Specification of random effects distributions in mixed-effects models with applications to small area estimation

2017 Fiscal Year Final Research Report

• Project/Area Number: 16H07406
• Research Category: Grant-in-Aid for Research Activity Start-up
• Allocation Type: Single-year Grants
• Research Field: Economic statistics
• Research Institution: The Institute of Statistical Mathematics
• Principal Investigator: Sugasawa Shonosuke 統計数理研究所, リスク解析戦略研究センター, 特任研究員 (50782380)
• Project Period (FY): 2016-08-26 – 2018-03-31
• Keywords: 小地域推定 / 混合効果モデル / 階層ベイズ / 標本調査

Outline of Final Research Achievements

We developed new statistical models and theories for small area estimation based on mixed-effects models. Especially, we focused on the fact that the distributional assumption of random effects is not necessarily consistent with real data, and aimed to develop effective methods to solve the problem. In this research project, we developed small area models with data transformation, heteroscedastic variances, selection of random effects and link functions.

Free Research Field

経済統計