計量生物学
Online ISSN : 2185-6494
Print ISSN : 0918-4430
検索
OR
閲覧
検索
最新号
選択された号の論文の3件中1~3を表示しています
    • |<
    • <
    • 1
    • >
    • >|
原著
  • Masaaki Doi, Kazuki Ide, Yohei Kawasaki
    38 巻 (2017 - 2018) 1 号 p. 1-16
    公開日: 2017/11/24
    ジャーナル フリー
    We here consider the problem of comparing the variances of two normal populations. To make a more efficient decision than that made with the conventional F-test, we propose using the Bayesian index of the superiority of the variance of one group to the other θ=Pr12 > σ22 | x1, x2). We express this index according to the hypergeometric series and the cumulative distribution functions of well-known distributions. Furthermore, we investigate the relationship between the Bayesian index and the p-value of the F-test. In addition, we propose another index, the Bayesian index of equivalence of two groups, e(Δ) = Pr(Δ < σ12 < 1/Δ | x1, x2) for 0 < Δ < 1, which is also expressed according to the hypergeometric series and the cumulative distribution functions of well-known distributions. Finally, we evaluate the properties of the Bayesian index of equivalence using simulation, and illustrate the application of the Bayesian indexes with data from actual clinical trials.
    抄録全体を表示
研究速報
  • Keiji Kakumoto, Yoshiyuki Tochizawa
    38 巻 (2017 - 2018) 1 号 p. 17-39
    公開日: 2017/11/24
    ジャーナル フリー

    Stepwise logistic regression is the traditional and most commonly used method for identifying biomarkers and evaluating the magnitude of their effects based on clinical data. Here, we evaluated the performance of the resampling methods leave-one-out cross-validation, 10-fold cross-validation, bootstrap, and .632+ bootstrap in terms of internal validation of prediction analysis using stepwise logistic regression. We conducted simulation studies to compare the ability of these methods to estimate prediction accuracy based on simulation settings (including statistical models) derived from two real biomarker discovery studies (Ogata et al., Leukemia Research 2012; 36: 1229–1236; Yoshimi et al., Molecular Psychiatry 2016; 21: 1504–1510). The simulation results revealed that leave-one-out cross-validation, 10-fold cross-validation, and .632+ bootstrap were comparable in terms of the root mean square error. We therefore recommend the application of these methods to similar biomarker discovery studies that involve approximately ten biomarkers with or without binary biomarkers (such as sex) and various degrees of correlation between the biomarkers.

    抄録全体を表示
総説
    • |<
    • <
    • 1
    • >
    • >|
feedback
Top