CSSM News

2012 News

Professor Brian Cullis appointed chair of International Biometrics Committee

The XXVIIth International Biometric Conference will be held in Florence, Italy, 2014 and Professor Brian Cullis has been appointed as chair of International Program Committee as well as a member of the Local Organising Committee.

The biennial conference is a highlight in world biometrics, with eminent international speakers, involving Special Invited Sessions from the ISI (International Statistical Institute), showcases for Young Statisticians, Biometrics and JABES, many other sessions presenting contributed talks, and a workshop.

Professor Brian Cullis' International Program Committee will be responsible for the planning and direction of the scientific facets of the conference. His role as a memberof the Local Organising Committee, will be responsible for the planning and direcion of all non-scientific program facets of the conference including selection of venue and finances. These roles have a close working relationship and are crucial to the planning and delivery of the conference.

The webpage for the 2014 conference has not yet been published. But for more information concerning the conference, please refer to the International Biometric Society homepage or the homepage for the upcoming conference in Kobe, Japan later this year.

IBS homepage - http://www.biometricsociety.org/

Conference homepage - http://secretariat.ne.jp/ibc2012/index.html

 Maximum Likelihood Estimation for Sample Surveys

CSSM members Ray Chambers and David Steel have collaborated with colleagues Suojin Wang from Texas A&M University and Alan Welsh from the Australian National University to produce a book on Maximum Likelihood Estimation for Sample Surveys, which has recently been published by CRC press.

Sample surveys provide data used by researchers in a large range of disciplines to analyse important relationships using well-established and widely-used likelihood methods. The methods used to select samples often result in the sample differing in important ways from  the target population and standard application of likelihood methods can lead to biased and inefficient estimates. Maximum Likelihood Estimation for Sample Surveys presents an overview of likelihood methods for the analysis of sample survey data that account for the selection methods used, and includes all necessary background material on likelihood inference. It covers a range of data types including multilevel data, and is illustrated by many worked examples using tractable and widely-used models. It also discusses more advanced topics, such as combining data, non-response, and informative sampling.

Further details can be found at: http://www.crcpress.com/product/isbn/9781584886327?utm_source=WhatCounts+Publicaster+Edition&utm_medium=email&utm_campaign=DZL17-2_Stat_Theory_JK&utm_content=Maximum+Likelihood+Estimation+for+Sample+Surveys

  Reviewing Census Options in the UK

CSSM Director David Steel has been appointed as an expert reviewer in an advisory panel to provide quality assurance and methodological advice to the UK Office for National Statistics "Beyond 2011" programme. The UK Statistics Authority set up "Beyond 2011" in April 2011 to investigate and assess alternative options for producing the population and socio-demographic data required by users in England and Wales, including those that are currently delivered by the decennial census. This work will include testing models for the use of administrative and survey data as an alternative to the  UK's traditional census approach. "Beyond 2011" will provide a recommendation to the UK Parliament in 2014 on the way forward for the collection of population and socio-demographic statistics, following a period of in-depth research and evaluation across a range of statistical options.

Further information about the programme is available here: http://www.ons.gov.uk/ons/about-ons/what-we-do/programmes---projects/beyond-2011/index.html

 Award winning book from Distinguished Professor Noel Cressie

Released in 2011, Distinguished Professor  Noel Cressie in conjunction with Christopher K. Wikle published "Statistics for Spatio-Temporal Data", a major text in the sphere of Spatial Statistics and Environmental Statistics. The book won the 2011 PROSE Award for Professional and Scholarly Excellence in the Mathematics Category, from the Association of American Publishers.

The book incorporates ideas from the areas of time series and spatial statistics as well as stochastic processes. Beginning with separate treatments of temporal data and spatial data, the book combines these concepts to discuss spatio-temporal statistical methods for understanding complex processes.

This is a state-of-the-art presentation of spatio-temporal processes, bridging classic ideas with modern hierarchical statistical modeling concepts and the latest computational methods. From understanding environmental processes and climate trends to developing new technologies for mapping public-health data and the spread of invasive-species, there is a high demand for statistical analyses of data that take spatial, temporal, and spatio-temporal information into account. Statistics for Spatio-Temporal Data presents a systematic approach to key quantitative techniques that incorporate the latest advances in statistical computing as well as hierarchical, particularly Bayesian, statistical modeling, with an emphasis on dynamical spatio-temporal models.

The book is suitable for graduate students, professional sttaisticians, and researchers and practicioners in the field of applied mathematics, engineering, and the environmental and health sciences.

For further details, please view the book here, or view Professor Noel Cressie's home page here.

Arthur Gilmour receives ALF award

Dr Arthur Gilmour, a Principal Research Fellow with the Centre for Statistical and Survey Methodology, was recognised at the Regional Conference of the International Biometric Society's; nicknamed 'Biometrics by the Blowholes'; in Kiama at the Conference dinner on 7 December 2011.

