In May 2002 a workshop was held at the National Science Foundation to discuss the future challenges and opportunities for the statistics community. After the workshop the scientific committee produced an extensive report that described the general consensus of the community. This article is an abridgment of the full report.

In this article we discuss statistical techniques for modeling data from cohort studies that examine long-term effects of air pollution on children’s health by comparing data from multiple communities with a diverse pollution profile. Under a general multilevel modeling paradigm, we discuss models for different outcome types along with their connections to the generalized mixed effects models methodology. The model specifications include linear and flexible models for continuous lung function data, logistic and/or time-to-event models for symptoms data that account for misspecifications via hidden Markov models and Poisson models for school absence counts. The main aim of the modeling scheme is to be able to estimate effects at various levels (e.g., within subjects across time, within communities across subjects and between communities). We also discuss in detail various recurring issues such as ecologic bias, exposure measurement error, multicollinearity in multipollutant models, interrelationships between major endpoints and choice of appropriate exposure metrics. The key conceptual issues and recent methodologic advances are reviewed, with illustrative results from the Southern California Children’s Health Study, a 10-year study of the effects of air pollution on children’s respiratory health.

Methods are introduced and illustrated for synthesizing evidence from case-control and cohort studies, and controlled trials, accounting for differences among the studies in their design, length of follow-up and quality. The methods, based on hierarchical but nonexchangeable Bayesian models, are illustrated in a synthesis of disparate information about the health effects of passive exposure to environmental tobacco smoke.

Sampling has become an integral part of passive network measurement. This role is driven by the need to control the consumption of resources in the measurement infrastructure under increasing traffic rates and the demand for detailed measurements from applications and service providers. Classical sampling methods play an important role in the current practice of Internet measurement. The aims of this review are (i) to explain the classical sampling methodology in the context of the Internet to readers who are not necessarily acquainted with either, (ii) to give an account of newer applications and sampling methods for passive measurement and (iii) to identify emerging areas that are ripe for the application of statistical expertise.

Today’s Internet is a massive, distributed network which continues to explode in size as e-commerce and related activities grow. The heterogeneous and largely unregulated structure of the Internet renders tasks such as dynamic routing, optimized service provision, service level verification and detection of anomalous/malicious behavior extremely challenging. The problem is compounded by the fact that one cannot rely on the cooperation of individual servers and routers to aid in the collection of network traffic measurements vital for these tasks. In many ways, network monitoring and inference problems bear a strong resemblance to other “inverse problems” in which key aspects of a system are not directly observable. Familiar signal processing or statistical problems such as tomographic image reconstruction and phylogenetic tree identification have interesting connections to those arising in networking. This article introduces network tomography, a new field which we believe will benefit greatly from the wealth of statistical theory and algorithms. It focuses especially on recent developments in the field including the application of pseudo-likelihood methods and tree estimation formulations.

A fundamental problem of Internet traffic engineering is bandwidth estimation: determining the bandwidth (bits per second) required to carry traffic with a specific bit rate (bits per second) offered to an Internet link and satisfy quality-of-service requirements. The traffic is packets of varying sizes that arrive for transmission on the link. Packets can queue up and are dropped if the queue size (bits) is bigger than the size of the buffer (bits) for the queue. For the predominant traffic on the Internet, best-effort traffic, quality metrics are the packet loss (fraction of lost packets), a queueing delay (seconds) and the delay probability (probability of a packet exceeding the delay). This article presents an introduction to bandwidth estimation and a solution to the problem of best-effort traffic for the case where the quality criteria specify negligible packet loss. The solution is a simple statistical model: (1) a formula for the bandwidth as a function of the delay, the delay probability, the traffic bit rate and the mean number of active host-pair connections of the traffic and (2) a random error term. The model is built and validated using queueing theory and extensive empirical study; it is valid for traffic with 64 host-pair connections or more, which is about 1 megabit/s of traffic. The model provides for Internet best-effort traffic what the Erlang delay formula provides for queueing systems with Poisson arrivals and i.i.d. exponential service times.

Norman Lloyd Johnson was born on January 9, 1917, in Ilford, Essex, just east of London, England. He received degrees at University College London in 1936 (B.Sc. in Mathematics) and 1937/38 (B.Sc. and M.Sc. in Statistics). In 1938, at age 21, he was appointed Assistant Lecturer in the Department of Statistics at UCL. During World War II, he served under Egon Pearson as Experimental Officer with the Ordnance Board.

He returned in 1945 to the Statistics Department at University College London and remained there until 1962, as Assistant Lecturer, Lecturer and then Reader. In 1948 he obtained his doctorate in Statistics at UCL, based on his work on the Johnson system of frequency curves. In the following year he became a Fellow of the Institute of Actuaries in London. Two visiting appointments in the United States, at the University of North Carolina (UNC) at Chapel Hill in 1952–1953 and at Case Institute of Technology in Cleveland, Ohio, in 1960–1961, led to his permanent appointment as Professor in the Department of Statistics at UNC in the Fall of 1962. He served as Chairman 1971–1976 and officially retired in 1982, but has continued to be active in scholarship and research as Professor Emeritus.

Norman Johnson is the author or co-author of 17 books, including two textbooks, each in two volumes, and the Distributions in Statistics series initiated with Sam Kotz, 1969–1972, which in its second edition will have run to six volumes. Along with Sam Kotz he has been Editor of 14 books, including the 10-volume Encyclopedia of Statistical Sciences and the three-volume Breakthroughs in Statistics series, all of which are invaluable sources of information for students, teachers and researchers. He is author of more than 180 papers, monographs and tables, many appearing in journals such as Biometrika, The Annals of Mathematical Statistics and Journal of the American Statistical Association. His co-authors include B. L. Welch, Egon Pearson, Florence David, Fred Leone, Harry Smith, Jr., I. W. Burr, James Grizzle, A. W. Kemp, N. Balakrishnan and his wife Regina Elandt-Johnson. He is a Fellow and recipient of the Wilks Award of the American Statistical Association (ASA) and recipient of the Shewhart Medal, American Society for Quality Control. He is featured in the 1995 ASA videotape “An Interview with Norman L. Johnson.”

Norman L. Johnson died in Chapel Hill November 18, 2004.