권등급을 예측하기 위만 목적보다는 기업의 고유 신응위험을 평가하여 이에 적합한 신용등급을 부여함으로써, 효율적인 대출업무를 수행하기 위해 활용되고 있다. 본 연구에서는 기존의 부실예측모형들을 대상으로 다중 부실확률모형 (Business Failure Probability Map; BFPM) 접근방법을 이용한 신응등급화 방법을 제안하고자 한다. 본 연구에서 제시된 다중 부실확률모형은 신경망모형과 로짓모형을 통합하여 부도율, 점유율을 고려한 다단계 신용등급을 예측할 수 있게 해준다. 다중 부도확률지도 접근방법을 이용하여 각 금융기관에서 정의하는 수준의 신용리스크를 효과적으로 추정하고, 이를 기준으로 보다 객관적인 다단계 신용등급을 산출하는 새로운 신응등급화 방법을 제시 하고자 한다.

• Journal of Distribution Research
• /
• v.14 no.1
• /
• pp.45-65
• /
• 2009

As a number of people using the internet for their shopping steadily rises, it is increasingly important for retailers to understand why consumers decide to buy products via online or offline. The main purpose of this study is to develop and test a model that enhance our understanding of how consumers respond future online and offline channels for their purchasing. Rather than merely adopting statistical models like most other studies in this field, the present study develops a model that combines double-cohort method with multinomial logit model. It is desirable if one can adopt an overall encompassing criterion in the study of consumer behaviors form diverse sales channels. This study uses the concept of cohort or aging to enable this comparison. It enables us to analyze how consumers respond to online and offline channels as people aged by measuring their shopping behavior for an online and offline retailers and their subsequent purchase intentions. Based on some empirical findings, this study concludes with policy implications and some necessary fields of future studies desirable.

• Journal of Korean Society of Transportation
• /
• v.15 no.3
• /
• pp.39-49
• /
• 1997

본 연구는 서울대도시권을 대상으로 토지이용패턴과 통행수단선택간의 관계를 경헙적으로 분석하여 수도권 토지이용 및 교통정책에 시사점을 제시하는 것을 목적으로 하고 있다. 다중 로짓모형을 이용한 분석에서 직장 및 주거빌도가 높을수록 전철과 버스 등 대중교퉁수단에 대한 의존도를 보이는 것으로 나타났다. 또한 직장중심지의 경우 버스보다는 자가용이용율이 높은 것으로 나타나 고밀도 정책이 반드시 대중교통수단으로의 이동을 의미하는 것은 아니라는 사실을 경험적으로 입증하고 있다.

• Journal of the Economic Geographical Society of Korea
• /
• v.20 no.2
• /
• pp.173-188
• /
• 2017

This paper aims to analyze the effects of the residential area and personal characteristics of households on the preference of residential location factors. The main results of this study are as follows. Firstly, considering the results of multiple regression analysis, it can be seen that preference of location factors is differentiated according to the residential area and personal characteristics of households by individual location factors. Secondly, considering the results of binomial logistic regression analysis, it can be also elucidated that the preferred location factors are differentiated according to the residential area and personal characteristics of the households. Therefore, it is judged that the residential area and personal characteristics of household and the location factors of the household are mutually influencing each other.