Lawrence McCandless, Associate professor

Last updated: Spring 2017

Contact Information
Faculty of Health Sciences (primary appointment)
Department of Statstics and Actuarial Sciences (associate member)
Simon Fraser University
Burnaby BC V5A 1S6

2014 - Present, Associate Professor, Simon Fraser Unversity
2015 - 2016, Visiting Professor, Department of Epidemiology, Biostatistics and Occupational Health, McGill University 
2008 - 2014, Assistant Professor, Simon Fraser Unversity

2007  PhD, Department of Statistics, University of British Columbia
Supervisors: Paul Gustafson and Peter Austin
2008 Postdoctoral Fellow, Department of Epidemiology and Biostatistics, Imperial College London
Supervisors: Sylvia Richardson and  Nicky Best

Research Interests
Biostatistics; Epidemiology; Bayesian inference; MCMC; Causal inference; Mediation analysis;
Longitudinal data; Missing data; Propensity scores; Meta-analysis; Survival analysis

Application areas
Reproductive and child health epidemiology, environmental epidemiology, mental health epidemiology

Collaborations & current projects
1. Analysis of environmental chemical exposures and child health outcomes in the HOME Study
With Bruce Lamphear and Joseph Braun.

2. Bayesian longitudinal data analysis with missing data in the At Home / Chez Soi randomized controlled trial
With Joan Hu and Julian Somers  

Service to academic community
Associate editor of Statistics in Medicine (2013-)
Statistical Society of Canada (SSC): Board of directors (2013-2015); Student travel awards chair (2014-2017)

Funding as principal investigator for biostatistics research
CIHR Catalyst Grant, "Biostatistical methods for estimating the cumulative impact of environmental contaminant exposures on preterm birth", 2016-2018, $198,330
NSERC Discovery Grant, "Bayesian bias modelling for causal inference in statistics", 2015-2020, $80,000
CIHR Planning Grant, "Prenatal exposure to environmental contaminants and fetal growth: How to account for multiplicity when testing multiple statistical hypotheses?", 2015, $12,500
NSERC Discovery Grant, "Bayesian bias modelling for analysis of observational data", 2009-2015, $65,000
Selected Invited Conference Talks
Sensitivity analysis for several unmeasured confounders. ACIC 2015 Philedelphia
A Bayesian perspective on unmeasured confounding in large administrative databases.   ISCB 2014 Vienna
Causal inference in epidemiology using Bayesian methods: The example of meta-analysis of statins and fracture risk.  JSM 2013 Montreal
Graduate Students
Janice Mung-Yi Hu (PhD 2017-present)
Harry Zhang (PhD 2017-present)
Brendan Bernardo (MSc 2016-present)
Tian Li (MSc 2015-present)
Janice Mung-Yi Hu (MSc 2014-2016)
Meghan Woods (MPH 2014-2016)
Emily Rempel (MSc 2012-2014)
Selected Publications in Biostatistics and Epidemiology
McCandless LC, Gustafson P. (2017) A comparison of Bayesian and Monte Carlo sensitivity analysis for unmeasured confounding. Statistics in Medicine (in press).
McCandless LC, Patterson ML, Currie LB, Moniruzzaman A, Somers JM. (2016) Bayesian estimation of the size of a street-dwelling homeless population. Journal of Modern Applied Statistical Methods 15:1 (25 pages).
McCandless LC, Stewart LC, Rempel ES, Venners SA, Somers JM. (2015) Criminal justice system contact and mortality among offenders with mental illness in British Columbia: an assessment of mediation.   Journal of Epidemiology and Community Health. 69:460-6.
Gustafson P, McCandless LC. (2014) Commentary: Priors, Parameters, and Probability: A Bayesian Perspective on Sensitivity Analysis.  Epidemiology 25:910-12.
Lash TL, Fox MP, MacLehose RF, Maldonado G, McCandless LC, Greenland S (2014) Good practices for quantitative bias analysis.  International Journal of Epidemiology 43:1969-85.
McCandless LC. (2013) Statins and fracture risk: Can we quantify the healthy-user effect?  Epidemiology 24:743-52. Runner up for Rothman Prize for best paper published in Epidemiology in 2013.
McCandless LC, Richardson S, Best N. (2012) Adjustment for missing confounders using external validation data and propensity scores. Journal of the American Statistical Association 107:40-51.
McCandless LC, Gustafson P, Levy AR, Richardson S. (2012) Hierarchical priors for bias parameters in Bayesian sensitivity analysis for unmeasured confounding. Statistics in Medicine 31:383-96. 
McCandless LC. (2012) Meta-analysis of observational studies with unmeasured confounders. The International Journal of Biostatistics. 8:2, Article 5 (33 pages).
McCandless LC. (2012) Discussion of " Bayesian effect estimation accounting for adjustment uncertainty," by Wang C, Parmigiani and Dominici F. Biometrics 68, 678-80.
Gustafson P, McCandless LC, Levy AR and S. Richardson (2010) Simplified Bayesian Sensitivity Analysis for Mismeasured and Unobserved Confounders. Biometrics 4:1129-37.

Gustafson P, McCandless LC (2010). Probabilistic Approaches to Better Quantifying the Results of Epidemiologic Studies. International Journal of Environmental Research and Public Health 7:1520-39.
McCandless LC, Douglas IJ, Evans SJ, Smeeth L (2010). Cutting Feedback in Bayesian Regression Adjustment for the Propensity Score. The International Journal of Biostatistics 6:2, 16. (24 pages)

McCandless LC, Gustafson P, Austin PC. (2009) Bayesian propensity score analysis for observational data. Statistics in Medicine 15:94-112.

McCandless LC, Gustafson P, Levy AR (2008). A sensitivity analysis using information about measured confounders yielded improved assessments of uncertainty from unmeasured confounding. Journal of Clinical Epidemiology 61:247-55.
McCandless LC, Gustafson P, Levy AR. (2007) Bayesian sensitivity analysis for unmeasured confounding in observational studies. Statistics in Medicine. 26:2331--47.

Gustafson P, McCandless LC (2005). Comment on Multiple-bias modelling for analysis of observational data." by Sander Greenland. Journal of the Royal Statistical Society, Series A 168:267-306.
Gustafson P, Hossain S, McCandless LC. (2005) Innovative Bayesian methods for biostatistics and epidemiology. In Handbook of Statistics, Vol. 25 on Bayesian Statistics (D. Dey and C.R. Rao, Eds.), Elsevier, pp763-92.