News

NIASRA News 2013

14th Annual J.B. Douglas Postgraduate Awards Day

On 19th November 2013, six PhD students and three staff members made their way up to UTS in Sydney for the 14th Annual J.B. Douglas Postgraduate Awards Day run by the NSW branch of the Statistical Society of Australia (SSAI).

Six students from five universities were chosen to represent their school by presenting a talk on their research. Sarah Neville (supervisor Distinguished Professor Matt Wand) was our UOW representative and presented an excellent and very engaging talk on 'Elaborate Distribution Semiparametric Regression via Mean Field Variational Bayes'.

The standard of the presentations is always very high. Francis Hui from UNSW who presented an outstanding talk was awarded the only prize of $1000. His presentation title was 'New Methods for Mixture Modelling of Multi-Species Datasets in Ecology'.

Congratulations to Francis Hui from UNSW and to Sarah for being chosen to represent UOW. Noel Cressie was one of the judges for the awards as well as the Invited Guest Speaker for the event. He presented a fascinating talk on 'The Statistical Analysis of Satellite Retrievals' for which the abstract is below.

The Statistical Analysis of Satellite Retrievals
Distinguished Professor Noel Cressie
National Institute for Applied Statistics Research Australia (NIASRA)
University of Wollongong

Remote sensing data from satellites are not direct measurements of a physical or chemical property. They are radiances detected by a spectrometer on board a satellite. A retrieval for each sounding is obtained by solving an ill-posed inverse problem. The resulting geophysical data are often sparse and incomplete with respect to the globe as a whole. Hence, statistical methods are needed that are able to exploit spatial and temporal dependencies in the data to produce complete global maps, together with associated uncertainty estimates. These methods need to accommodate differing spatial variability around the globe, they need to allow for change-of-support, and they need to yield computationally feasible statistical inferences for very-large-to-massive datasets. In this talk, we introduce such spatio-temporal methods and use them to analyze aerosol optical depth (AOD) data obtained from the MISR instrument on board the Terra satellite.

We finished the evening with drinks and dinner overlooking the Sydney skyline which was a great time to network with other students and SSAI members from other universities and to catch up with old friends before travelling home to Wollongong by train.

Thanks to all those who came to cheer on Sarah and Noel.

Sarah Neville receiving certificate
Sarah receiving her certificate from Scott Sisson, SSAI NSW Branch President.

14th Annual J.B. Douglas Postgraduate Awards Day
The six HDR students who presented their topic of research at the awards day receiving their certificate. From left to right: Chong You (University of Sydney), Sarah Neville (University of Wollongong), Zhipeng Hao (Macquarie University), Frances Garden (University of Sydney), Salman Cheema (University of Newcastle) , Francis Hui (University of NSW) (winner).


NEW SURVEYS JOURNAL

The Journal of Survey Statistics and Methodology (JSSAM) (http://jssam.oxfordjournals.org/) was recently launched, with issue 1 appearing in May 2013.  The new journal aims "to publish cutting edge scholarly articles on statistical and methodological issues for sample surveys, censuses, administrative record systems, and other related data."  JSSAM has the backing of leading professional bodies the American Statistical Association and the American Association for Public Opinion Research, and aims to become "the flagship journal for our profession".  NIASRA is involved in this exciting development, with Professor Ray Chambers a member of the editorial board, and A/Prof Robert Clark authoring an article on "Sample Design using Imperfect Design Data" in the first issue.


NIASRA is helping to monitor New Zealanders’ health with a new contract with the NZ Ministry of Health

Associate Professor Robert Clark and other University of Wollongong statisticians will be providing statistical expertise to NZ Ministry of Health's population health monitoring surveys. A two-year research contract from 2013-2015 for up to NZ$250,000 has been signed, and this is the fourth contiguous two-year contract with the Ministry. The collaboration so far has led to innovative and major changes to the design and operation of the NZ health survey, including new methodologies which have been published in leading statistical journals.

UoW's role over the next two years will include training in the analysis of survey data and the provision of analysis and other statistical services feeding into the now continuous NZ Health Survey. Analysis of both costs and variability associated with interviewers and other factors is expected to lead to innovations in survey methods and improved cost efficiency for the survey.

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 three projects associated with the NZ Crime and Safety Survey, and four Statistics NZ projects. NIASRA also has 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.

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

Robert Clark MoH


NIASRA and ABS Symposium on ‘Bayes for Official Statistics’

In association with SSAI and the Australian Bureau of Statistics, a symposium on 'Bayes for Official Statistics' will be conducted in at ABS House, Canberra, 16 October 2013.

The symposium will discuss applications of Bayes that are relevant to Official Statistics, with talks from internationally recognised statisticians including Professor Ray Chambers from NIASRA, and will cover Bayes applications in the areas of missing data, small area estimation, sample design and inference.

