Dr George Leckie

Reader in Social Statistics


  • Multilevel modelling
  • Longitudinal data analysis
  • Dyadic data analysis
  • Value-added models
  • Applications of social statistics in education


I am a Reader in Social Statistics and Co-Director of the Centre for Multilevel Modelling (CMM) at the School of Education, University of Bristol, UK. I am also an Associate Editor of the Journal of the Royal Statistical Society, Series A. I am currently principal investigator on an ESRC grant and am a co-investigator on an MRC grant and on a Swedish Research Council grant.

Previously, I held research positions at the Centre for Market and Public Organisation, University of Bristol. I held for several years a status-only Associate Professor position at the Graduate Department of Applied Psychology and Human Development, University of Toronto, Canada. I have also been a visiting fellow at Cornell University, Queensland University of Technology, UCL Institute of Education London, University of York, and VU University Amsterdam.

I have held an ESRC Future Research Leaders grant and have previously been a co-investigator on several other ESRC grants. My research has been published in various international journals, including: Journal of the Royal Statistical Society, Series A; Journal of Educational and Behavioral Statistics; Journal of Educational Measurement; and Journal of Statistical Software. I was awarded the Wood Medal in the Royal Statistical Society's 2017 honours for my contributions to Social Statistics.

I have taught over 40 multilevel modelling short courses across UK, Europe, Australia and US.

Research interests

My methodological interests are in the development, application and dissemination of multilevel and other latent variable models to analyse educational and other social science data. Particular areas of interest include multilevel analysis of non-hierarchical data (e.g., cross-classified models, multiple membership models), longitudinal data analysis (e.g., growth-curve models, latent class growth analysis, growth mixture models, dynamic models), variance function models (e.g., mixed-effects location scale models), and dyadic data analysis (e.g., actor-partner interdependence model, social relations model).

My substantive interests in educational research include: statistical properties of school performance indicators and their associated publication in league tables; value-added models (VAMs) for estimating school and teacher effects on student achievement; statistical modelling of rater effects on test scoring; and quantifying neighbourhood, school and family effects on child outcomes. I also frequently collaborate with co-authors working in other disciplines, including: anthropology, dentistry, economics, epidemiology, management, psychology, social policy, and sociology.

My statistical software interests are in developing runmlwin and runmixregls, commands to fit multilevel models in the MLwiN and the MIXREGLS software from within Stata.

Research grants

My grants as Principal Investigator sum to £650,000 while my grants as Co-Investigator sum to £5 million. I have been grant funded 40% of my time over the ten year period 2010/11 through 2019/20. 

Current grants:

  • 2018-2021 How should we measure school performance and hold schools accountable? A study of competing statistical methods and how they compare to Progress 8, Principal Investigator.
  • 2018-2021 Multilevel Analyses of Individual Heterogeneity: innovative concepts and methodological approaches in Public Health and Social Epidemiology, Swedish Research Council, Co-Investigator
  • 2016-2019 Modelling within-individual variation in repeated continuous exposures, MRC, Co-Investigator

Past grants:


At undergraduate level, I teach sessions on Year 1 Convincing Stories and I am Unit Director Year 2 Educational Statistics.

At masters level, I am a Unit Tutor on Statistics in Education, teaching half the unit. I am Unit Director on Multivariate Statistical Methods in Education and also teach half of this unit. I am Unit Tutor teaching one-third of MSc Mathematics and Programming Skills. I am also pathway co-ordinator for the MSc in Education, personal tutor to 20 students, and supervise masters dissertations.

I also run two three-day fee-paying short courses for external academic researchers and PhD students:

I  supervise seven PhD students (five of whom are ESRC funded) applying multilevel modelling to address substantive research questions in the social sciences.

At EdD level, I supervise one EdD Hong Kong student.

I have also taught over 40 other multilevel modelling short courses across UK, Europe, Australia and US, including: Belfast, Brisbane, Bristol, Brussels, Cincinnati, Dublin (Centre for Longitudinal Studies in Ireland), Dublin (Eurofound), Dublin (Royal College of Surgeons, Ireland), Dublin (University College Dublin), Essex, Ghent, Giessen, Groningen, Malmo, Oxford, London (Royal Statistical Society), Paris (Organisation for Economic Cooperation and Development), Southampton, Sydney, Tuebingen, and Zurich.

