Sensitivity analysis for publication bias in multivariate meta-analysis
| Project/Area Number |
18H03208
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 60030:Statistical science-related
|
|---|
| Research Institution | Osaka University |
|---|
Principal Investigator |
Hattori Satoshi 大阪大学, 大学院医学系研究科, 教授 (50425154)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
小向 翔 大阪大学, 大学院医学系研究科, 助教 (70794543)
逸見 昌之 統計数理研究所, 数理・推論研究系, 准教授 (80465921)
|
|---|
| Project Period (FY) |
2018-04-01 – 2022-03-31
|
| Project Status |
Completed (Fiscal Year 2022)
|
| Budget Amount *help |
¥17,030,000 (Direct Cost: ¥13,100,000、Indirect Cost: ¥3,930,000)
Fiscal Year 2021: ¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2020: ¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2019: ¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2018: ¥5,590,000 (Direct Cost: ¥4,300,000、Indirect Cost: ¥1,290,000)
|
|---|
| Keywords | メタアナリシス / 公表バイアス / 選択モデル / 感度解析 / 臨床試験登録 / 予後因子研究 / 診断法研究 / ネットワークメタアナリシス / 要約ROC曲線 |
|---|
| Outline of Final Research Achievements |
Meta-analysis is a statistical method to synthesize published research findings and plays very important roles in creating clinical guidelines. Meta-analysis is usually conducted with published results in scientific journals. Then, good results are likely included in the analysis and it leads bias, called the publication bias. In the standard meta-analysis for randomized clinical trials, lots of methods for publication bias have been established. On the other hand, very limited development has been made for multivariate meta-analysis such as the network meta-analysis and meta-analysis of diagnosis or prognosis studies. In this research, several parametric sensitivity analysis methods for publication bias in the multivariate meta-analysis were developed.
|
| Academic Significance and Societal Importance of the Research Achievements |
多変量メタアナリシス、特に、ネットワークメタアナリシスの適用例は近年劇的に増加しており、伝統的な方法では見出すことのできなかった知見が多く生み出されています。しかしながら、公表バイアスに対処する方法はほとんど開発されてきておらず、果たして、メタアナリシスによる結果が十分に説得力があり安定したものであるかについての危惧が常に残る状態でした。本研究では多変量メタアナリシスに適用可能な公表バイアスの影響を定量化する方法を与えています。多変量メタアナリシスの結果の妥当性を考察することができ、臨床医学研究への大きなインパクトが期待されます。
|
Report
(5 results)
Research Products
(18 results)
