• Title/Summary/Keyword: Logit model

Search Result 703, Processing Time 0.029 seconds

A study on sensitivity of representativeness indicator in survey sampling (표본 추출법에서 R-지수의 민감도에 관한 연구)

  • Lee, Yujin;Shin, Key-Il
    • The Korean Journal of Applied Statistics
    • /
    • v.30 no.1
    • /
    • pp.69-82
    • /
    • 2017
  • R-indicator (representativeness indicator) is used to check the representativeness of samples when non-responses occur. The representativeness is related with the accuracy of parameter estimator and the accuracy is related with bias of the estimator. Hence, unbiased estimator generates high accuracy. Therefore, high value of R-indicator guarantees the accuracy of parameter estimation with a small bias. R-indicator is calculated through propensity scores obtained by logit or probit modeling. In this paper we investigate the degree of relation between R-indicator and different non-response rates in strata using simulation studies. We also analyze a modified Korea Economic Census data for real data analysis.

Heterogeneity Tests of the Potential Labor Force among Not-employed in Korea (미취업자 분류의 잠재노동력 차별성 검정)

  • Park, Myungsoo
    • Journal of Labour Economics
    • /
    • v.43 no.4
    • /
    • pp.117-141
    • /
    • 2020
  • The paper focuses on the question of whether and how the labor underutilization indicator supplements the unemployment rate. The research is based on the differences in the labor market behavior among three groups of the not-employed; the unemployed, potential labor force and the rest of outside the labor force. The annual transition rate among the labor market states shows that the potential labor force has the explicit unmet need for employment different from the rest of the outside the labor force. The multinomial logit regression controlling the effects of individual characteristics rejects the hypothesis that the potential labor forces are behaviorally identical to the unemployed. The evidence shows that the two indices should be interpreted distinctively.

  • PDF

A Study on One Factorial Longitudinal Data Analysis with Informative Drop-out

  • Lee, Ki-Hoon
    • Journal of the Korean Data and Information Science Society
    • /
    • v.17 no.4
    • /
    • pp.1053-1065
    • /
    • 2006
  • This paper proposes a method in one-way layouts for longitudinal data with informative drop-out. When dropouts are informative, that is, correlated with unobserved data and/or the previous observed data, the simple imputation methods such as 'last observation carried forward' (LOCF) methods would arise the bias of the testing models. The maximum likelihood procedure combined with a logit model for the drop-out process is proposed to test treatment effects for one factorial designs and compared with LOCF method in two examples.

  • PDF

Estimation for misclassified data with ultra-high levels

  • Kang, Moonsu
    • Journal of the Korean Data and Information Science Society
    • /
    • v.27 no.1
    • /
    • pp.217-223
    • /
    • 2016
  • Outcome misclassification is widespread in classification problems, but methods to account for it are rarely used. In this paper, the problem of inference with misclassified multinomial logit data with a large number of multinomial parameters is addressed. We have had a significant swell of interest in the development of novel methods to infer misclassified data. One simulation study is shown regarding how seriously misclassification issue occurs if the number of categories increase. Then, using the group lasso regression, we will show how the best model should be fitted for that kind of multinomial regression problems comprehensively.

The Utilization of Customer Information in Korean Retail Bank

  • Kwak, Soo-Hwan
    • Journal of Information Management
    • /
    • v.39 no.2
    • /
    • pp.235-249
    • /
    • 2008
  • The combination of information and technology makes dramatically increase both information quality and quantity. Almost of company utilize customer information for the purpose of increasing sales amount and profitability. The purpose of this paper is to discover customer information's utilization practices in the Korean financial industry. The case of K Bank's information analysis in the inbound and outbound marketing is provided, The customer segmentation is used for the inbound marketing by using RFM analysis. And the loan card model is used for the outbound marketing by using logit analysis.

