BSc (UWA); MSc (ANU); PhD (Johns Hopkins)



Statistics
2021

I have made significant contributions to the development of statistical methodology, particularly in the areas of modelling and analysis of sample survey data and in the application of statistical methods to social and official statistics. My research has spanned a wide range of applications in the design and analysis of sample surveys, including methodology for small sample inference from surveys and on issues related to the analysis and modelling of data collected in complex surveys, particularly likelihood-based methods for modelling the complex data structures that arise when data obtained from auxiliary sources, particularly by linkage to administrative registers, are integrated with sample survey data in analysis. My PhD research was the first to address outlier robust methods for finite population prediction, while my research on efficient model-based survey inference for distributions remains the basis for most modern approaches to this topic. I was the lead author on the first paper to describe the M-quantile class of distributional models that are now widely used as robust alternatives to the parametric distribution-dependent mixed models often employed in hierarchical modelling of survey data. I was the main author for the first published paper to describe how the Missing Information Principle provides the correct framework for full information likelihood analysis of sample survey data and was the author of a major Statistics New Zealand research report that described a practical approach to the secondary analysis of probability-linked data. I have co-edited two books, one that is widely regarded as the most advanced and up to date reference on statistical issues associated with the analysis of survey data, and the other the first to address statistical theory for dealing with the analysis of multiple data sets in a way that accounts for the very different ways in which these data may have been acquired. A defining characteristic of my research has been on applying foundational principles for statistical inference to real survey data analysis problems, including problems associated with the analysis of survey data that have been probabilistically linked to auxiliary data sources and the integration of multiple sources of auxiliary information into survey data analysis. My 2012 book Maximum Likelihood Estimation for Sample Surveys, co-authored with Steel, Welsh and Wang, is the only one that provides a rigorous development of how maximum likelihood methods should be defined when applied to sample survey data, while my other 2012 book, An Introduction to Model-Based Survey Sampling with Applications, co-authored with Clark, is one of the very few sample survey texts that offers a comprehensive and integrated model-based approach to sample survey inference. My most recent research addresses the use of statistical methods for causal inference in the context of mitigation of the effects of climate warming, focusing on rainfall enhancement via orographic uplift of ionized aerosols, and on government programs designed to encourage revegetation of degraded farming land. 

  • Honorary Professorial Fellow, University of Wollongong, 2019 - current
  • Leverhulme Professor of Social Statistics, University of Southampton, 1995-2002
  • Head, Department of Social Statistics, University of Southampton, 1999-2002
  • Director, Southampton Statistical Sciences Research Institute, 2003-2006
  • New Zealand Statistical Association Visiting Lecturer, 2008
  • Simon Visiting Professor, University of Manchester, 2009
  • Associate Editor for various international journals, 1995-2015, including Journal of the Royal Statistical Society (Series A and B), Journal of Official Statistics, Survey Methodology, Journal for Survey Statistics and Methodology
  • Co-Editor in Chief, International Statistical Review, 2015-2019
  • Member of Methodology Advisory Committees of the UK Office for National Statistics (2002-2005), the Australian Bureau of Statistics (2006-2016), and the Italian National Institute of Statistics (2017-2019)
  • Fellow of the American Statistical Association
  • Elected Member of the International Statistical Institute
  • President, International Association of Survey Statisticians, 2011-2013
  • International Representative, Board of the American Statistical Association, 2011-2014
  1. Dawber, J. and Chambers, R. (2019). Modelling group heterogeneity for small area estimation using M-quantiles. International Statistical Review, 87, S1, S50-S63. doi:10.1111/insr.12284.
  2. Chambers, R. and Diniz da Silva, A. (2019). Improved secondary analysis for linked data: A framework and an illustration. Journal of the Royal Statistical Society, Series A, 183, 37-59.
  3. Chambers, R., Salvati, N., Fabrizi, E. and Diniz da Silva, A. (2019) Domain estimation under informative linkage. Statistical Theory and Related Fields, DOI: 10.1080/24754269.2019.1653158
  4. Bertarelli, G., Salvati, N. and Chambers, R. (2020). Outlier robust small domain estimation via bias correction and robust bootstrapping. To appear in Statistical Methods and Applications. DOI 10.1007/s10260-020-00514-w.
  5. Salvati, N, Fabrizi, E, Ranalli, M.G. and Chambers, R. (2020). Small area estimation with linked data. To appear in Journal of the Royal Statistical Society, Series B.