Abstract
This article reports a surveillance mechanism that can be used to monitor syndromic data on respiratory syndrome. The data used for illustration are the daily counts of respiratory-syndrome visits sampled from the National Health Insurance Research Database in Taiwan. The population size is 160 000. A regression model with an autoregressive-integrated-moving-average error term is fitted to the data and then CUmulative SUM (CUSUM) residual charts are plotted to detect aberrations in the frequency of visits to a walk in clinic. Day-of-the-week, seasonal, and holiday effects are considered in the regression model. It is shown that a CUSUM residual chart can be used to detect abnormal increases in daily counts of respiratory-syndrome visits.
Additional information
Notes on contributors
Huifen Chen
Huifen Chen is a Professor in the Industrial and Systems Engineering Department at Chung-Yuan University, Taiwan. She completed her Ph.D. in Industrial Engineering at Purdue University in 1994 and master’s in Statistics at Purdue University in 1990. Her research interests include statistical process control, public health, random-vector generation, and stochastic root finding.
Chaosian Huang
Chaosian Huang received a master’s degree in Industrial and Systems Engineering from Chung-Yuan University, Taiwan, in 2009. He is currently a senior engineer in the Department of Manufacturing, Lextar Electronics Corp., Hsinchu, Taiwan.