Dr Gilmour, along with Professor Susan Wilson each received the inaugural AFL award for their long time service to the society and to the biometrics profession. The ALF award is named after and in honour of the region's first vice-president E.A (Alf) Cornish.

Professor Brian Cullis presented the tribute speech to Arthur Gilmour, whilst Professor Alan Welsh from ANU presented the tribute to the other winner of the ALF award, Professor Susan Wilson. The recipients each received a pewter goblet as a gift for their recognition.

Presentation of the ALF award to Susan Wilson and Arthur Gilmour: with gifts L to R; Arthur Gilmour, Brian Cullis, Mario D'Antuono, Sue Wilson and Alan Welsh.

Photogragh courtesy of IBS members Hans Hockey and Harold Henderson.

New Book Release - An Introduction to Model-Based Survey Sampling with Applications

Ray Chambers and Robert Clark, have published a new book titled "An Introduction to Model-Based Survey Sampling with Applications".

This text brings together important ideas on the model-based approach to sample survey, which has been developed over the last twenty years. Suitable for graduate students and professional statisticians, it moves from basic ideas fundamental to sampling to more rigorous mathematical modelling and data analysis and includes exercises and solutions. For further details of the content please click here 

Associate Professor Yan-Xia Lin presents paper at 10th Asia-Pacific Bioinformatics Conference

Associate Professor Yan-Xia Lin attended the 10th Asia Pacific Bioinformatics Conference (APBC2012) in Melbourne, Australia, from 17 to 19 January 2012. The conference received 129 submissions from authors of 16 countries included a large number of high-quality papers in genomic analysis, protein interaction, regulatory network studies and supporting web resources. Among those papers, 43 papers are accepted for presentation in conference. The paper Yan-Xia presented is "The algorithm of equal accceptance region for detecting copy number alterations: application to next generation sequencing data".

Bioinformatics is the application of statistics, computer science and information technology to the field of biology and medicine. The research in Bioinformatics has rapidly developed recently. Statistics has become more and more important in Bioinformatics, particularly, developing new statistical methods for analysing large data sets.

Bioinformatics has strong impact on human health. Research on DNA copy number is an example. Copy number variations (CNV) are alterations of the DNA of a genome that results in the cell having an abnormal number of copies of one or more sections of the DNA. Some CNVs have been associated with susceptibility or resistance to disease. To accurately estimate CNVs based on copy number information provided by genome sequence is a job for statisticians.

Two popular technologies are used to obtain copy number information from genome sequences. One is the Array-Comparative Genomic Hybridization (aCGH) technology and the other is Next Generation Sequencing technology. The next generation sequencing technology tends to provide less random noise on copy number observations if the depth of sequencing data is enough. This technology is potentially powerful alternative to aCGH for identifying genomic structural variations. However, producing sequencing data is expensive currently. Yan-Xia, in her paper, provides an algorithm. By using the algorithm, a data analyser is able to identify a sufficient depth for sequencing data before any sequencing data are produced. A set of sequencing data with the depth will contain sufficient information to ensure the quality of copy number analysis preset b the data analyser. 

Continuing the Collaborative Agreement between Australian Bureau of Statistics and the University of Wollongong

The Collaborative Agreement between the Centre for Statistical and Survey Methodology (CSSM) at the University of Wollongong and the Australian Bureau of Statistics (ABS) began in December 2004 and in March 2006 resulted in the appointment of Ray Chambers as the first Professor of Statistical Methodology - a position funded by ABS. The ABS is very pleased to announce that it has signed a new collaborative agreement that extends funding of the position from March 2011 until March 2014.

Since his appointment, Professor Chambers, working together with the Director of CSSM, Professor David Steel, has improved the skills of ABS methodologists, by questioning the status-quo, encouraging innovation, and by encouraging the development of sound and defensible methods. He has achieved this through annual symposia, courses, mentorship, collaborations, workshops and membership of the ABS' Methodology Advisory Committee. In particular, Professor Chambers' leadership in developing methods of analysing data that are probabilistically-linked, an area of strategic importance to ABS, has been particularly beneficial. Frank Yu, head of the ABS's Methodology and Data Management Division believes that the work of the Centre has significantly enhanced the capacity of ABS staff in conducting methodological research and improving the rigour of ABS's methodological design.

While the elements of the new agreement are essentially unchanged, it puts more emphasis on long term collaborations. The first collaborative project is to develop a framework that uses para-data, or data collected during the survey collection process, to improve responses rates. Professor Chambers is continuing to work on analysis of probabilistically-linked data and will also work on likelihood methods for combining data, another area of strategic importance to ABS. A successful symposium on Robust Regression was held on October 2011. The next symposium is scheduled for October 2012 and will cover Analysis of Longitudinal Data. For more information, please contact Dr James Chipperfield on (02) 6252 7301. 

Continuous Health Information for New Zealand with the help of Wollongong's Statistics Research Strength

University of Wollongong Statisticians will be providing statistical research and advice on the NZ Ministry of Health's population health monitoring surveys. A two-year research contract from 2011-2013 for approximately AUD$200,000 has just been signed, building on successful 2006-2011 collaboration agreements. A/Prof. Robert Clark regularly visits Wellington to collaborate with Ministry researchers.

