The Use of a Univariate Times Series Model to Forecast the Behavior of Pork Meat Production in Baja California, Mexico

Using the monthly data of tons of pork meat produced in the State of Baja California, Mexico between January 2003 to December 2010 and based on the Box- Jenkins methodology anautorregresive moving average (ARMA) model was constructed to represent the behavior of the local production. Using the correlogram and the Dickey-Fuller test on the time series no evidence of non stationary behavior was found, the process was continued with the validation of a group of autorregresive AR (p) and moving average MA(q) combinations until two were selected: a ARMA with a 12 months lag for the autorregresive and moving average processes and a AR also lagged twelve months. To establish which model better represented the data generating process, the regression coefficients together with the Akaike and Schwarz criteria were used, and to determine the presence of autocorrelation, the correlograms were inspected and a Ljung-Box test was applied, based on this results the ARMA model was selected, it was also found that the same model had better forecasting characteristics that the AR model. It was concluded that this type of time series model may be considered as a useful tool to provide short term forecasts for the production of pork meat.