I author an extensive set of multilevel modelling training materials for the LEMMA Multilevel Modelling Online Course.

Professional activities

I play an active role in the Royal Statistical Society. I am currently an Associate Editor of the Journal of the Royal Statistical Society, Series A. Since 2008, I have taught (with Professor Harvey Goldstein) an annual two-day course on multilevel modelling for the society's short-course programme. Previously, I sat on the Social Statistics Section committee and the Professional Development Centre committee. I have published in the society's Series A (Statistics in Society) journal and Significance magazine and have peer reviewed for Series A and Series C. I have presented regularly at the society's annual conference and at various society local group meetings.

I have worked or advised on a range of government and other external projects: Bulgarian Ministry of Education and Science; Catholic University of Portugal; Colombian Evaluation Institute; Higher Education Academy; Home Office; King’s College London (MRC grant); National Assessment Agency; National Center for Educational Achievement (NCEA) / ACT testing company; National Institute for Certified Educational Measurements, Slovak Republic; Pearson Education; RAND Europe; The Times and Sunday Times Data Analysis Team; University of Birmingham (DoH grant); University of Oxford (Ofqual grant); University of the West of England (Unilever grant: Dove); World Bank.

Other professional activities:

  • 2017–          Associate Editor of the Journal of the Royal Statistical Society, Series A.
  • 2017–          Member of HEFCE Learning Gain Expert Group
  • 2017            ESRC commissioning panel for NCRM Phase II Call
  • 2015            Member of Sutton Trust Evaluation Framework Advisory group 
  • 2014–          Co-Organiser of DfE funded NPD User Group annual meetings 
  • 2013–2015   Member of the Royal Statistical Society’s Social Statistics Section committee 
  • 2012–          Academic member of the ESRC Peer Review College
  • 2011–2015   Member of the Royal Statistical Society’s Professional Development Centre steering committee
  • 2009-           Fellow of the Royal Statistical Society

