An Application of Generalized Estimating Equations to the Data from Influenza Surveillance in Canada

• Activity Number: 34
• Type: Contributed
• Date/Time: Sunday, August 2, 2009 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Shenghai Zhang*+ and Ping Yan
• Companies: Public Health Agency of Canada and
• Keywords: GEE ; Influenza ; Survaillance ; Public health

Abstract

Influenza leads to the hospitalization of 20,000 people yearly and results in 4,000 deaths each year from flu or flu-related complication in Canada (http://www.phac-aspc.gc.ca/im/2007/index-eng.html). It imposes huge costs on society due to, for example, high levels of work absence and increased pressure on the health-care system. Especially, influenza strikes the elderly and infant population hard. Statistical models for influenza data have been used for many purposes. The aim of this study is to demonstrate aspects of modeling influenza surveillance data by using generalized estimating equations, when the purpose is monitoring of influenza. One of important aims for the influenza surveillance system is to detect changes in the influenza incidence. To do so, it is needed to develop reasonable models for predictions by using data from influenza surveillance.