For further information, and to register, visit the symposium web site.


World Statistics Congress, Hong Kong

The 59th ISI World Statistics Congress was held late August 2013 in Hong Kong. With a theme of “Youth” for this year, the congress provided a platform for the international statistical community to share and present the latest knowledge and innovation in statistics, with the scientific programme encompassing a wide range of topics to facilitate professional exchanges and sharing amongst experts and practitioners in various statistical spheres.

NIASRA staff members Professor Ray Chambers, Professor David Steel, Dr Gunky Kim presented papers at the congress, with Professor Chambers presenting the Cochran-Hansen award to Mr. Emilio Escobar from Mexico for the best paper on survey research methods submitted by a young statistician from a developing country.

Professor Chambers (right) and Emilio Escobar

Professor Ray Chambers presents an award at the 2013 WSC

A previous article provides further information on the NIASRA staff attending the conference.

Professor Steel (right) in discussion with another delegate at the congress.

Professor David Steel at the 2013 WSC


Distinguished Professor Noel Cressie is working with NASA

Since 2011, UOW Distinguished Professor Noel Cressie has been serving on NASA’s Orbiting Carbon Observatory-2 (OCO-2) Science Team, centered at the Jet Propulsion Laboratory (JPL) in Pasadena, California. As a member of the OCO-2 Science Team, he is studying global precisions and accuracies of column-integrated CO2 from the OCO-2 instrument. The mission is essentially to "watch how the Earth breathes" and map the surface fluxes (sources and sinks) of CO2. This project is one of several that is being carried out by Professor Cressie under his recent two-year (2013-2015) appointment as a JPL Distinguished Visiting Scientist.

Under the second NASA project, funded by NASA’s Earth Systems Technology Office, he is part of a team led by JPL Principal Statistician, Dr. Amy Braverman. This work concerns fusing multi-instrument, multi-process spatial and spatio-temporal datasets, to obtain new datasets that combine information from multiple instruments. The new datasets are accompanied by measures of their uncertainty. The data-fusion methodology is being applied to CO2 data from the Japanese instrument GOSAT, OCO-2, and mid-tropospheric CO2 data from JPL’s AIRS instrument. As a consequence, near-surface CO2 values can be inferred more precisely, from which flux (sources and sinks) estimates can be obtained. Where the CO2 comes from (sources) and where it goes to (sinks) is essential to our understanding of the carbon cycle and its role in global climate change.

Professor Cressie is also working on a third project, Likelihood-Based Quantification of Agreement between Climate Model Output and NASA Data Records, funded by NASA’s Earth Science Data Records Uncertainty Analysis Program. With JPL's Dr. Braverman, they are using statistical-resampling methodology to evaluate the consistency of climate-model simulations with remote sensing observations. Those models would then be trusted to supply accurate forecasts of future climate.

Read more: Award-winning Wiley author takes on statistical role at NASA

For further information, visit the OCO-2 website or AIRS’s Spatio-temporal mapping of CO2 website. At the conclusion of the latter website, there is a movie showing spatial statistical prediction of mid-tropospheric CO2 as time progresses through the boreal spring of 2010.

From left to right, Dr. Michael R. Gunson (OCO-2 Project Scientist), Dr. Amy Braverman (JPL Principal Statistician), and UOW’s Distinguished Professor Noel Cressie.

Professor Noel Cressie at NASA 


Professor Ray Chambers appointed to prestigious United Nations Committee

Professor Ray Chambers from NIASRA has been appointed to the Scientific Advisory Committee (SAC) supporting the Global Strategy to Improve Agricultural and Rural Statistics that is currently being developed by the Food and Agriculture Organisation of the United Nations (FAO). The SAC is responsible for providing key advice on the Global Strategy's research plan, which is aimed at developing more cost-effective methods and tools for data collection, analysis and dissemination relating to global agricultural outputs, particularly in developing countries. In this context, the research plan aims to extend recent methodological and technological advances in statistical data collection and analysis in order to take into account the specific needs and capacities of developing countries.

The terms of reference of the SAC involve providing technical advice to the global office of the FAO on technical issues, analysing the results of research activities commissioned by the global office of the FAO, validating the process and results of these research activities, ensuring that the best technical standards are respected, and supporting the global office in the selection of the most appropriate institutions/experts (in conformity with FAO rules) when the activities of these research topics are outsourced.

The SAC had their first meeting in Rome on 1 July this year. Issues discussed included master sampling frames, estimating cost of production in developing countries, estimating livestock and livestock products, estimating postharvest losses, and better integration of geographic information and statistics, as well as addressing administrative arrangements and plans for managing the committee.