Journal articles

  1. Browne, D. T., Wade, M, Plamondon, A., Leckie, G., Perlman, M., Madigan, S., & Jenkins, J. Child and contextual effects in the emergence of differential maternal sensitivity across siblings. Developmental Psychology. Forthcoming.
  2. Brunton-Smith, I., Sturgis, P., & Leckie, G. How collective is collective efficacy? The importance of consensus in judgments about community cohesion and willingness to. Criminology. Forthcoming.
  3. Goldstein, H., Leckie, G., Charlton, C., Tilling, K., & Browne, W. J. Multilevel growth curve models that incorporate a random coefficient model for the level 1 variance function. Statistical Methods in Medical Research. Forthcoming.
  4. Lampert, C, Kim, M., Hubbard, T., Roy, R., & Leckie, G. Fearlessly swimming upstream to risky waters: The role of geographic entry in innovation. Journal of Management Studies. Forthcoming.
  5. Leckie, G. Avoiding bias when estimating the consistency and stability of value-added school effects using multilevel models. Journal of Educational and Behavioral Statistics. Forthcoming.
  6. Sandhu, S. S. and Leckie, G. Diurnal variation in orthodontic pain: clinical implications and pharmacological management. Seminars in Orthodontics. Forthcoming.
  7. Austin, P. C., Stryhn, H., Leckie, G., & Merlo, J. (2018). Measures of clustering and heterogeneity in multilevel Poisson regression analyses of rates/count dataStatistics in Medicine, 37, 572-589.
  8. Axelsson Fisk, S., Mulinari, S., Wemrell, M., Leckie, G., Perez Vicente, R., Merlo, J. (2018). Chronic Obstructive Pulmonary Disease in Sweden: An intersectional multilevel analysis of individual heterogeneity and discriminatory accuracy. Social Science and Medicine: Population Health, 4, 334-346.
  9. Baird, J.-A., Meadows, M, Caro, D., and Leckie, G. (2017). Rater Accuracy and Training Group Effects in Expert and Supervisor-Based Monitoring Systems. Assessment in Education: Principles, Policy & Practice, 24, 44-59. 
  10. Browne, D. T., Kumar, A., Puente-Duran, S., Georgiades, K., Leckie, G., & Jenkins, J. (2017). Emotional problems among recent immigrants and parenting status: Findings from a national longitudinal study of immigrants in Canada. PloS one, 12(4), 1-14.
  11. Brunton-Smith, I., Sturgis, P., Leckie, G. (2017). Detecting, and understanding interviewer effects on survey data using a cross-classified mixed-effects location scale model. Journal of the Royal Statistical Society: Series A (Statistics in Society), 180, 2, 551-568.
  12. von Hinke Kessler Scholder, S., & Leckie, G. Protecting Calorie Intakes against Income ShocksJournal of Economic Behavior and Organization, 141, 210-232.
  13. Leckie, G., & Goldstein, H. (2017). The evolution of school league tables in England 1992-2016: ‘contextual value-added’, ‘expected progress’ and ‘progress 8’British Educational Research Journal, 43, 193-212.
  14. Steele F., Clarke, P., Leckie, G., Allan, J., & Johnston, D. (2017). Multilevel structural equation models for longitudinal data where predictors are measured more frequently than outcomes: An application to the effects of stress on the cognitive function of nurses. Journal of the Royal Statistical Society: Series A (Statistics in Society), 180, 263-283.
  15. Browne, D.T., Leckie, G., Prime, H., Perlman, M., & Jenkins, J. (2016). Observed sensitivity during family interactions and cumulative risk: A study of multiple dyads per family. Developmental Psychology, 52, 1128-1138.
  16. Diedrichs, P. C., Atkinson, M. J. Garbett, K. M., Williamson, H., Halliwell, E., Rumsey, N. Leckie, G., Sibley, C. G., & Barlow, F. K. (2016). Randomised controlled trial of an online mother-daughter body image and well-being interventionHealth Psychology, 35, 996-1006. DOI: 10.1037/hea0000361.
  17. Goldstein, H. and Leckie, G. Trends in examination performance and exposure to standardised tests in England and Wales. (2016). British Educational Research Journal, 42, 367-375.
  18. Merlo, J., Wagner, P., Ghith, N., & Leckie, G. (2016). An original stepwise multilevel logistic regression analysis of discriminatory accuracy: the case of neighbourhoods and health. PLoS ONE, 11(4), 1-31.
  19. Sandhu, S. and Leckie, G. (2016). Orthodontic pain trajectories in adolescents: how different are the individuals? American Journal of Orthodontics & Dentofacial Orthopedics, 149, 491-500.
  20. Zhang, Z., Parker, R., Charlton, C.,  Leckie, G., and Browne, W.J. R2MLwiN - A program to run the MLwiN multilevel modelling software from within RJournal of Statistical Software, 72, 10, 1-43.
  21. Koster, J., Leckie, G., Miller, A., and Hames, R. (2015). Multilevel modeling analysis of dyadic network data with an application to Ye’kwana food sharingAmerican Journal of Physical Anthropology, 157, 507-512.
  22. Perlman, M., Lyon Amos, M., Leckie, G., Steele, F. and Jenkins, J. Capturing the temporal sequence of interaction in young siblings. PLoS ONE, 10(5), 1-21.
  23. Leckie, G. and Goldstein, H. (2015). A multilevel modelling approach to measuring changing patterns of ethnic composition and segregation among London secondary schools, 2001-2010. Journal of the Royal Statistical Society: Series A (Statistics in Society), 178, 405-424.
  24. Koster, J. and Leckie, G. (2014). Food sharing networks in lowland Nicaragua: An application of the social relations model to count data. Social Networks, 38, 100-110.
  25. Leckie, G. (2014). runmixregls - A program to run the MIXREGLS mixed-effects location scale software from within Stata. Journal of Statistical Software, 59 (Code Snippet 2), 1-41.
  26. Leckie, G., French, R., Charlton, C., and Browne, W. (2014). Modeling heterogeneous variance-covariance components in two-level models. Journal of Educational and Behavioral Statistics, 39, 307-332.
  27. Zammit, S., Gunnell, D., Lewis, G., Leckie, G., Dalman, C. and Allebeck, P. (2014). Individual and area level influence on suicide risk: a multilevel longitudinal study of Swedish school children. Psychological Medicine, 44, 267–277. 
  28. Leckie, G. and Charlton, C. (2013). runmlwin - A program to run the MLwiN multilevel modelling software from within Stata. Journal of Statistical Software, 52 (11),1-40.
  29. Jenkins, J., Rasbash, J., Leckie, G., Gass, K. and Dunn, J. (2012). The role of maternal factors in sibling relationship quality: a multilevel study of multiple dyads per family. Journal of Child Psychology and Psychiatry, 53, 622-629.
  30. Leckie, G., Pillinger, R., Jones, K. and Goldstein, H. (2012). Multilevel modelling of social segregation. Journal of Educational and Behavioral Statistics, 37, 3-30.
  31. Cheung, C., Goodman, D., Leckie, G. and Jenkins, J. (2011). Understanding contextual effects on externalizing behaviors in children in out-of-home care: Influence of workers and foster families. Children and Youth Services Review, 33, 2050-2060.
  32. Leckie, G. and Baird, J.-A. (2011). Rater effects on essay scoring: A multilevel analysis of severity drift, central tendency and rater experience. Journal of Educational Measurement, 48, 399-418.
  33. Leckie, G. and Goldstein, H. (2011). A note on “The limitations of using school league tables to inform school choice”. Journal of the Royal Statistical Society: Series A (Statistics in Society), 174, 833-836.
  34. Leckie, G. and Goldstein, H. (2011). Understanding uncertainty in school league tables. Fiscal Studies, 32, 207-224.
  35. Rasbash, J., Leckie, G., Pillinger, R. and Jenkins, J. (2010). Children's educational progress: partitioning family, school and area effects, Journal of the Royal Statistical Society: Series A (Statistics in Society), 173, 1-26.
  36. Leckie, G. (2009). The complexity of school and neighbourhood effects and movements of pupils on school differences in models of educational achievement, Journal of the Royal Statistical Society: Series A (Statistics in Society), 172, 537-554.
  37. Leckie, G. and Goldstein, H. (2009). The limitations of using school league tables to inform school choice, Journal of the Royal Statistical Society: Series A (Statistics in Society), 172, 835-851.
  38. Propper, C., Burgess, S., Bolster, A., Leckie, G., Jones, K. and Johnston, R. (2007). The impact of neighbourhood on the income and mental health of British social renters, Urban Studies, 44, 393-415.
  39. Propper, C., Damiani, M., Leckie, G. and Dixon, J. (2007). Impact of patients’ socioeconomic status on the distance travelled for hospital admission in the English National Health Service, Journal of Health Service Research & Policy, 12, 153-159.

