Ouyou toukeigaku

Contributed Papers

Multiple Comparison Procedures for a Simple Ordered Restriction in Multi-Sample Models with Bernoulli Responses

Taka-aki Shiraishi

Article type: Contributed Papers
2014 Volume 43 Issue 1-3 Pages 1-22
Published: 2014
Released on J-STAGE: May 16, 2015

DOIhttps://doi.org/10.5023/jappstat.43.1

JOURNAL OPEN ACCESS

Show abstractHide abstract

Single step multiple comparison procedures for ordered means are proposed by Hayter (1990) and Lee and Spurier (1995) in k normal populations. First we consider multiple comparison procedures for the differences among proportions in k binomial populations under a simple ordered restriction. We may discuss Hayter type single step procedures based on arcsine transformation. Furthermore we may propose a closed testing procedure which is superior to the Hayter type test procedure. Next we consider multiple comparison procedures for successive comparisons between ordered proportions. We may discuss Lee-Spurrier type single step procedures. Furthermore we may propose a closed testing procedure which is superior to the Lee-Spurrier type test procedure. We may find that the two closed testing procedures are superior to the closed testing procedure proposed by Shiraishi (2011a).

View full abstract

Download PDF (772K)
Development of Adaptive Step Function Regression for Survival Data

Toshio Shimokawa, Mitsuhiro Tsuji, Masashi Goto

Article type: Contributed Papers
2014 Volume 43 Issue 1-3 Pages 23-43
Published: 2014
Released on J-STAGE: May 16, 2015

DOIhttps://doi.org/10.5023/jappstat.43.23

JOURNAL OPEN ACCESS

Show abstractHide abstract

The prognostic factors affecting survival time are important components of survival analysis. Covariates may be evaluated by the tree-structured method, but this method has high-dimensional interaction. Tibshirani and LeBranc (1993) proposed an automatic binary logistic Estimator (ABLE) method for exploring such indices in binary outcomes. ABLE is constructed from linear combinations of index functions, and the regression parameters are estimated from maximum likelihood in a logistic regression model framework, namely, the automatic proportional hazard Estimator (APHE) model. In this paper, ABLE is extended to the right-censored survival response. The model incorporates the survival multivariate adaptive regression spline algorithm (LeBranc and Crowley, 1999). The effectiveness of the APHE method was validated on real data from phase III clinical trials for infectious diseases and via small-scale simulations.

View full abstract

Download PDF (1776K)

Notes

Estimation of the Stable Point for the Production Process with Damped Oscillation Data

Takashi Inomata, Toshinari Kamakura, Jun-ya Gotoh

Article type: Notes
2014 Volume 43 Issue 1-3 Pages 45-57
Published: 2014
Released on J-STAGE: May 16, 2015

DOIhttps://doi.org/10.5023/jappstat.43.45

JOURNAL OPEN ACCESS

Show abstractHide abstract

We study the state of production processes in detail to control and improve productivity and product quality. In this article we consider the problems on slow-response characteristics for heat-seal process. The slow-response processes are characterized by damped oscillation.
We modeled the boundaries of oscillating state and stable state and proposed the estimation problems on the first stable point of the stable state. This estimation by the method of least square is recognized as the problem on a nonconvex minimization.
To attain a globally optimal solution, we proposed a method for setting a starting point based on the model characteristics. Vast simulation results illuminated that our method converged to the preferable values without any negative variances using even any algorithms.
We also applied this method to practical data in the heat-seal process.

View full abstract

Download PDF (952K)

Register with J-STAGE for free!