Generations Of Statisticians Research Articles

Remembering Ralph B. D’Agostino Sr.

Ralph B D’Agostino, Sr. was a very well-regarded statistician/biostatistician who made significant contributions to the areas of non-parametrics, design of clinical trials, and research in cardiovascular disease. This memorial article gathers heartfelt remembrances from colleagues, family, and former students, who recall not only his many significant scientific contributions but also his unwavering dedication to mentoring the next generation of statisticians.

Data science skills for the next generation of statisticians

This paper analyses the future prospects of statistics as a profession and how data science will change it. Indeed, according to Hadley Wickham, Chief Scientist at Rstudio, “a data scientist is a useful statistician”, establishing a strong connection between data science and applied statistics. In this direction, the aim is to look to the future by proposing a structural approach to future scenarios. Some possible definitions of data science are then discussed, considering the relationship with statistics as a scientific discipline. The focus then turns to an assessment of the skills required by the labor market for data scientists and the specific characteristics of this profession. Finally, the phases of a data science project are considered, outlining how these can be exploited by a statistician.

Digital Age: New Competencies and Occupations that Define a Sustainable Development Amidst the Industrial Revolution 4.0

The paper focuses on the challenges of training a new generation of statisticians with the core 21st-century competencies for life, work, and creativity in a digital society amidst the fourth industrial revolution (Industry 4.0). Along with the economic feasibility, the attractiveness of improving the quality of life, and new possibilities for developing the creative potential of human beings, Industry 4.0 freights with risks of destabilization of the world socio-economic system, but also creates a new cultural and historical context of the advancement of the humankind, where the network becomes a new human habitat, when digital technologies penetrate all spheres of human activity. It requires the development of «digital» skills that have never been more important than today. Summarizing the results of digital skills projects, the UNESCO Institute for Statistics developed the «Digital Literacy Global Framework» as a basis for creating national digital literacy frameworks and digital competence models for various occupations. The article substantiates the importance of digital competencies and the feasibility of developing common requirements for digital literacy in the EAEU member-states and establishing a system for its development with a single scientific, educational and methodological center that will at the same time become the core of a new ecosystem of continuous statistical training, designed to correct the situation when it is almost impossible to find a statistician with the necessary competencies in the labor market. One of the reasons for this is that the existing system of statistical education does not meet the needs of the digital age, which requires new approaches to the organization of continuing education. However, the digital agenda implies not only the development of digital competencies, including statistical literacy but also the emergence of new «digital» professions, to which the profession of a statistician can be assigned if it is filled with competencies listed in the paper. This will allow statistics to take its rightful place among the occupations determining sustainable development in the digital age.

High-Dimensional Linear Models: A Random Matrix Perspective

Professor C.R.Rao’s Linear Statistical Inference is a classic that has motivated several generations of statisticians in their pursuit of theoretical research. This paper looks into some of the fundamental problems associated with linear models, but in a scenario where the dimensionality of the observations is comparable to the sample size. This perspective, largely driven by contemporary advancements in random matrix theory, brings new insights and results that can be helpful even for solving relatively low-dimensional problems. This overview also brings into focus the fundamental roles played by the eigenvalues of large covariance-type matrices in the theory of high-dimensional multivariate statistics.

Training the Next Generation of Statisticians: From Head to Heart

ABSTRACTA holistic view of training is advocated where educators focus not only on the competence but also on the character of future statisticians. The issues related to developing passion, formulating philosophy, and building moral personhood are discussed. The vision is to foster a generation of statisticians who are both well-equipped problem-solvers in specific scientific areas and compassionate reformers to the general society.

Statistical Computing in Information Society

Abstract In the presence of massive data coming with high heterogeneity we need to change our statistical thinking and statistical education in order to adapt both - classical statistics and software developments that address new challenges. Significant developments include open data, big data, data visualisation, and they are changing the nature of the evidence that is available, the ways in which it is presented and the skills needed for its interpretation. The amount of information is not the most important issue – the real challenge is the combination of the amount and the complexity of data. Moreover, a need arises to know how uncertain situations should be dealt with and what decisions should be taken when information is insufficient (which can also be observed for large datasets). In the paper we discuss the idea of computational statistics as a new approach to statistical teaching and we try to answer a question: how we can best prepare the next generation of statisticians.

Globally efficient non-parametric inference of average treatment effects by empirical balancing calibration weighting.

The estimation of average treatment effects based on observational data is extremely important in practice and has been studied by generations of statisticians under different frameworks. Existing globally efficient estimators require non-parametric estimation of a propensity score function, an outcome regression function or both, but their performance can be poor in practical sample sizes. Without explicitly estimating either functions, we consider a wide class calibration weights constructed to attain an exact three-way balance of the moments of observed covariates among the treated, the control, and the combined group. The wide class includes exponential tilting, empirical likelihood and generalized regression as important special cases, and extends survey calibration estimators to different statistical problems and with important distinctions. Global semiparametric efficiency for the estimation of average treatment effects is established for this general class of calibration estimators. The results show that efficiency can be achieved by solely balancing the covariate distributions without resorting to direct estimation of propensity score or outcome regression function. We also propose a consistent estimator for the efficient asymptotic variance, which does not involve additional functional estimation of either the propensity score or the outcome regression functions. The proposed variance estimator outperforms existing estimators that require a direct approximation of the efficient influence function.

