Abstract

Survey data, both cross-sectional and longitudinal, now being collected by government, health and social science organizations have increasingly complex structures. Many methods of data analysis have already been developed for cross-sectional surveys. Much work remains to be done. Many newer surveys done by Statistics Canada involve longitudinal data collection. The data from both cross-sectional and longitudinal surveys are becoming increasingly available across Canada through the recently created Statistics Canada Research Data Centres.

Statistics Canada has identified a pressing need for new methodologies in view of their ongoing data collection efforts in these complex surveys. The workshop will be devoted to the discussion of newly emerging methodologies for the analysis of complex surveys. It is also intended that the workshop will bring together academics who have both methodological and subject matter research interests in complex survey data, and researchers from Statistics Canada who have either a research interest in, or are "at the front line" working with, these data on a daily basis.

Some of the themes that will be pursued include: (1) variance estimation for complex without replacement sampling designs; (2) modeling of correlated duration data from longitudinal surveys; (3) multi-level modeling of survey data; and (4) item response theory for surveys. Graduate students are encouraged to attend.

Tentative participants include:

David Binder (StatCan) Jiahua Chen (Waterloo) Michael Escobar (Toronto) Mike Hidiroglou (StatCan) Milorad Kovacevic (StatCan) Jerry Lawless (Waterloo) Wendy Lou (Toronto) Jon Rao (Carleton)

Nancy Reid (Toronto) Georgia Roberts (StatCan) Jamie Stafford (Toronto) Randy Sitter (Simon Fraser) Brajendra Sutradhar (Memorial) Roland Thomas (Carleton) Mary Thompson (Waterloo) Changbao Wu (Waterloo).

Supported by MITACS