Usefulness of In-store Spotting Survey in Developing a Supermarket Location Analysis Model (내점객 인터뷰에 근거한 슈퍼마켓 입지분석 모델의 실용성 평가)

  • 서성무;고윤배
    • Asia Marketing Journal
    • /
    • v.1 no.1
    • /
    • pp.5.1-5.11
    • /
    • 1998
  • 이 연구는 2차자료가 부족한 우리나라 슈퍼마켓 업체의 여건을 감안하여 간편하게 활용할 수 있는 입지분석 모델의 가능성을 탐구하였다. 연구모델은 두 가지 기준을 근거로 모두 네가지 모델을 설정하고 비교검토했다. 먼저 표본추출방법에 의해 내점객표본과 지역할당표본으로 분류하고, 이것을 다시 포함하는 변수의 범위에 따라 축소모델과 확장모델로 구분하였다. 공간상호작용모델의 추정에는 MNL(Multinomial Logit)방식을 이용했다. 분석결과 내점객표본으로 조사해서 얻은 응답자의 주거지와 주로 찾는 점포, 그리고 사전적으로 입수한 경쟁점포의 매장면적, 인접점포까지의 거리에 대한 자료만을 이용해서 추정한 가장 간단한 모델이 비교적 만족스러운 결과를 나타냈다.

  • PDF

An Analysis for Urban Competitiveness of Global Cities & 7 Metropolitan Korean Cities using Oxford Economics Data (우리나라 7대 광역시와 세계 770개 도시 경쟁력 비교분석 - Oxford Economics 자료에 근거한 도시경쟁력 -)

  • Cho, Jae Ho
    • Journal of the Korean Regional Science Association
    • /
    • v.33 no.4
    • /
    • pp.3-17
    • /
    • 2017
  • This study ranks by developing an urban competitiveness index of major global cities, including seven cities in Korea using data from the Global Cities Forecast (2013) provided by Oxford Economics. The City competitiveness index is selected from 18 indicators including scale index, ratio index, growth rate index while Gini coefficient is used for distribution index. In order to analyze the relationship between the competitiveness index and the distribution index, we use the LOGIT panel regression model. As a result, the increase in income inequality (Gini coefficient) has a negative effect on the economic growth rate in 5-year time lag shown statistically significant. We have compiled global rankings of 770 city competitiveness based upon 19 indicators by combining the global competitiveness index and the distribution index. The trend of rank shows that 7 Metropolitan Korean Cities are expected to decline substantially over the period. In particular, Seoul ranked $59^{th}$ in 2010 and $74^{th}$ in 2015. Its ranking is expected to be decline to $185^{th}$ in 2030. The declining competitiveness of Korean cities is expected to lead to a weakening of Korea's national competitiveness in the long run. Accordingly, it is imperative to identify problems and seek strategic plans to secure global urban competitiveness.

Corporate Default Prediction Model Using Deep Learning Time Series Algorithm, RNN and LSTM (딥러닝 시계열 알고리즘 적용한 기업부도예측모형 유용성 검증)

