| الوصف: |
Currently, Value at Risk (VaR) is one of the most important measures of risk. It is the percentile of the profit and loss distribution of a portfolio over a specified period. Through the rapid development in the world, we can negotiate portfolio risk and loss via the dynamic VaR method. In this paper, we propose a stochastic volatility with Student-t errors (SV-t) model that maximizes the expected returns subject to a VaR constraint to depict the risk of heterodasticity and leptokurtic accurately. We also propose the most efficient and best method, the Markov Chain Monte Carlo (MCMC) estimation method. Using spot price data from the Chicago Board of Trade (CBOT), we empirically find that there are more integrated and skewed data because a growing number of the multinational powerful world markets exchanges have emerged. In this paper, we also find a leverage effect, asymmetric heavy-tailed errors, and jump components exist in the returns of the corn and soybean markets. Corn in particular is empirically found to have a larger leverage effect than soybeans, indicating that the corn risk is greater than soybean risk to avoid increased damaged and asymmetric information Therefore, when shocks influence these markets, the corn and soybean markets are found to serially outperform each other in terms of the leverage effect, at least in the short term. Until now few papers have discussed these aspects and have found different derivative effects of fluctuations between corn and soybean commodity markets in agriculture development. To the best of my knowledge, no article has discussed volatility and risk by the SV-t model and applied it to the VaR in time series between corn and soybean agricultural commodity markets. This paper is less restrictive and more realistic, which could lead to a more asymmetric information response through agricultural economic activities. However, both corn and soybean price VaR values are more than 5%, indicating possible underestimates of returns from portfolio operations. Therefore, we ... |