| Project/Area Number |
16K19249
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Epidemiology and preventive medicine
|
|---|
| Research Institution | Mie University |
|---|
Principal Investigator |
OGURA Toru 三重大学, 医学部附属病院, 講師 (00580060)
|
|---|
| Project Period (FY) |
2016-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2017: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2016: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
|
|---|
| Keywords | 分割表 / マクネマー検定 / メタアナリシス / 信用区間 / 実質水準 / ベイズ法 / 統計数学 |
|---|
| Outline of Final Research Achievements |
It was known that the McNemar test was limited by its unexpectedly small power, and the McNemar test was improved using what can be expressed as a Bayesian test. As the determination of the critical region within the framework of "T≧α'" (α≠α'), α' was set so that the actual level becomes as high as possible while strictly observing the significance level. Next, we extended the proposed test to combinations of binary matched-pairs data from multiple strata. The test statistic was the product of the posterior probabilities of the multiple strata. In numerical experiments, the proposed test for multiple strata was superior when the test statistics of the individual strata were close. In addition, a novel credible interval of the binomial proportion was proposed by improving the Highest Posterior Density interval using the logit transformation. By the inverse logit transformation of the interval, the novel credible interval for the binomial proportion was obtained.
|
| Academic Significance and Societal Importance of the Research Achievements |
マクネマー検定は有意水準5%で検定しても実質水準が5%よりはるかに小さいことがあった。本研究の提案法を用いると有意水準を厳守しながら実質水準の高い検定を行うことができる。すなわち、検定が有意になりにくいことが改善された。また、複数試験の併合では、従来の各試験の分割表における各セルを足し合わせて併合の分割表によるマクネマー検定では、2試験の結果が極端であっても、併合後は良い結果の試験に引っ張られる可能性があったが、提案法では2試験の結果が安定していないと併合後の結果は良くならず、偶然を排除することができる検定であった。
|