  • Cha, Sungjae;Kang, Jungseok
    • Journal of Intelligence and Information Systems
    • /
    • v.24 no.4
    • /
    • pp.1-32
    • /
    • 2018
  • In addition to stakeholders including managers, employees, creditors, and investors of bankrupt companies, corporate defaults have a ripple effect on the local and national economy. Before the Asian financial crisis, the Korean government only analyzed SMEs and tried to improve the forecasting power of a default prediction model, rather than developing various corporate default models. As a result, even large corporations called 'chaebol enterprises' become bankrupt. Even after that, the analysis of past corporate defaults has been focused on specific variables, and when the government restructured immediately after the global financial crisis, they only focused on certain main variables such as 'debt ratio'. A multifaceted study of corporate default prediction models is essential to ensure diverse interests, to avoid situations like the 'Lehman Brothers Case' of the global financial crisis, to avoid total collapse in a single moment. The key variables used in corporate defaults vary over time. This is confirmed by Beaver (1967, 1968) and Altman's (1968) analysis that Deakins'(1972) study shows that the major factors affecting corporate failure have changed. In Grice's (2001) study, the importance of predictive variables was also found through Zmijewski's (1984) and Ohlson's (1980) models. However, the studies that have been carried out in the past use static models. Most of them do not consider the changes that occur in the course of time. Therefore, in order to construct consistent prediction models, it is necessary to compensate the time-dependent bias by means of a time series analysis algorithm reflecting dynamic change. Based on the global financial crisis, which has had a significant impact on Korea, this study is conducted using 10 years of annual corporate data from 2000 to 2009. Data are divided into training data, validation data, and test data respectively, and are divided into 7, 2, and 1 years respectively. In order to construct a consistent bankruptcy model in the flow of time change, we first train a time series deep learning algorithm model using the data before the financial crisis (2000~2006). The parameter tuning of the existing model and the deep learning time series algorithm is conducted with validation data including the financial crisis period (2007~2008). As a result, we construct a model that shows similar pattern to the results of the learning data and shows excellent prediction power. After that, each bankruptcy prediction model is restructured by integrating the learning data and validation data again (2000 ~ 2008), applying the optimal parameters as in the previous validation. Finally, each corporate default prediction model is evaluated and compared using test data (2009) based on the trained models over nine years. Then, the usefulness of the corporate default prediction model based on the deep learning time series algorithm is proved. In addition, by adding the Lasso regression analysis to the existing methods (multiple discriminant analysis, logit model) which select the variables, it is proved that the deep learning time series algorithm model based on the three bundles of variables is useful for robust corporate default prediction. The definition of bankruptcy used is the same as that of Lee (2015). Independent variables include financial information such as financial ratios used in previous studies. Multivariate discriminant analysis, logit model, and Lasso regression model are used to select the optimal variable group. The influence of the Multivariate discriminant analysis model proposed by Altman (1968), the Logit model proposed by Ohlson (1980), the non-time series machine learning algorithms, and the deep learning time series algorithms are compared. In the case of corporate data, there are limitations of 'nonlinear variables', 'multi-collinearity' of variables, and 'lack of data'. While the logit model is nonlinear, the Lasso regression model solves the multi-collinearity problem, and the deep learning time series algorithm using the variable data generation method complements the lack of data. Big Data Technology, a leading technology in the future, is moving from simple human analysis, to automated AI analysis, and finally towards future intertwined AI applications. Although the study of the corporate default prediction model using the time series algorithm is still in its early stages, deep learning algorithm is much faster than regression analysis at corporate default prediction modeling. Also, it is more effective on prediction power. Through the Fourth Industrial Revolution, the current government and other overseas governments are working hard to integrate the system in everyday life of their nation and society. Yet the field of deep learning time series research for the financial industry is still insufficient. This is an initial study on deep learning time series algorithm analysis of corporate defaults. Therefore it is hoped that it will be used as a comparative analysis data for non-specialists who start a study combining financial data and deep learning time series algorithm.

Revisit Intention of Visitors to Cultural Festival using Logit Model (로짓모형을 이용한 축제참가자의 재방문 의사 분석)

  • Heo, Chung-Uk
    • Korean Business Review
    • /
    • v.22 no.1
    • /
    • pp.139-156
    • /
    • 2009
  • This article investigates the relationships between motivation and revisit intention of visitors to Gangneung Danoje Festival as cultural festival with social demand. Out of 550 questionnaires distributed, a total of 514 usable questionnaires were collected. The hypothesized causal model was tested by logit model, which included satisfaction model to each program as well as overall satisfaction model to cultural festival. Model 1 is constructed with satisfaction and revisit intention to each program, and Model 2 with overall satisfaction and revisit intention to cultural festival. In this models causal variables were inputted including satisfaction to festival programs, frequency of visitation, days of stay, time required to destination. In Model 1 positive sign were shown by causal variables as satisfaction to each program, frequency of visitation, days of stay but negative signs was shown by time required to festival place. In Model 2 sign directions of causal variables were same in Model 1. In comparison, Model 2 is more significant than Model 1 on the basis of statistical theory as significance level and coefficient of determination. Consequently, cultural festival managers should test the satisfaction level of visitors to each program of cultural festival and make efforts to establish advanced program in order to attract more visitors.

  • PDF

Economic Values of Recreational Water: Rafting on the Hantan River (수자원의 휴양가치분석 : 한탄강 래프팅을 사례로)

  • Kwon, Oh Sang;Lim, YoungAh;Kim, Won Hee
    • Environmental and Resource Economics Review
    • /
    • v.16 no.3
    • /
    • pp.427-449
    • /
    • 2007
  • This study estimates the recreation benefits of rafting on the Hantan River. A choice experiment is conducted and the economic values of controlling water stream and water quality are estimated. Both the conditional logit and the multinomial pro bit models are estimated. This study rejects the IIA assumption of the conditional log it model and supports using a more flexible model such as the multinomial probit model.

  • PDF