Methods for forecasting intermittent demand are compared using a large data-set from the UK Royal Air Force (RAF). Several important results are found. First, we show that the traditional per period forecast error measures are not appropriate for intermittent demand, even though they are consistently used in the literature. Second, by comparing target service levels to achieved service levels when inventory decisions are based on demand forecasts, we show that Croston's method (and a variant) and Bootstrapping clearly outperform Moving Average and Single Exponential Smoothing. Third, we show that the performance of Croston and Bootstrapping can be significantly improved by taking into account that each lead time starts with a demand.