摘要：Using Theil’s inequality coefficient based on the mean square prediction error, this paper evaluates the forecasting efficiency of the central government budget and revised budget estimates in Pakistan for the period 1987/88 to 2007/08 and decomposes the errors into biasedness, unequal variation and random components to analyze the source of error. The results reveal that budgetary forecasting is inefficient in Pakistan and the error is due mainly to exogenous variables (random factors). We also find that neither the budget nor revised budget estimates of revenue and expenditure satisfy the criteria of rational expectations of forecasting. Further, there is very little evidence of improvement in the efficiency of budgetary forecasts over time
