JaLCDOI 10.18926/fest/11562
FullText URL 003_037_046.pdf
Author Kim Hyum-Jeong| Tarumi, Tomoyuki| Tanaka, Yutaka|
Abstract The present paper deals with multivariate analyses applied to the maximum likelihood estimate(s) for (the mean vector and) the covariance matrix based on incomplete data, and derives influence functions for the mean vector, the covariance matrix and some statistics in multivariate analyses. Influential directions in the sense of Cook's local influence are also derived. A numerical example is given to show the usefulness of the proposed method.
Publication Title 岡山大学環境理工学部研究報告
Published Date 1998-01-14
Volume volume3
Issue issue1
Start Page 37
End Page 46
ISSN 1341-9099
language 英語
File Version publisher
NAID 120002313576
JaLCDOI 10.18926/fest/19708
Title Alternative Swap-Rate of Entrance Examination and Its Software -SRAS-
FullText URL 004_007_018.pdf
Author Tarumi, Tomoyuki| Yamamoto, Yoshiro|
Abstract Alternative When we select N₀ student from N applicants using a result of an entrance examination, which consists of two step selection, the primary test and the secondary test. It is important to evaluate the contribution for each test. Swap-rate is one of the measure of the contribution for each stage test, and it its widely used. In this paper, we describe a population swap-rate and a sample swap-rate in the first. Next, we consider the distribution of applicants who change the result of the test from pass to fail. Finary, we introduce our system "SRAS - Swap-Rate Analysis System-", that can analyze the examination data on such point of view.
Publication Title 岡山大学環境理工学部研究報告
Published Date 1999-02-26
Volume volume4
Issue issue1
Start Page 7
End Page 18
ISSN 1341-9099
language 日本語
File Version publisher
NAID 120002309160
JaLCDOI 10.18926/fest/11492
Title Alternative Development of a statistical survey analysis system using Internet
FullText URL 008_009_017.pdf
Author Fujino, Tomokazu| Tarumi, Tomoyuki|
Abstract We constructed the online analysis system of the Okayama Activity Area Survey in place since 1979. This is one way to solve the problem in case of releasing the result of a statistical survey. In this paper, we treat the detail of the structure of the system.
Keywords microdata statistical disclosure control web based system online database
Publication Title 岡山大学環境理工学部研究報告
Published Date 2003-03
Volume volume8
Issue issue1
Start Page 9
End Page 17
ISSN 1341-9099
language 日本語
File Version publisher
NAID 120002314053
JaLCDOI 10.18926/fest/11448
FullText URL 009_009_017.pdf
Author Setiawan Agus| Tarumi, Tomoyuki|
Abstract Small Area Estimation (SAE) is the process of using statistical models to link survey outcome variables to a set of predictor variables known for small domains, in order to predict domain-level estimates. The need for detailed statistics on small area is constantly increasing. Small area estimation is becoming important in survey sampling due to a growing demand for reliable small area statistics from both public and private sectors. Bayesian hierarchical models provide a convenient framework for disease mapping and geographical correlation studies. Computation may be carried out using the freely-available WinBUGS software. Two approaches prediction to estimate total patient in small area i will be presented. For the purpose of this paper, the small area estimation in this context use data of Indnesia's population based on the 2000 census for the population of Jakarta and data of patient diarrhea from District Health Service of Jakarta. We interest to predict total patient of diarrhea as variable of interest and data population as auxiliary data from unsample for each small area.
Keywords Auxiliary data Population density Sample survey Small area estimation WinBUGS
Publication Title 岡山大学環境理工学部研究報告
Published Date 2004-02-27
Volume volume9
Issue issue1
Start Page 9
End Page 17
ISSN 1341-9099
language 英語
File Version publisher
NAID 120002313784
JaLCDOI 10.18926/fest/11447
Title Alternative Development of the Mesh Data Analysis System
FullText URL 009_001_007.pdf
Author Niu, Donghui| Tarumi, Tomoyuki|
Abstract Area mesh statistics is a kind of small area statistics. The area mesh data of Japan can be created in a lot of way and many of them can be downloaded, for example, from the land's value information service which is provided by Ministry of Land, Infrastructure and Transport of Japan. We developed database of these area mesh data. By using mesh navigator software (Makita Naoki, 1997), which needs to run on ProAtlas2000 and Microsoft Access2000, we displayed the mesh data on the map. What visualized on the map is very convenient. For extending the advantages of area mesh data to spatial geographical statistics, we used PostgreSQL to develop a new database of mesh data. We also develop some programs in Delphi for the analysis of area mesh data, such as Histogram, Echelon analysis, and etc.
Keywords Area mesh data PostgreSQL PQCompo ProAtlas2000
Publication Title 岡山大学環境理工学部研究報告
Published Date 2004-02-27
Volume volume9
Issue issue1
Start Page 1
End Page 7
ISSN 1341-9099
language 日本語
File Version publisher
NAID 120002313385
JaLCDOI 10.18926/fest/11486
Title Alternative Variable Selection Method using Apriori Algorithm on Contingency Table
FullText URL 010_041_047.pdf
Author Ohno, Manabu| Tarumi, Tomoyuki|
Abstract We proposed a new applied method for induction of variable selection on contingency table. This method is the application of Apriori algorithm on variable selection of contigency table with iteraction. We assume that variables are dichotomous variable. We confirm that can be select variable, when minimun support is low level by using AIC on variable selection criterion.
Keywords Apriori Algorithm Varable Selection Contigency Table Interaction
Publication Title 岡山大学環境理工学部研究報告
Published Date 2005-02-28
Volume volume10
Issue issue1
Start Page 41
End Page 47
ISSN 1341-9099
language 日本語
File Version publisher
NAID 120002313938
JaLCDOI 10.18926/fest/12818
Title Alternative Spatial analysis of Kawaguchi City crime data
FullText URL 13_017_022.pdf
Author Ohshimo, Yuki| Tarumi, Tomoyuki|
Abstract In this paper, we built some models of the spatial data, and evaluate those, using the crime data of Kawaguchi city, Saitama prefecture in Japan. Compute the Moran’I statistics of five crime data related to thefts in the city, the value of sneakthief take the aggregation. So, we pay attention to the sneak, and make a model to estimate the incidence of the events. As a regression, we select the old-age index among regional indexes. Applying a simple regression(SR), a spatial autoregressive model(SAR), a geographically weighted regression(GWR) , we evaluate these models. In GWR model, it is interesting that there are some sections in which the sign of the coefficient takes the opposite versus SR and SAR models. So, stratifying the data by the sign of it, we investigate to data precisely.
Keywords crime data Kawaguchi city spatial analysis spatial autoregressive model geographically weighted regression
Publication Title 岡山大学環境理工学部研究報告
Published Date 2008-03
Volume volume13
Issue issue1
Start Page 17
End Page 22
ISSN 1341-9099
language 日本語
File Version publisher
NAID 120002304883
JaLCDOI 10.18926/fest/12824
Title Alternative Estimate of the posted land price in Okayama city and its visualizing system
FullText URL 13_043_049.pdf
Author Nakao, Kazuo| Tarumi, Tomoyuki|
Abstract The posted land price is a decrared land price from Land Appraisal Committee, and current market price is selling price of the market. In this paper, we investigate the methods to estimate land price from the posted land price in Okayama city, and create the visualizing system of the price on.
Keywords Land price Google maps GIS Ajax
Publication Title 岡山大学環境理工学部研究報告
Published Date 2008-03
Volume volume13
Issue issue1
Start Page 43
End Page 49
ISSN 1341-9099
language 日本語
File Version publisher
NAID 120002304790