One-Health-Research-Consulting/RVF-Multinomial-Hurdle

Repository for analysis for Farm-Level Risk Factors of Increased Abortion and Mortality in Domestic Ruminants during the 2010 Rift Valley Fever Outbreak in Central South Africa # RVF-Multinomial-Hurdle Repository for analysis for Farm-Level Risk Factors of Increased Abortion and Mortality in Domestic Ruminants during the 2010 Rift Valley Fever Outbreak in Central South Africa Abstract: (1) Background: Rift Valley fever (RVF) outbreaks in domestic ruminants have severe socio-economic impacts. Climate-based continental predictions providing early warnings to regions at risk for RVF outbreaks are not of a high enough resolution for ruminant owners to assess their individual risk. (2) Methods: We analyzed risk factors for RVF occurrence and severity at the farm-level using the number of domestic ruminant deaths and abortions reported by farmers in central South Africa during the 2010 RVF outbreaks using a Bayesian multinomial hurdle framework. (3) Results: We found strong support that the proportion of days with precipitation, the number of water sources and the proportion of goats in the herd were positively associated with increased severity of RVF (the numbers of deaths and abortions) during the 2010 RVF outbreaks. We did not find an association between any risk factors and whether RVF was reported on farms. (4) Conclusions: At the farm-level we identified risk factors of RVF severity; however there was little support for risk factors of RVF occurrence. This suggests that farmers have limited tools to assess their individual risk for the occurrence of an RVF outbreak on their farm, but can implement measures to reduce the severity of outbreaks when they arise. This repository contains the code to conduct and analyze a multinomial-hurdle model. It also contains the deidentified data for the analysis for this paper. In order to deidentify the data and be in compliance with IRB regulations, we had to remove the GPS coordinates. This means the UTM was also removed and the data cannot be used to run the model with the Gaussian process as the UTM are not available. However, the code is provided even though it cannot be run with the data in thi …