Dalla Lana School of Public Health

Faculty Member

Eleanor Pullenayegum

Research Interests

I help ensure that healthcare is based on high-quality evidence by:

• developing new statistical methods to handle the complex data that often arise in medical research
• working with colleagues to choose the most appropriate design and analysis for research
• training graduate students in statistical methods

I have several projects in these areas that are suitable for students considering Master’s or Doctoral work; see the instructions here to inquire about openings.

Education & Training History

PhD, Biostatistics, University of Toronto
Certificate of Advanced Studies in Mathematics, University of Cambridge
BA, Mathematics, University of Cambridge

Other Affiliations

Senior Scientist, The Hospital for Sick Children

Primary Teaching Responsibilities

Statistical Analysis of Health Economic Data (co-taught with Dr Anna Heath)

Professional Summary & Appointments

• Senior Scientist, Child Health Evaluative Sciences, Hospital for Sick Children (2016-present)
• Scientist, Child Health Evaluative Sciences, Hospital for Sick Children (2013-2016)
• Associate Professor, Dalla Lana School of Public Health, University of Toronto (2013-present)
• Biostatistician, St Joseph’s Healthcare Hamilton (2007-2013)
• Associate Professor, Depeartment of Clinical Epidemiology & Biostatistics, McMaster University (2012-2013)
• Assistant Professor, Depeartment of Clinical Epidemiology & Biostatistics, McMaster University (2007-2012)
• Postdoctoral Fellow, Department of Statistics and Actuarial Science, University of Waterloo (2006)
• Medical Statistician, Centre for Applied Medical Statistics, Department of Public Health and Primary Care, University of Cambridge (2000-2002))

Honours & Awards

CIHR New Investigator Award (2012-2018)
Young Investigator Award of the Section on Teaching Statistics in the Health Sciences, American Statistical Association (2008)
Schuldham Plate, Gonville & Caius College, University of Cambridge (1999)

Current Research Projects

• Methodology for irregularly observed longitudinal data

Longitudinal data are useful for understanding how disease evolves over time. Often longitudinal data can be collected through clinic based cohorts in which patients are enrolled in the cohort at diagnosis, followed up as medically necessary, and data are gathered through a chart review. This is an efficient and low cost approach to data collection. However, since patients tend to visit more often when unwell, this can lead to overestimation of the burden of disease unless accounted for appropriately. I develop analytic methods to handle the informative nature of the visit process.

• Methodology for health utilities

Health utilities are used in economic evaluations to help assess cost-effectiveness of treatments, and so ultimately contribute to decisions on which treatments should be publicly funded. I am interested in measurement of health utilities, in particular a) correctly quantifying the statistical uncertainty in these measurements, and b) reducing the extent of uncertainty. This is important as it reduces the risk of funding treatments that are not cost-effective, this enabling better use of limited resources.

Graduate Students

If you are a prospective doctoral or master’s student interested in studying under my supervision, please visit my lab’s webpage where you will find detailed instructions on preparation and setting up a meeting.

PhD

• Naomi Chang (2021-present)
• Alexandra Bushby (2021-present)
• Rose Garrett (2018-present)
• Kuan Liu (2015-2021) Bayesian causal inference with longitudinal data
• Shahriar Shams (2014-2021) Quantifying and Reducing Uncertainty in the Measurement of Health Utilities
• Armend Lokku (2014-2020) Summary Measures for Quantifying the Extent of Visit Irregularity in Longitudinal Data
• Kelvin Chan (2012-2016) Addressing Uncertainties in Health Utilities
• Qing Guo (2008-2013) Sample size calculations in fMRI studies

MSc

• Xiawen Zhang (2021-present)
• Di Shan (2021-present)
• Menelaos Konstantinidis (2021-present)

Representative Publications

* indicates a student under my supervision

See here for a more complete list.

Longitudinal data

Pullenayegum EM, Birken C, Maguire J; TARGet Kids! Collaboration, Clustered longitudinal data subject to irregular observation. Stat Methods Med Res.2021 Apr;30(4):1081-1100.

