An Interview with Stanford M. Forrester, Editor and Publisher of bottle rockets

A little haiku zine / from Connecticut / who would have guessed? This installment of “They Might Be Giants” focuses on bottle rockets, a small haiku journal from, that's right, Connecticut. Stanford M. Forrester, publisher and editor of bottle rockets, talked briefly with Michael Brown about poetry, fireworks, and why he does what he does. Serials Review 2003; 29:321–324.     

Bay! Bar charts

Allan Reese has often asserted that authors and editors appear less able to proofread graphs than text. It is hard to prove such a claim except by parading examples that, had they been expressed in text, would fall into the category that Private Eye calls "Colemanballs"—things you would never say with brain fully engaged. Here, he provides a few such examples.     

工程硕士在职研究生学位论文质量与个人背景特征——基于有序Probit模型的实证分析

在多年教育实践的基础上,国内的研究者们对提高专业学位研究生培养质量问题发表了许多论文,但大多是一般性的工作经验总结,鲜有人能够上升到教育学、社会学、心理学理论层面的研究,更没有做到基于统计学方法的科学实证检验。借鉴英文文献中关于欧美国家同类问题的理论和实证研究成果,采用某"985"高校2008—2011年毕业的2 366名工程硕士专业学位在职研究生的数据,应用有序probit模型,对学位论文的质量与在职研究生的人口学、职业经验、本科教育等背景特征之间的关系进行实证分析,得出了一些能够弥补现有中文文献空白的结论。     

A link-free sparse group variable selection method for single-index model

For regression problems with grouped covariates, we adapt the idea of sparse group lasso (SGL) [10 J. Friedman, T. Hastie, and R. Tibshirani, A note on the group lasso and a sparse group lasso, Tech. Rep., Statistics Department, Stanford University, 2010. [Google Scholar]] to the framework of the sufficient dimension reduction. Assuming that the regression falls into a single-index structure, we propose a method called the sparse group sufficient dimension reduction to conduct group and within-group variable selections simultaneously without assuming a specific link function. Simulation studies show that our method is comparable to the SGL under the regular linear model setting and outperforms SGL with higher true positive rates and substantially lower false positive rates when the regression function is nonlinear. One immediate application of our method is to the gene pathway data analysis where genes naturally fall into groups (pathways). An analysis of a glioblastoma microarray data is included for illustration of our method.     

Career story: Pharmaceutical Statistician

Nobody could accuse the Royal Statistical Society's President Andy Grieve of looking for a quiet life. As well as being a consultant statistician for pharmaceuticals company Pfizer, he has for many years been heavily involved with the Society and Statisticians in the Pharmaceutical Industry. However, he claims to Helen Joyce that his early career was shaped by a fondness for "taking the easy option".     

Racing, the Law and the Top Jockey: the Kieren Fallon trial

In a headline-hitting trial at the Old Bailey last year, top jockey Kieren Fallon was accused of "throwing" races. Did he really ride to lose? John Haigh comes to a clear statistical conclusion.     

A Bayesian approach to inference about a change point model with application to DNA copy number experimental data

In this paper, we study the change-point inference problem motivated by the genomic data that were collected for the purpose of monitoring DNA copy number changes. DNA copy number changes or copy number variations (CNVs) correspond to chromosomal aberrations and signify abnormality of a cell. Cancer development or other related diseases are usually relevant to DNA copy number changes on the genome. There are inherited random noises in such data, therefore, there is a need to employ an appropriate statistical model for identifying statistically significant DNA copy number changes. This type of statistical inference is evidently crucial in cancer researches, clinical diagnostic applications, and other related genomic researches. For the high-throughput genomic data resulting from DNA copy number experiments, a mean and variance change point model (MVCM) for detecting the CNVs is appropriate. We propose to use a Bayesian approach to study the MVCM for the cases of one change and propose to use a sliding window to search for all CNVs on a given chromosome. We carry out simulation studies to evaluate the estimate of the locus of the DNA copy number change using the derived posterior probability. These simulation results show that the approach is suitable for identifying copy number changes. The approach is also illustrated on several chromosomes from nine fibroblast cancer cell line data (array-based comparative genomic hybridization data). All DNA copy number aberrations that have been identified and verified by karyotyping are detected by our approach on these cell lines.     

How to take a penalty

When Rob Eastaway told friends he was embarking on a project to write a book about the maths of sport, they didn't hear the word "maths"-they heard "statistics". That, after all, is the most obvious interpretation. But, as he discovered, mechanics, geometry and even some mathematical history all play their part.     

Driving out failure

Product recall notices in shops, newspapers and elsewhere inform us now and then of children's toys that might be dangerous or electrical goods that could catch fire. You or I might describe that as faulty design. Tim Davis calls it an "escaped failure mode"—and he is against it. His world is not toys or electrical goods, but vehicles, where failure modes and recalls are more expensive and usually more serious. As an example: in 2001 the failure of certain Firestone tyres on Ford SUVs led to rollover accidents in which close to 300 people died. Nearly 20 million tyres needed to be recalled. Industry estimates put the cost at around †3 billion. It was Tim Davis who was called in to find out what had gone wrong. Julian Champkin interviewed him.     

Change Points with Linear Trend Followed by Abrupt Change for the Exponential Distribution

We discuss testing procedures to detect if a random sequence of exponentially distributed random variables has been subjected to a linear trend change followed by an abrupt change. We propose three statistics and explore their distribution theories. As an illustration, we applied these tests to Stanford heart transplant data and airport inter arrival data.     

