Hyak Mortality Monitoring System: Innovative Sampling and Estimation Methods

Samuel J. Clark, University of Washington
Jon Wakefield, University of Washington
Tyler McCormick, University of Washington

We propose a new statistical framework for health/population data where traditional data are scarce. HYAK combines sampling and longitudinal surveillance to create a cheap, accurate, sustainable monitoring platform. HYAK's basic components: 1. DATA MELDING: a sampling and surveillance component including: (1) longitudinal, prospectively linked data from health and demographic surveillance systems, (2) data from linked sample surveys in large areas surrounding the surveillance sites using highly efficient informed sampling; 2. CAUSE OF DEATH: verbal autopsy to characterize the distribution of deaths by cause; 3. SES: measurement of socioeconomic status in order to characterize poverty and wealth. We conduct a simulation study of the informed sampling component of HYAK. Compared to traditionally cluster sampling, HYAK's informed sampling captures more deaths and produces estimates of both death counts and mortality rates that have lower variance and small bias.