Two NIASRA students graduate with PhDs

NIASRA would like to congratulate Dr Alexandra (Sandy) Burden and Dr Diane Hindmarsh who were awarded their PhD awards at the Graduation ceremony held on July 26, 2013 and wish them success and fulfilment in their future endeavours.  The tile of Sandy’s thesis is “Zone Issues in the Analysis of Small Area Health Data”, and the title of Diane’s thesis is “Small Area Estimation for Health Surveys”.  

From left to right, Professor David Steel, Dr Alexandra (Sandy) Burden, and Dr Diane Hindmarsh

NIASRA Graduation July 2013


NIASRA competes strongly in National bridge competition

Steve Hurley, NIASRA project coordinator, played in the NSW team at the Australian National Teams bridge championship in Adelaide early July. The team comprised of three pairs, two from Sydney and a country pair including Steve, with Steve and his partner being the first country pair to represent NSW. Qualifying for the final was over five days where they were about second or third between Victoria and the favorites South Australia. Steve played in the final round against South Australia and scored well for NSW to win their way into the final. South Australia played too strongly in final so NSW came a creditable second.


2013 Vice-Chancellor's Awards for Excellence in Research

Professor Brian Cullis and his research partner Grains Research Development Corporation have shared the Vice Chancellor’s Award for Outstanding Achievement in Research Partnership.  This involves the National Variety Trials (NVT) program, Public Plant Breeding programs, and Wheat Classification programs.  Read further detail on the work with the GRDC.


MAJOR GRANT TO FUND RESEARCH INTO GENOMIC SELECTION.

Prof Brian Cullis and Associate Professor Alison Smith from NIASRA and Dr Haydn Kutchel, from the industry partner, Australian Grain Technologies, have been awarded and Australian Research Council Linkage grant for their project entitled “Genomic selection: a new frontier for higher rates of genetic gain in wheat”.  This involves genetic improvement in wheat yields is estimated between 0.75% and 1% per annum.  Read further detail on the their work.


Professor David Steel elected as a member of the prestigious International Statistical Institute

NIASRA Director David Steel has been recently elected as a member of the International Statistical Institute (ISI), which is a leading world organisation in statistics disciplines.  Members are elected by virtue of their contributions to the development or application of statistical methods, administration of statistical services, or development and improvement of statistical education.  Read further details about the ISI and other ISI members from NIASRA.


Distinguished Professor Noel Cressie invited to speak as International Biometrics Society biennial conference.

The next biennial conference for the Australasian Region of the International Biometrics Society will be held in Western Australia in December 2013, and Professor Noel Cressie from NIASRA has been invited to speak.

The conference discusses issues ranging across spatial and temporal statistics, linear mixed models, complex genetic mixed models, design of experiments, generalized linear and additive models, and Bayesian methods.  Professor Noel Cressie will deliver a presentation titled “Statistics for Spatio-Temporal Data”.  Other invited speakers are Prof. Thomas Yee from Auckland University, Prof. Ian James from Murdoch University, Prof. Christine Müller from Technische Universität Dortmund, Prof. Alan Welsh from Australian National University, and Ric Coe from the World Agroforestry Centre.

For further information on the conference, please visit their website here.


Professor Brian Cullis appointed Chair of the IBC, Italy, 2014

Professor Brian Cullis has been appointed International Programme Committee Chair of the 27th International Biometric Conference to be held 6-11 July in Florence, Italy.

The International Biometric Society is an international society promoting the development and application of statistical and mathematical theory and methods in the biosciences, including agriculture, biomedical science and public health, ecology, environmental sciences, forestry, and allied disciplines. And the conference is the major event for the IBS held each year in different locations around the world.

Working with the Education Committee, this role broadly involves liaising with leading industry groups and professionals to advertise and receive invited papers for the scientific programme, then chairing a team to evaluate and select papers to be included in the Scientific Program, then that team scheduling presentations and participants through the conference.

For further information on the conference please view here.


NIASRA wins MLA tender 

Dr Simon Diffey, a Research Fellow within the National Institute for Applied Statistics Australia (NIASRA), was successful in a Meat & Livestock Australia tender to provide a Pasture Variety Trial Network (PVTN) design and analysis service. The University of Wollongong is the lead organisation in this project worth $120K over 2.5 years. The project also includes researchers from the Queensland Department of Agriculture, Forestry, and Fisheries; and the NSW Department of Primary Industries.

This project complements existing projects within NIASRA's Centre for Bioinformatics and Biometrics Research, the flagship project being the $6M over 5 years Statistics for the Australian Grains Industry (SAGI) project led Professor Brian Cullis. Both Dr Simon Diffey and Dr Alison Smith, a Principal Research Fellow within NIASRA, are fully funded by industry. Simon is funded by the Grains Research Development Corporation (GRDC) and the CRC for High Integrity Australian Pork and Alison is funded by GRDC.