Fitting linear regression models to censored data by least squares and maximum likelihood methods

Several approaches have been suggested for fitting linear regression models to censored data. These include Cox's propor­tional hazard models based on quasi-likelihoods. Methods of fitting based on least squares and maximum likelihoods have also been proposed. The methods proposed so far all require special purpose optimization routines. We describe an approach here which requires only a modified standard least squares routine.

We present methods for fitting a linear regression model to censored data by least squares and method of maximum likelihood. In the least squares method, the censored values are replaced by their expectations, and the residual sum of squares is minimized. Several variants are suggested in the ways in which the expect­ation is calculated. A parametric (assuming a normal error model) and two non-parametric approaches are described. We also present a method for solving the maximum likelihood equations in the estimation of the regression parameters in the censored regression situation. It is shown that the solutions can be obtained by a recursive algorithm which needs only a least squares routine for optimization. The suggested procesures gain considerably in computational officiency. The Stanford Heart Transplant data is used to illustrate the various methods.     

Managing Serials in an Institutional Repository: An Interview With Kay Teel

ABSTRACT

In this interview from March 2017, Kay Teel, metadata librarian for serials and arts resources at the Stanford University Libraries, discusses the issues involved in providing access to serials through an institutional repository.     

Nonparametric estimator for the survival function of quality adjusted lifetime (QAL) in a three-state illness–death model

In this work, we consider nonparametric estimation of QAL distribution in a three-state illness–death model. In our approach, we first write down the expression for the distribution of QAL in terms of the joint distribution of the sojourn times in the three states. The estimate of the QAL distribution is obtained by substituting the estimates of sojourn time distributions in the expression of the QAL distribution. The proposed nonparametric estimate, assuming independence between time to illness and sojourn time in the state of illness, is uniformly consistent. Asymptotic normality has also been established. An estimate of asymptotic variance has been obtained. The performance of the proposed estimator is investigated by simulation. A data set of the Stanford Heart Transplant program has been analyzed for illustration.     

Bayesian Random Segmentation Models to Identify Shared Copy Number Aberrations for Array CGH Data

Array-based comparative genomic hybridization (aCGH) is a high-resolution high-throughput technique for studying the genetic basis of cancer. The resulting data consists of log fluorescence ratios as a function of the genomic DNA location and provides a cytogenetic representation of the relative DNA copy number variation. Analysis of such data typically involves estimation of the underlying copy number state at each location and segmenting regions of DNA with similar copy number states. Most current methods proceed by modeling a single sample/array at a time, and thus fail to borrow strength across multiple samples to infer shared regions of copy number aberrations. We propose a hierarchical Bayesian random segmentation approach for modeling aCGH data that utilizes information across arrays from a common population to yield segments of shared copy number changes. These changes characterize the underlying population and allow us to compare different population aCGH profiles to assess which regions of the genome have differential alterations. Our method, referred to as BDSAcgh (Bayesian Detection of Shared Aberrations in aCGH), is based on a unified Bayesian hierarchical model that allows us to obtain probabilities of alteration states as well as probabilities of differential alteration that correspond to local false discovery rates. We evaluate the operating characteristics of our method via simulations and an application using a lung cancer aCGH data set.     

目光深远的统计学大师 ——张尧庭先生逝世五周年纪念

 张尧庭先生是一位目光深远的统计学大师。本文认为他生前提出的下述观点即“统计学的发展全靠数学与实际问题的推动”,“为反映整体的、动态的东西统计学必须要有新突破”,以及“促进数理统计和经济统计的学术交流”等,在今天仍然具有现实意义,可为我们现时的统计学教学与研究的深入发展提供有益参考。     

For censored and truncated data

In this paper we develop nonparametric methods for regression analysis when the response variable is subject to censoring and/or truncation. The development is based on a data completion princple that enables us to apply, via an iterative scheme, nonparametric regression techniques to iteratively com¬pleted data from a given sample with censored and/or truncated observations. In particular, locally weighted regression smoothers and additive regression models are extended to left-truncated and right-censored data Nonparamet¬ric regression analysis is applied to the Stanford heart transplant data, which have been analyzed by previous authors using semiparametric regression meth¬ods. and provides new insights into the relationship between expected survival time after a heart transplant and explanatory variables.     

Control charts in practice

In the first issue of Significance , Roland Caulcutt suggested that a common feature of many successful companies is their development of a "management-by-fact" culture. He further suggested that such a culture requires that managers focus on processes, and that control charts be used at all levels throughout the organisation. In this follow-up article he explains how the various types of control chart are set up and used in practice.     

Testing for Linear Regression Relationships in Randomly Right-Censored Varying-Coefficient Models

A test statistic is constructed to test linear relationships in randomly right-censored varying-coefficient models. A residual-based bootstrap procedure is employed to derive the p-value of the test. The performance of the test is examined by extensive simulations. The simulation results show that the bootstrap estimate of the null distribution of the test statistic is approximately valid and the test method with the residual-based bootstrap works satisfactorily for at least moderate censoring rates of the response. Furthermore, the proposed test is applied to the Stanford heart transplant data for exploring a linear regression relationship between the logrithm of the survival time and the age of the patients.     

Wild card

In 1992 Persi Diaconis of Stanford University told the world just how many times a pack of cards should be shuffled. He is one of the more colourful of professors of statistics. He tells Julian Champkin about crooked dice, tossing coins and conjuring tricks—and how statistics makes sense of his world.     

中国绿色经济发展指数研究

文章界定了绿色经济与绿色经济发展指数,根据生态经济系统物质流动的原理与绿色经济的关系,构建了中国绿色经济发展指数,并运用"十一五"时期的数据对指数进行验证。测算结果表明:中国绿色经济发展处于低水平发展阶段,目前的绿色经济发展不具有典型绿色经济的性质。