Other publications

  1. Browne, D. T., Leckie, G., & Jenkins, J. M.  (2018). Understanding Couples and Family Dynamics through Dyadic Methodology. In Fiese, B., Deater-Deckard, K. Celano, M., Jouriles, E., & Whisman, M. (Ed.) APA Handbook of Contemporary Family Psychology, X, Chapter X, X-X. Forthcoming.
  2. Leckie, G. and Goldstein, H. (2018). Monitoring school performance using value-added and value-table models: Lessons from the UK. In Perna, C., Pratesi, M., & Ruiz-Gazen, A. (Eds.) Studies in Theoretical and Applied Statistics, Springer, Chapter 23, X-X.
  3. Leckie, G. (2014). Cross-classified hierarchical linear modeling. In: Michalos A. C. (Ed.). Encyclopedia of Quality of Life and Well-Being Research. Springer, Dordrecht, Netherlands: Springer, pp 1359-1363.
  4. Leckie, G. (2014). Multiple membership models. In: Michalos A. C. (Ed.). Encyclopedia of Quality of Life and Well-Being Research. Springer, Dordrecht, Netherlands: Springer, pp 4206-4210.
  5. Leckie, G. (2012) Cross-classified multilevel models using Stata: How important are schools and neighbourhoods for students’ educational attainment? In Garson, D. (Ed.) Hierarchical Linear Modeling: Guide and Applications. Sage, 311-332.
  6. Propper, C. and Leckie, G. (2011) Increasing competition between providers in health care markets: The economic evidence. In Smith, P. and Glied, S. (Eds.) Oxford Handbook of Health Economics. Oxford, Oxford University Press, 671-687.
  7. Leckie, G., Pillinger, R., Jenkins, J. and Rasbash, J. (2010) School, family, neighbourhood: which is most important to a child's education? Significance, 67-72.
  8. Goldstein, H. and Leckie, G. (2008) School league tables: What can they really tell us? Significance, 5, 67-69.
Image of George Leckie
Dr George Leckie
Edit this page