These close links with the agricultural industry, and the grains industry in particular, have led to GRDC funded student summer vacation scholarships worth $3000 each and 2 honours year scholarships worth $10000 each. The Centre for Bioinformatics and Biometrics Research has recently advertised a PhD scholarship in the area of statistical genetics worth $35K a year and is looking to make 2 new industry funded appointments in the near future to work in the area of plant breeding and quantitative genetics. 


Post doc to work on experimental designs in genomic studies

NIASRA has secured a 12 month post doctorate position to investigate computing methods for generating optimal experimental designs in real-time for large phenotyping experiments in genomic studies.

Working with The Department of Fisheries & Forestry Queensland (DAFF), the position in NIASRA will undertake research on a design generator for complex optimal experimental designs under a general linear statistical model. The model may include random (and correlated) genetic, fixed or random non-genetic, and correlated residual effects. The aims of the project include:

  • efficient model-based optimal design software, including R functions for unoptimised starting designs;
  • methods to generate inverse relationship matrices for inclusion in the design model;
  • direct links to a plant breeding information system (Katmandoo) for storing experimental designs; including a web interface capability and model specification in XML; and 
  • tools to manipulate plant pedigrees with filial generations in R.

The appointee will commence 1 July 2013 and continue to 30 June 2014. 


NIASRA is jumping into R

NIASRA staff, Sandy Burden, Carole Birrell, Thomas Suesse and Anne Porter, have been successful in obtaining an ESDF grant for their project titled ‘Jump into R’.

When teaching statistics, the choice of software to support learning is fundamental to the success of the subject. R is a freely-available statistical software package, which is widely used for research and by industry, and is currently introduced and taught to honours students in statistics. This project will introduce R into 2nd year statistics subjects. The project aims to improve student’s conceptual understanding of statistics and develop modern programming skills at a lower level, so students have a greater understanding and improved skill set at graduation, improving their employment opportunities. It also builds on the use of open source software at the first year level, allowing better access to learning resources at home by low socioeconomic students.

The project involves two core elements: (1) redeveloping teaching material to reflect and support the use of R, and (2) providing a web page of useful links to online learning resources for R, accessible to the wider university community.

For further information, please contact Sandy Burden sburden@uow.edu.au  


Measuring radio audiences

NIASRA have been working with Commercial Radio Australia to improve the radio audience measurement system. For more detail, read the UOW news item here.  


International conferences

In 2013, NIASRA staff and students will be attending a variety of conferences and meetings to deliver papers or take part in the meeting.  These are as follows =>

  • Graybill Conference in Colorado, USA (June) - Ray Chambers
  • IEEE International Conference on Multimedia and Expo in San Jose, USA (July) - Payam Mokhtarian
  • IEEE International Conference on Intelligent Rail Transportation in Beijing, China (August) - Payam Mokhtarian
  • Joint Statistical Meeting in Montreal, Canada (August) - Ray Chambers
  • ISI conference in Hong Kong (August) - Ray Chambers, Gunky Kim, James Chipperfield, Margo Barr, and David Steel
  • International Conference on Survey Research Methodology in Taipei, Taiwan (September) - Walter Davis
  • Scientific Advisory Committee in Bangkok, Thailand (September) - Ray Chambers, Payam Mokhtarian, and Sumonkanti Das.
  • 60th anniversary SASA Conference in Limpopo, South Africa (November) - Ray Chambers

For further details of NIASRA's participation, click here.


NIASRA is offering a short course on sampling methods for small or hard-to-reach populations

This is a one-day course aimed at statisticians and survey professionals interested in small populations. The course will be held on 14 June, 2013 at the Sydney Business School (Sydney Campus). The presenters are Professor Matthias Schonlau, who is a Professor of Statistics at the University of Waterloo, Canada and Associate Professor Robert Clark, from the National Institute for Applied Statistics Research Australia (NIASRA), at the University of Wollongong.

For more information about the course please click here.

To obtain a nomination form please click here.


Ray Chambers to Co-chair, First Asian International Statistical Institute Satellite Meeting on Small Area Estimation, Bangkok, Thailand on September 1-4, 2013.

 "The meeting will provide researchers an opportunity to learn state-of-the-art small area estimation techniques from the experts in the field"

For more information, please visit the website http://www.math.sc.chula.ac.th/sae2013

Last reviewed: 26 August, 2014

Upcoming Events

The Questionnaire Revealed, Dr. Pamela Campanelli
1 - 3 November 2017

Past Events

International Conference on Robust Statistics, July 2017