Abstract
Foot-and-mouth disease (FMD) is a highly contagious viral disease that affects a variety of cloven-hoofed animals. It spreads rapidly and results in considerable economic loss for agriculture in regions where the disease occurs. The main objective of this study is to develop statistical models that will reasonably predict temporal FMD case counts in endemic regions or countries, and which will also perform well under sporadic epidemic phases that increase FMD counts beyond background endemic circumstances. We used FMD data from Iran to develop correlated data models for predicting the number of FMD cases at future times and to assess the statistical importance of risk factors for increased frequency of FMD. Model selection and validation are accomplished by using the deviance information criterion and the mean absolute prediction error.
Original language | English (US) |
---|---|
Pages (from-to) | 619-636 |
Number of pages | 18 |
Journal | Journal of the Royal Statistical Society. Series A: Statistics in Society |
Volume | 175 |
Issue number | 2 |
DOIs | |
State | Published - Apr 2012 |
Externally published | Yes |
Keywords
- Auto-regressive structure
- Bayesian method
- Foot-and-mouth disease
- Iran Veterinary Organization
- Longitudinal data
- Office Internationale des Epizooties
- Ornstein
- Random-effects model
- Threshold model
- Uhlenbeck process