A good deal of humility: Cochran on observational studies

A good deal of humility: Cochran on observational studies

Statistics and Causality: Separated to Reunite-Commentary on Bryan Dowd's “Separated at Birth”

Statistics and Causality: Separated to Reunite-Commentary on Bryan Dowd's “Separated at Birth”

Student's z, t, and s

The year 2008 marks the 100th anniversary of the publication of The Probable Error of a Mean by William Sealy Gosset, nom de plume “Student.” Gosset's work and his relationships with the leading statisticians of his day have been considered by several authorities. Despite the extensive documentation, and the seminal nature of the work, modern-day statistics textbooks give him, and this 1908 article, short shrift. Thus, few of today's students—or their teachers—are aware of the “z” statistic whose sampling distribution he actually derived, the mathematical derivation, his simulations to check his work, the material used in the simulations, the table he produced, the “one-line” missing proof supplied by the 22-year-old Fisher (still a student himself) or the subsequent switch, in collaboration with Fisher, from the z to the t statistic. We remind readers of these aspects, and rework his calculations using 21st century computing power. We hope that the next generation of statisticians come to know more about the man and his work than simply that “he worked for the Guinness brewery,” and appreciate that not all statistical distributions are derived in a single pass. Research students would do well to use his 1908 article as a model when writing their first statistical article.

Training Statisticians To Be Alert To The Dangers Of Misapplying Statistical Methods

Statisticians are faced with a variety of challenges. Their ability to cope successfully with these challenges depends, in large part, on the quality of their training. It is not the purpose of this article to present a comprehensive training plan that will overhaul the standard curriculum a statistician might follow under current training regimens (i.e., in a degree program). Rather, the objective is to point out important areas that appear to be under-represented in standard curricula and correspondingly overlooked too often in practice. The hope is that these areas might be better integrated into the training of the next generation of statisticians.

Teaching Experimental Design

After a career as a consulting statistician, I decided to teach. This article describes my evolving views as I developed and taught introductory university courses on experimental design, organized around and stimulated by three different texts and three different universities. Primarily, I found it to be essential, particularly at the course's beginning, to embed textbook examples in credible scientific or business contexts in order to try to convince students of the value of statistical experimental design and analysis in their subsequent careers. In contrast, uninteresting, even nonsensical, undeveloped examples that serve only as formula drill give students the opposite impression. My purpose in this article is to present selected expanded textbook examples and to use these illustrations to examine fundamental issues in experimental design such as: the importance of subject-matter, the choice of experimental units, the nature and purpose of blocking, and the contrast between random sampling and random assignment of treatments. These examples expose fundamental issues in how our profession functions in a collaborative environment and how we prepare the next generation of statisticians and statistically savvy professionals. My hope is that the illustrations provided will be directly useful to beginning instructors and provocative to the experienced.

An Essay on Statistical Decision Theory

(2000). An Essay on Statistical Decision Theory. Journal of the American Statistical Association: Vol. 95, No. 452, pp. 1277-1281.

What Academia Needs

I have been asked to speak on the topic Modem Interdisciplinary University Statistics Education: What the Customer (Academia) Needs. My translation of this is: What kind of education would we like our future faculty to have so that they can best train the next generation of statisticians in industry, government, and academia? Or, equivalently, to what training and opportunities should we expose our own Ph.D. students? I arrive at this by considering statistics departments as the customer for new statistics faculty. As for interdisciplinary, I think the adjective is redundant. Leslie Kish in his 1977 American Statistical Association presidential address (Kish 1978, p. 1) gives a description of our field that makes this point well:

Graphical Models in Applied Multivariate Statistics

The Wiley Paperback Series makes valuable content more accessible to a new generation of statisticians, mathematicians and scientists.Graphical models--a subset of log-linear models--reveal the interrelationships between multiple variables and features of the underlying conditional independence. This introduction to the use of graphical models in the description and modeling of multivariate systems covers conditional independence, several types of independence graphs, Gaussian models, issues in model selection, regression and decomposition. Many numerical examples and exercises with solutions are included.This book is aimed at students who require a course on applied multivariate statistics unified by the concept of conditional independence and researchers concerned with applying graphical modelling techniques.

The Analysis of Variance

Originally published in 1959, this classic volume has had a major impact on generations of statisticians. Newly issued in the Wiley Classics Series, the book examines the basic theory of analysis of variance by considering several different mathematical models. Part I looks at the theory of fixed-effects models with independent observations of equal variance, while Part II begins to explore the analysis of variance in the case of other models.

Social and Economic Adjustments in a Democratic World

THIE YEAR, just passed, will no doubt go down as one of the most significant, thus far, in statistical history. It will be remembered by this generation of statisticians, not so much because of the value and importance of the output of statistical material, but rather by the fact that figures-statistical data-were the central point of economic and social controversy through the greater part of the year. Indeed, the battle of statistics was well under way before the year 1946 began. It came to the forefront in the automobile wage controversy; in the contention of the Automobile Workers Union that wage rates could be raised by a certain amount without necessarily increasing the cost of cars to the public. When this contention was denied and the union undertook to modify its demands, if management could prove by actual evidence that the wage increase could not be granted without an appreciable rise in production costs and hence in the price of its products, management, according to press dispatches, stood by its constitutional rights to refuse to make such data available. There followed one of the longest and costliest strikes in the annals of the automobile industry, a strike that was finally resolved after granting a wage increase of fairly considerable proportions. It is not intended here to question the right of management, as reported in the press, to refuse to reveal the details of its costs. That is an issue of public policy that is an integral part of our concept of the nature of private rights, and our concept of under what conditions an industry comes within what has been defined as a public utility. Nor are we here concerned with the circumstances or the manner in which an agency of the federal government concluded that an increase of 191 cents was justifiable. Nor are we concerned with the circumstances that finally led the management to grant the increase it made. What we are concerned with is the fact that we, you and I, do not know, and perhaps never will know, whether wages could have been increased 25 cents, 184 cents, 16 cents, or even 10 cents, without appreciably raising the labor cost of making automobiles-had the controversy been amicably settled with-