Exploratory structural equation modeling via sparse regularization
Project/Area Number |
15K15949
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Multi-year Fund |
Research Field |
Statistical science
|
Research Institution | Kyushu University (2016-2018) Osaka University (2015) |
Principal Investigator |
Hirose Kei 九州大学, マス・フォア・インダストリ研究所, 准教授 (40609806)
|
Research Collaborator |
Yamamoto Michio
Nagata Haruhisa
|
Project Period (FY) |
2015-04-01 – 2019-03-31
|
Project Status |
Completed (Fiscal Year 2018)
|
Budget Amount *help |
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2018: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2017: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2016: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2015: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
|
Keywords | スパース正則化 / Prenet正則化 / ロバスト推定 / スパース推定 / 因子分析 / 正則化法 / 因子回転 / 因子回帰 / グラフィカルモデル |
Outline of Final Research Achievements |
The main contribution based on this research fund is that we have proposed various methodologies via sparse estimation in factor analysis. Specifically, we have introduced a variety of regularization methods, such as Prenet (product elastic net) regularization. These methods are constructed by our theory that the regularization in factor analysis is a generalization of factor rotation.
|
Academic Significance and Societal Importance of the Research Achievements |
因子回転は50年以上前から使われている古い手法であるが,それを一般化した正則化法を使うことにより,高次元データのスパース推定や完全単純構造によるクラスタリングなど,今までできなかったような解析ができるようになった.また,本研究課題でRパッケージを作成して公開したことにより,誰でも容易に正則化因子分析を使えるようになった.
|
Report
(5 results)
Research Products
(31 results)
-
-
-
[Journal Article] An Interpersonal Sentiment Quantification Method Applied to Work Relationship Prediction2017
Author(s)
Imada, M., Hirose, K., Yoshida, M., Sunyong, K., Toyozumi, N., Lopez, G. and Kano, Y.
-
Journal Title
NTT Technical Review
Volume: 15
Pages: 1-15
Related Report
Peer Reviewed / Open Access
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-