Forecasting the agricultural structure using empirical transition matrices
描述了一种利用经验转移矩阵预测农业结构的技术，通过独立同分布马尔可夫链估计新农场数量并推导预测误差标准差，以瑞典农场数据验证三年期预测效果。
Summary This article gives a description of a technique used to forecast the agricultural structure. Different models for estimating the number of new farms are considered. The standard deviation of the prediction error can be derived if the state of the farms can be described by independent and identically distributed Markov chains. The technique is applied to data for all Swedish farms and the forecasts are compared to the actual values after a period of three years. The assumptions of the model and its relation to economic theory and to other forecasting techniques are discussed.