Biomedical subjects

Shinto Eguchi

Publications and source records attributed to Shinto Eguchi.

4 recordsLinked to original sources

PubMed2005

Modeling late entry bias in survival analysis.

In a failure time analysis, we sometimes observe additional study subjects who enter during the study period. These late entries are treated as left-truncated data in the statistical literature. However, with real data, there is a substantial possibility that the delayed entries may have extremely different hazards compared to the other standard subjects. We focus on a situation in which such entry bias might arise in the analysis of survival data. The purpose of the present article is to develop an appropriate methodology for making inference about data including late entries. We construct a model that includes parameters for the effect of delayed entry bias having no specification for the distribution of entry time. We also discuss likelihood inference based on this model and derive the asymptotic behavior of estimates. A simulation study is conducted for a finite sample size in order to compare the analysis results using our method with those using the standard method, where independence between entry time and failure time is assumed. We apply this method to mortality analysis among atomic bomb survivors defined in a geographical study region.

Algorithms↗

PubMed2004

Robustifying AdaBoost by adding the naive error rate.

AdaBoost can be derived by sequential minimization of the exponential loss function. It implements the learning process by exponentially reweighting examples according to classification results. However, weights are often too sharply tuned, so that AdaBoost suffers from the nonrobustness and overlearning. Wepropose a new boosting method that is a slight modification of AdaBoost. The loss function is defined by a mixture of the exponential loss and naive error loss functions. As a result, the proposed method incorporates the effect of forgetfulness into AdaBoost. The statistical significance of our method is discussed, and simulations are presented for confirmation.

Algorithms↗

PubMed2004

Information geometry of U-Boost and Bregman divergence.

We aim at an extension of AdaBoost to U-Boost, in the paradigm to build a stronger classification machine from a set of weak learning machines. A geometric understanding of the Bregman divergence defined by a generic convex function U leads to the U-Boost method in the framework of information geometry extended to the space of the finite measures over a label set. We propose two versions of U-Boost learning algorithms by taking account of whether the domain is restricted to the space of probability functions. In the sequential step, we observe that the two adjacent and the initial classifiers are associated with a right triangle in the scale via the Bregman divergence, called the Pythagorean relation. This leads to a mild convergence property of the U-Boost algorithm as seen in the expectation-maximization algorithm. Statistical discussions for consistency and robustness elucidate the properties of the U-Boost methods based on a stochastic assumption for training data.

Algorithms↗

PubMed2002

Robust blind source separation by beta divergence.

Blind source separation is aimed at recovering original independent signals when their linear mixtures are observed. Various methods for estimating a recovering matrix have been proposed and applied to data in many fields, such as biological signal processing, communication engineering, and financial market data analysis. One problem these methods have is that they are often too sensitive to outliers, and the existence of a few outliers might change the estimate drastically. In this article, we propose a robust method of blind source separation based on the beta divergence. Shift parameters are explicitly included in our model instead of the conventional way which assumes that original signals have zero mean. The estimator gives smaller weights to possible outliers so that their influence on the estimate is weakened. Simulation results show that the proposed estimator significantly improves the performance over the existing methods when outliers exist; it keeps equal performance otherwise.

Journal Article↗