Browsing by Author "Chen, Lin-An"

Now showing 1 - 13 of 13

A non-parametric coverage interval
(2008-02-01)
Lin, Shuo-Huei
;
Chan, Wenyaw
;
Chen, Lin-An
;
統計學研究所
;
Institute of Statistics
Classically the non-parametric coverage interval is estimated by empirical quantiles. We introduce an alternative way for estimating the coverage interval by symmetric quantiles given by Chen and Chiang (1996 J. Nonparametric Stat. 7 171-85). We further show that this alternative has a better precision in the sense that its asymptotic variances are smaller than the classical one.
Extending the discussion on coverage intervals and statistical coverage intervals
(2006-12-01)
Chen, Lin-An
;
Hung, Hui-Nien
;
統計學研究所
;
Institute of Statistics
Willink ( 2004 Metrologia 41 L5 - 6) is concerned that, in the society of metrology, there is potential for confusion between coverage interval and statistical coverage interval and he makes a precise interpretaion of these two terms. We further clarify that the confidence of a coverage interval is actually a statistical coverage interval.
Linear trimmed means for the linear regression with AR(1) errors model
(2010-11-01)
Lai, Yi-Hsuan
;
Chen, Lin-An
;
Tang, Chau-Shyun
;
統計學研究所
;
管理科學系
For the linear regression with AR(1) errors model, the robust generalized and feasible generalized estimators of Lai et al. (2003) of regression parameters are shown to have the desired property of a robust Gauss Markov theorem. This is done by showing that these two estimators are the best among classes of linear trimmed means. Monte Carlo and data analysis for this technique have been performed. (C) 2010 Elsevier B.V. All rights reserved.
Maximum average-power (MAP) tests
(2007)
Chen, Lin-An
;
Hung, Hui-Nien
;
Chen, Chih-Rung
;
統計學研究所
;
Institute of Statistics
The objective of this article is to propose and study frequentist tests that have maximum average power, averaging with respect to some specified weight function. First, some relationships between these tests, called maximum average-power (MAP) tests, and most powerful or uniformly most powerful tests are presented. Second, the existence of a maximum average-power test for any hypothesis testing problem is shown. Third, an MAP test for any hypothesis testing problem with a simple null hypothesis is constructed, including some interesting classical examples. Fourth, an MAP test for a hypothesis testing problem with a composite null hypothesis is discussed. From any one-parameter exponential family, a commonly used UMPU test is shown to be also an MAP test with respect to a rich class of weight functions. Finally, some remarks are given to conclude the article.
Mode type quasi-range and its applications
(2008)
Chen, Lin-An
;
PeterYang, Hsien-Chueh
;
Tang, Chau-Shyun
;
統計學研究所
;
管理科學系
Building from the consideration of closeness, we propose the mode quasi-range as an alternative scale parameter. Application of this scale parameter to formulate the population standard deviation is investigated leading to an efficient sample estimator of standard deviation from the point of asymptotic variance. Monte Carlo studies, in terms of finite sample efficiency and robustness of breakdown point, have been performed for the sample mode quasi-range. This study reveals that this closeness consideration-based mode, quasi-range, is satisfactory because these statistical procedures based on it are efficient and are less misleading for drawing conclusion from the sample results.
Parametric coverage interval
(2007-04-01)
Chen, Lin-An
;
Huang, Jing-Ye
;
Chen, Hung-Chia
;
統計學研究所
;
Institute of Statistics
Parametric estimation of coverage interval is useful since the parametric intervals are generally narrower than the non-parametric ones; however, it has been considered only for the measurement variable with normal distribution. Here we propose a general technique for constructing parametric coverage intervals that may deal with all distributions, both symmetric and asymmetric, in measurement science.
Statistical inferences based on outliers for gene expression analysis
(2017-08-01)
Lai, Yi-Hsuan
;
Chen, Hung-Chia
;
Chen, Lin-An
;
Chen, Dung-Tsa
;
Hung, Hui-Nien
Discovering differential genes through the detection of outliers in samples from disease group subjects is a new and important approach for gene expression analysis. Extending the outlier mean of Chen et al. (2010a), we develop the asymptotic distributions of the outlier least squares estimator (LSE) and the outlier proportion for the linear regression model. An optimal property of the best linear outlier mean acting as an outlier estimator version of the Gauss Markov theorem for the outlier LSE is presented. Power comparisons demonstrate that tests based on outlier estimators are competitive in detecting a shift of the parent tail distribution. An analysis of DNA microarray data from samples of pancreatic breast tumors supports the use of outlier-based methods. (C) 2017 Elsevier B.V. All rights reserved.
Symmetric quantiles and their applications
(2006-09-01)
Chiang, Yuang-Chin
;
Chen, Lin-An
;
Yang, Hsien-Chueh Peter
;
統計學研究所
;
Institute of Statistics
To develop estimators with stronger efficiencies than the trimmed means which use the empirical quantile, Kim (1992) and Chen & Chiang (1996), implicitly or explicitly used the symmetric quantile, and thus introduced new trimmed means for location and linear regression models, respectively. This study further investigates the properties of the symmetric quantile and extends its application in several aspects. ( a) The symmetric quantile is more efficient than the empirical quantiles in asymptotic variances when quantile percentage a is either small or large. This reveals that for any proposal involving the alpha th quantile of small or large alpha s, the symmetric quantile is the right choice; (b) a trimmed mean based on it has asymptotic variance achieving a Cramer-Rao lower bound in one heavy tail distribution; ( c) an improvement of the quantiles-based control chart by Grimshaw & Alt ( 1997) is discussed; (d) Monte Carlo simulations of two new scale estimators based on symmetric quantiles also support this new quantile.