Lokku A*, Birken CS, Maguire JL, Pullenayegum EM; TARGet Kids! Collaboration. Quantifying the extent of visit irregularity in longitudinal data. Int J Biostat. 2021 Aug 16

Pullenayegum EM. Meeting the Assumptions of Inverse-Intensity Weighting for Longitudinal Data Subject to Irregular Follow-Up: Suggestions for the Design and Analysis of Clinic-Based Cohort Studies. Epidemiologic Methods 2020 9 (1)

Liu K*, Saarela O, Feldman BM, Pullenayegum E. Estimation of causal effects with repeatedly measured outcomes in a Bayesian framework. Stat Methods Med Res. 2020 Sep;29(9):2507-2519.

Pullenayegum EM, Lim LS. Longitudinal data subject to irregular observation: A review of methods with a focus on visit processes, assumptions, and study design. Stat Methods Med Res. 2016 Dec;25(6):2992-3014.

Pullenayegum EM. Multiple outputation for the analysis of longitudinal data subject to irregular observation. Stat Med. 2015 Dec 13. doi: 10.1002/sim.6829. [Epub ahead of print] PubMed PMID: 26661690.

Pullenayegum EM, Feldman BM. Doubly robust estimation, optimally truncated inverse-intensity weighting and increment-based methods for the analysis of irregularly observed longitudinal data. Statistics in Medicine. 2013 Mar 15; 32(6):1054-72. doi:10.1002/sim.5640.

Health Utilities

Waudby-Smith I*, Pickard AS, Xie F, Pullenayegum EM. Using Both Time Tradeoff and Discrete Choice Experiments in Valuing the EQ-5D: Impact of Model Misspecification on Value Sets. Med Decis Making. 2020 May;40(4):483-497

Shams S*, Pullenayegum E. Design and sample size considerations for valuation studies of multi-attribute utility instruments. Stat Med. 2020 Oct 15;39(23):3074-3104

Chan KKW, Pullenayegum EM. The Theoretical Relationship between Sample Size and Expected Predictive Precision for EQ-5D Valuation Studies: A Mathematical Exploration and Simulation Study. Medical Decision Making 2020 40 (3), 339-347

Pullenayegum EM, Pickard AS, Xie F. Latent Class Models Reveal Poor Agreement between Discrete Choice and Time Trade-off Preferences. Medical Decision Making 2019 39 (4), 421-436

Shams S*, Pullenayegum EM. Reducing Uncertainty in EQ-5D Value Sets: The Role of Spatial Correlation. Medical Decision Making. 2019 Feb; 39(2):91-99. doi: 10.1177/0272989X18821368. Epub 2019 Jan 24. PubMed PMID: 30678526

Chan KKW*, Xie F, Willan AR, Pullenayegum EM. Conducting EQ-5D Valuation Studies in Resource-Constrained Countries: The Potential Use of Shrinkage Estimators to Reduce Sample Size. Medical Decision Making. 2017 Aug 1:272989X17725748.doi: 10.1177/0272989X17725748. [Epub ahead of print] PubMed PMID: 28823185

Chan KKW^*, Xie F, Willan AR, Pullenayegum EM. Underestimation of Variance of Predicted Health Utilities Derived from Multi-Attribute Utility Instruments: The Use of Multiple Imputation as a Potential Solution. Medical Decision Making. 2017 Apr;37(3):262-272. doi: 10.1177/0272989X16650181. Epub 2016 Jul 10

Pullenayegum EM, Chan KKW*, Xie F. Quantifying Parameter Uncertainty in EQ-5D-3L Value Sets and Its Impact on Studies That Use the EQ-5D-3L to Measure Health Utility: A Bayesian Approach. Med Decis Making. 2016 Feb;36(2):223-33. doi: 10.1177/0272989X15591966. Epub 2015 Jul 2. PubMed PMID: 26139449.

Chan KKW^*, Gupta M, Willan A, Pullenayegum EM. Underestimation of Uncertainties in Health Utilities derived from Mapping Algorithms involving Health Related Quality of Life Measures: Statistical Explanations and Potential Remedies. Medical Decision Making. 2014 Oct; 34(7):863-72. doi: 10.1177/0272989X13517750. Epub 2014 Jan 9. PubMed PMID: 24407513.

Knowledge Translation

Pullenayegum EM, Platt RW, Barwick M, Feldman BM, Offringa M, Thabane L. Knowledge translation in biostatistics: a survey of current practices, preferences, and barriers to the dissemination and uptake of new statistical methods. Stat Med. 2016 Mar 15;35(6):805-18. doi: 10.1002/sim.6633. Epub 2015 Aug 25. PubMed PMID: 26307183.

Software

R package IrregLong for analysing longitudinal data subject to irregular observation