View : 218 Download: 0

Full metadata record

DC Field Value Language
dc.contributor.advisor이동환-
dc.contributor.author이민지-
dc.creator이민지-
dc.date.accessioned2019-02-18T16:30:46Z-
dc.date.available2019-02-18T16:30:46Z-
dc.date.issued2019-
dc.identifier.otherOAK-000000153682-
dc.identifier.urihttp://dcollection.ewha.ac.kr/common/orgView/000000153682en_US
dc.identifier.urihttp://dspace.ewha.ac.kr/handle/2015.oak/248584-
dc.description.abstractWe consider the regression model where response variables are multivariate and correlated. In particular, the Copula regression models can be used when the marginal distributions of each response variable are different each other. but those response variables are correlated. In this study, we review the copula model and copula-based regression model and method of estimating unknown parameters in those models. We apply the copula model for real data example, the internet and smartphone addiction data collected in Korea. Based on the copula model, we investigate the dependency between internet and smartphone addiction and find the risk factors associated with two addictions. Furthermore, the comparison of model fit with the linear regression model and generalized linear model is given.;회귀분석은 가장 일반적으로 사용되는 통계방법 중 하나이다. 그러나 종속변수의 확률분포가 정규분포를 따르지 않고, 이변량자료에서 연관성을 고려하기에 OLS(Ordinary Least Squares)와 GLM(Generalized Linear Model)은 적합하지 않다. 이러한 문제를 해결하기 위한 방법으로 Copula regression은 확률분포에 대한 제약이 없고 이변량자료의 연관성을 고려한다는 특징을 갖는다. 따라서 본 연구에서는 국내 청소년들의 인터넷 중독과 스마트폰 중독자료를 이용하여 이변량자료의 연관성을 고려한 Gaussian Copula모형에 대해 논의한다. 또한 앞서 언급한 OLS(Ordinary Least Squares)와 GLM(Generalized Linear Model) 와 모형을 비교하고 그 결과를 설명한다.-
dc.description.tableofcontentsI. Introduction 1 II. Methodology 3 A. Linear regression model 3 B. Generalized Linear Model 4 C. Copula Regression 5 III. Data Analysis 8 A. Data Description 8 B. Variable Description 9 C. Data Analysis 15 IV. Conclusion 29 Bibliography 30 Abstract(in Korean) 31-
dc.formatapplication/pdf-
dc.format.extent967999 bytes-
dc.languageeng-
dc.publisher이화여자대학교 대학원-
dc.subject.ddc500-
dc.titleA study on copula regression model for incorporating association between the internet and smartphone addiction-
dc.typeMaster's Thesis-
dc.creator.othernameMinji Lee-
dc.format.pageiv, 31 p.-
dc.identifier.thesisdegreeMaster-
dc.identifier.major대학원 통계학과-
dc.date.awarded2019. 2-
Appears in Collections:
일반대학원 > 통계학과 > Theses_Master
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE