Prêmio de risco de mercado variante no tempo e estrutura de erro autorregressiva para os preços do petróleo

• Autor(a) principal: Souza, Carla Gomes Costa de
• Data de Publicação: 2019
• Outros Autores: [e-mail]
• Tipo de documento: Dissertação
• Idioma: por
• Título da fonte: Biblioteca Digital de Teses e Dissertações da UERJ
• Texto Completo: http://www.bdtd.uerj.br/handle/1/18256
• topic: Commodity models; Market price of risk; Kalman filter; Oil prices; Modelos em commodities; Prêmio de risco de mercado; Filtro de Kalman; Preços do petróleo; Petróleo – Preços; Investimentos; Economia; CIENCIAS SOCIAIS APLICADAS::ECONOMIA

This Master's dissertation investigates whether considering a time-varying market price of risk (TVMPR) for oil prices improves the observed prices adjustment to smoothed ones. It compares SCHWARTZ e SMITH (2000) two and three factor models which is well established in the literature on commodity prices, with an extension proposed by BHAR e LEE (2011) that includes a time-varying market price (TVMPR) and autoregressive error structure. Additionally, it tests if considering a di erent autoregressive factor for each contract improves the t of the empirical data. The models are estimated using the Kalman filter. As a result, the best model, considering prices adherence, is the three-factor model with an autoregressive structure of errors with a diferent autoregressive factor for each contract, under the assumption of a single standard deviation for all contracts.