DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Sung-Ho | - |
dc.contributor.advisor | 김성호 | - |
dc.contributor.author | Kim, Eun-Jung | - |
dc.contributor.author | 김은정 | - |
dc.date.accessioned | 2011-12-14T04:53:51Z | - |
dc.date.available | 2011-12-14T04:53:51Z | - |
dc.date.issued | 2001 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=166260&flag=dissertation | - |
dc.identifier.uri | http://hdl.handle.net/10203/42025 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 응용수학전공, 2001.2, [ 26 p. ] | - |
dc.description.abstract | A new EM algorithm was proposed in Kim (2000) that is available for modelling a large recursive model of categorical variables which is too large to handle as a single model. An improvement on that algorithm is proposed in this thesis. The difference between the two algorithms is that while the marginal of a set of observed variables as obtained based on the estimates from an E-step may not be the same as the observed marginal in the former algorithm, the marginal from an E-step and the observed marginal are the same in the latter algorithm. As a consequence, the M-step in the latter algorithm becomes simpler than that in the former. This improvement still undergoes an information loss due to model-splitting. It is proved in the thesis that as we do more splitting on a model, we lose more information from data about the parameters of the model. Thus, it is strongly recommended that a model be split as little as possible for estimating parameters of the model with as much accuracy as possible. | eng |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | information loss | - |
dc.subject | model splitting | - |
dc.subject | recursive model | - |
dc.subject | 정보손실 | - |
dc.subject | 거대 순환 모형 | - |
dc.subject | 범주형 변수 | - |
dc.subject | 모형분할 | - |
dc.title | Fitting large recursive models of categorical variables by model-splitting and information loss | - |
dc.title.alternative | 모형분할에 의한 범주형 변수의 거대 순환 모형의 적합과 정보손실 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 166260/325007 | - |
dc.description.department | 한국과학기술원 : 응용수학전공, | - |
dc.identifier.uid | 000993132 | - |
dc.contributor.localauthor | Kim, Sung-Ho | - |
dc.contributor.localauthor | 김성호 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.