The density control chart: a general approach for constructing a single chart for simultaneously monitoring multiple parameters
(2012)
Chen, Hung-Chia
;
Yeh, Arthur B.
;
Yen, Chia-Ling
;
Chen, Lin-An
;
統計學研究所
"The majority of the existing literature on simultaneous control charts, i.e. control charting mechanisms that monitor multiple population parameters such as mean and variance on a single chart, assume that the process is normally distributed. In order to adjust and maintain the overall type-I error probability, these existing charts rely largely on the property that the sample mean and sample variance are independent under the normality assumption. Furthermore, the existing charting procedures cannot be readily extended to non-normal processes. In this article, we propose and study a general charting mechanism which can be used to construct simultaneous control charts for normal and non-normal processes. The proposed control chart, which we call the density control chart, is essentially based on the premise that if a sample of observations is from an in-control process, then another sample of observations is no less likely to be also from the in-control process if the likelihood of the latter is no less than the likelihood of the former. The density control chart is developed for normal and non-normal processes where the distribution of the plotting statistic of the density control chart can be explicitly derived. Real examples are given and discussed in these cases. We also discuss how the density control chart can be constructed in cases when the distribution of the plotting statistic cannot be determined. A discussion of potential future research is also given."
The distribution-based p-value for the outlier sum in differential gene expression analysis
(2010-03-01)
Chen, Lin-An
;
Chen, Dung-Tsa
;
Chan, Wenyaw
;
統計學研究所
;
Institute of Statistics
Outlier sums were proposed by Tibshirani & Hastie (2007) and Wu (2007) for detecting outlier genes where only a small subset of disease samples shows unusually high gene expression, but they did not develop their distributional properties and formal statistical inference. In this study, a new outlier sum for detection of outlier genes is proposed, its asymptotic distribution theory is developed, and the p-value based on this outlier sum is formulated. Its analytic form is derived on the basis of the large-sample theory. We compare the proposed method with existing outlier sum methods by power comparisons. Our method is applied to DNA microarray data from samples of primary breast tumors examined by Huang et al. (2003). The results show that the proposed method is more efficient in detecting outlier genes.
The distribution-based p-value for the outlier sum in differential gene expression analysis
(2010-03-01)
Chen, Lin-An
;
Chen, Dung-Tsa
;
Chan, Wenyaw
;
統計學研究所
;
Institute of Statistics
Outlier sums were proposed by Tibshirani & Hastie (2007) and Wu (2007) for detecting outlier genes where only a small subset of disease samples shows unusually high gene expression, but they did not develop their distributional properties and formal statistical inference. In this study, a new outlier sum for detection of outlier genes is proposed, its asymptotic distribution theory is developed, and the p-value based on this outlier sum is formulated. Its analytic form is derived on the basis of the large-sample theory. We compare the proposed method with existing outlier sum methods by power comparisons. Our method is applied to DNA microarray data from samples of primary breast tumors examined by Huang et al. (2003). The results show that the proposed method is more efficient in detecting outlier genes.
Uncertainty analysis for measurement of measurand
(2010-11-01)
Chen, Hung-Chia
;
Wu, Pei-Chen
;
Huang, Jing-Ye
;
Chen, Lin-An
;
統計學研究所
For measuring the true value of a measurand, vague statistical concept of measurand results in inefficient uncertainty analysis of measurement. The vagueness is caused by the fact that true value of the measurand is an unknown parameter such as population mean or median and the measurement of this true value is a random variable. Generally a parameter may be estimated remarkably more efficiently than the prediction of the random variable. The classical uncertainty analysis in the literature has been developed based on the structure that a measurand is a random variable. This misspecification of statistical concept costs serious price of sacrificing efficiency in terms of length of the uncertainty interval. The purpose of present study is to formally formulate a statistical model for the true value of measurand and provide an uncertainty analysis for the measurement of this true value. (C) 2010 Elsevier Ltd. All rights reserved.
Validation of tolerance interval
(2012-04-01)
Lai, Yi-Hsuan
;
Yen, Ya-Fen
;
Chen, Lin-An
;
統計學研究所
;
Institute of Statistics
The tolerance interval receives very much attention in literature and is widely applied in industry. However, it is generally constructed through the criterion of minimum width by Eisenhart et al. (1947). Although effort for clarification of several prediction related intervals has been made recently by Huang et al. (2010). the appropriateness of the tolerance interval for its role in industry applications is insufficiently discussed. According to manufacturers' requests, a concept of admissibility of tolerance intervals is defined in this paper and we show that these types of tolerance intervals are not admissible due to short of confidence. We further prove that a 100(1-alpha)% confidence interval of a gamma-coverage interval is admissible and is appropriate for use. (C) 2011 Elsevier B.V. All rights reserved.