UoW will be particularly involved in the design and analysis of a new continuous NZ Health Survey. Many countries have national health surveys run every 2 or 3 years as large one-off exercises. NZ Ministry of Health is pioneering an innovative approach where the survey will be continuously in the field, with the possibility of producing statistics as often as quarterly. The new survey, starting in mid 2011, will also save on development and infrastructure costs by avoiding a large setup cost every few years. It will allow particular topics, such as Maori health, to be analysed using data pooled over time, so as to give the best balance of precision and timeliness. Specific question modules, such as problem gambling and alcohol and drug use, will be slotted in and out of the survey over time.

This new contract builds on a theme of collaboration with NZ organisations, including an ARC linkage project with the Ministry of Health and other partners, the conduct of several reviews for the Ministry of Justice, and three research projects funded by Statistics NZ's Official Statistics Research scheme. UoW's Centre for Statistical and Survey Methodology also have major contracts and linkage projects with Australian organisations, including the Australian Bureau of Statistics, NSW Health, the Grains Research and Development Corporation, the Australian Rain Corporation and the Australian Market and Social Research Society.

 Link to Ministry of Health New Zealand website

 (Left to Right) Robert Templeton, Principal Technical Specialist, Health and Disability Intelligence Unit NZ and Associate Professor Robert Clark

Associate Professor Robert Clark recently delivered the 2011 Ken Foreman Lecture in Canberra

Associate Professor Robert Clark of UoW's Centre for Statistical and Survey Methodology recently delivered the annual invited Ken Forman Lecture, at ABS House in Canberra. This annual invited lecture honours Ken Foreman, who pioneered the use of mathematical statistics in Australian governement surveys, including the introduction of sampling (as opposed to censuses which had predominated), and the use of time series analysis of official statistics. The invitation to give this high profile talk was a great honour, particularly as Robert and Professors David Steel and Ray Chambers all benefited from Ken Foreman's legacy, and David and Ray both worked with Ken early in their careers.

Robert spoke on the Art and Science of Sample Design. The sample design is a plan for selecting a sample of units to be surveyed. Choice of a sample design has been expressed mathematically as an optimisation problem, but developing a sampling plan in practice is as much a craft as a science. Complications which need to be considered include balancing multiple objectives, imperfect design information, the practicalities of administering the survey by interview or other means, and incompleteness or inaccuracy of the sampling frame. Some of the current trends in household and business survey sample design were also reviewed. Robert also presented his new research on "data-driven sample designs", which make the most of imprecise design data.

There was a lively discussion led by discussants Alistair Rogers of the Australian Bureau of Statistics (ABS) and Ian McDermid of the Australian National University. The ABS have requested further discussions and a repeat seminar to explore the applicability of this work to ABS sample designs.

Distinguished Professor Noel Cressie Joins CSSM in 2012 

Distinguished Professor Noel Cressie is to join the Centre for Statistical and Survey Methodology in 2012.

Professor Cressie is a world-leading researcher in statistical modelling and analysis of spatial and spatio-temporal data, in Bayesian and empirical-Bayesian methods, and in environmental sciences. The methodology has been applied in areas of "big science", such as remote sensing of the earth on a global scale, regional climate modelling in space and time, and Bayesian statistical exposure modeling from sources to biomarkers. Other research areas include spatial command and control, disease mapping, medical imaging, and ice-stream dynamics.

Noel was born in Fremantle, Western Australia. He received a Bachelor of Science degree with first class honours in Mathematics from the University of Western Australia and MA and PhD degrees in Statistics from Princeton University.

He is currently Professor of Statistics, Distinguished Professor of Mathematical and Physical Sciences, and Director of the Program in Spatial Statistics and Environmental Statistics at The Ohio State University. He was previously Professor of Statistics and Distinguished Professor in Liberal Arts and Sciences at lowa State University.

Noel is the author of around 250 refereed articles and of three books, including Statistics for Spatial Data, revised edition, 1993.

Professor Cressie is a Fellow of the American Statistical Association, the Institute of Mathematical Statistics, and the Spatial Econometrics Association. He is also and Elected Member of the International Statistical Institute. Other honors include: being awarded the Distinguished Achievement Medal of ASA's Section on Statistics and the Environment; the Twentieth Century Distinguished Service Award in Environmental Statistics; the Distinguished Scholar Award of The Ohio State University; and the 2009 Fisher Award and Lectureship from the Committee of Presidents of Statistical Societies. He is on the Institute for Scientific Information's (ISI) elite list of highly cited researchers.

Director of CSSM, Professor David Steel said "This is a fantastic appointment for us and will continue the development of our strong research capacity in Applied Statistics".

UoW news release article can be viewed here

• 2011 Archived News
• 2010 Archived News
• 2009 Archived News
• 2008 Archived News
• 2007 Archived News