Utilizing historical data based on causal inference
| Project/Area Number |
15K15951
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Statistical science
|
|---|
| Research Institution | Yokohama City University |
|---|
Principal Investigator |
Masataka Taguri 横浜市立大学, データサイエンス学部, 准教授 (20587589)
|
|---|
| Project Period (FY) |
2015-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2017: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2016: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2015: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | ヒストリカルデータ / 因果推論 |
|---|
| Outline of Final Research Achievements |
In randomized clinical trials, treatment effects are usually evaluated based only on current study data. However, in many cases, data of previous trials for the control treatment are available. Here we focus on how to use the historical information effectively with negligible bias which leads to the control of type I error. It is important to reduce the risk of bias using the methods that borrows historical information most when the current data are consistent with historical data and borrows least when the current data are inconsistent. This kind of idea is sometimes called as dynamic borrowing. In this study, we explicitly derive the approximated bias formula in a simple hierarchical model with the prior mean fixed. Using the derived bias formula, we propose two approaches for bias and type I error control. Simulation studies showed our proposed estimators were performed reasonably well compared to other approaches.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究の成果による第一種の過誤を増大させず（バイアスが入らず）、かつ検出力の高い研究デザインを用いれば、効率的な薬剤開発につながる。希少疾患の領域では、対照群のデータを一部ヒストリカルデータで補うことにより、全体として、一定の統計的な評価・比較を可能にし、かつバイアスを抑えた、解析方法として用いうると考えている。ヒストリカルデータを信頼できる方法で有効活用することで、前向きの臨床試験相対的に短期間で試験を実施できるメリットがある。有効な治療をいち早く医療現場に届けることができることは、患者さんにとっても大きな利益につながりうると考えられる。
|
Report
(5 results)
Research Products
(19 results)
