Spatial regression methods to evaluate beekeeping production in the state of Rio de Janeiro

• Autor(a) principal: Tassinari,W.S.
• Data de Publicação: 2013
• Outros Autores: Lorenzon,M.C., Peixoto,E.L.
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Arquivo brasileiro de medicina veterinária e zootecnia (Online)
• Texto Completo: http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0102-09352013000200035
• topic: beekeeping productivity; spatial statistics; spatial regression models

Brazilian beekeeping has been developed from the africanization of the honeybees and its high performance launches Brazil as one of the world´s largest honey producer. The Southeastern region has an expressive position in this market (45%), but the state of Rio de Janeiro is the smallest producer, despite presenting large areas of wild vegetation for honey production. In order to analyze the honey productivity in the state of Rio de Janeiro, this research used classic and spatial regression approaches. The data used in this study comprised the responses regarding beekeeping from 1418 beekeepers distributed throughout 72 counties of this state. The best statistical fit was a semiparametric spatial model. The proposed model could be used to estimate the annual honey yield per hive in regions and to detect production factors more related to beekeeping. Honey productivity was associated with the number of hives, wild swarm collection and losses in the apiaries. This paper highlights that the beekeeping sector needs support and help to elucidate the problems plaguing beekeepers, and the inclusion of spatial effects in the regression models is a useful tool in geographical data.