Demand estimation in the presence of stochastic trend and seasonality: The case of meat demand in the United Kingdom

If budget shares have stochastic trend or seasonality or both, then demand equations based on the assumption of deterministic trend and deterministic seasonality will be mis-specified. We test this proposition by estimating a Linearized Almost Ideal (LAI) demand system for meat demand in the United Kingdom using Harvey's structural time series methodology. We demonstrate that the model specification allowing for stochastic trend and deterministic seasonality performs best in terms of diagnostic tests and goodness of fit measures. It is also shown that the model with stochastic trend is better at out-of-sample forecasting.