Grace Y. Yi


Grace Y. YiUniversity Research Chair

Contact Information:
Grace Yi

Research interests

Professor Yi's research interests focus on developing statistical methodology for event history analysis in fields such as chronic disease, clinical trials, and epidemiology. Many of the problems are motivated by challenges arising in health research, but the developed methods have a bearing on many diverse fields including demography, engineering, sociology, and survey research.

Standard statistical inference methods often require associated variables be "perfectly" measured. However, in reality, collected data are usually far from "perfect". Longitudinal studies, for instance, are commonly designed to collect data on every individual in the studies at each assessment, but missing observations frequently arise due to various reasons. Measurement error, on the other hand, is another typical feature associated with data. These features present considerable challenges in developing valid inferential procedures. Professor Yi's recent research has been particularly centering on various problems concerning missing data or measurement error in variables.


  • 2000 PhD in Statistics, University of Toronto, Canada
  • 1996 MA in Statistics, York University, Canada
  • 1989 MSc in Mathematics, Sichuan University, P.R.China
  • 1986 BSc in Mathematics, Sichuan University, P.R.China

Professor Yi received her PhD in statistics in 2000 from the University of Toronto, and then joined the University of Waterloo as a postdoctoral fellow (2000-2001). She was assistant professor (2001-2004), associate professor (2004-2010), and now is full professor (2010-present). Professor Yi is the 2010 winner of the CRM-SSC Prize, an honor awarded in recognition of a statistical scientist's professional accomplishments in research during the first 15 years after having received a doctorate. She was a recipient of the prestigious University Faculty Award granted by the Natural Sciences and Engineering Research Council of Canada (NSERC). She serves as an associate editor for The Canadian Statistics Journal and The Journal of Applied Probability and Statistics. She is a member of the American Statistical Association, the Statistical Society of Canada, the Eastern North American Region of the Biometrics Society, and the International Chinese Statistical Association.

Selected publications

  • G. Y. Yi and J. F. Lawless (2012). Likelihood-Based and Marginal Inference Methods for Recurrent Event Data with Covariate Measurement Error. To appear in The Canadian Journal of Statistics.
  • G. Y. Yi, Y. Ma, and R. J. Carroll (2012). A Functional Generalized Method of Moments Approach for Longitudinal Studies With Missing Responses and Covariate Measurement Error. Biometrika, 99, 151-165.
  • Z. Chen, G. Y. Yi, and C. Wu (2011). Marginal Methods for Correlated Binary Data with Misclassified Responses. Biometrika, 98, 647-662.
  • G. Y. Yi, W. Liu and L. Wu (2011). Simultaneous Inference and Bias Analysis for Longitudinal Data with Covariate Measurement Error and Missing Responses. Biometrics, 67, 67-75.
  • W. He and G. Y. Yi (2011). A Pairwise Likelihood Method for Correlated Binary Data with/without Missing Observations under Generalized Partially Linear Single-Index Models. Statistica Sinica, 21, 207-229.
  • B. Lindsay, G. Y. Yi, and J. Sun (2011). Issues and Strategies in the Selection of Composite Likelihoods. Statistica Sinica, 21, 71-105.
  • G. Y. Yi and N. Reid (2010). A Note on Mis-specified Estimating Functions. Statistica Sinica, 20, 1749-1769.
  • D. A. S Fraser, N. Reid, E. Marras, and G. Y. Yi (2010). Default Priors for Bayesian and Frequentist Inference. The Journal of Royal Statistical Society, Series B, 72, 631-654.
  • B. Chen, G. Y. Yi, and R. Cook (2010). Weighted Generalized Estimating Functions for Incomplete Longitudinal Response and Covariate Data. Journal of the American Statistical Association, 105, 336-353.
  • G. Y. Yi (2008). A Simulation-Based Marginal Method for Longitudinal Data with Drop-Out and Mismeasured Covariates. Biostatistics, 9, 501-512.
University of Waterloo
Contact information: