Development of high precision prediction model using management and analyst forecasts

• Project/Area Number: 25380605
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Accounting
• Research Institution: Takasaki City University of Economics
• Principal Investigator: Keiji Abe 高崎経済大学, 経済学部, 教授 (70277771)
• Project Period (FY): 2013-04-01 – 2018-03-31
• Project Status: Completed (Fiscal Year 2017)
• Budget Amount: ¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000); Fiscal Year 2016: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000); Fiscal Year 2015: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000); Fiscal Year 2014: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000); Fiscal Year 2013: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
• Keywords: 利益予測 / 予測の合成 / 利益予想 / アナリスト / 会計学

Outline of Final Research Achievements

In this research, as a proposal to supplement management forecasts, we try to combine forecasts using analyst forecasts. We use the Bayesian approach using past forecasts proposed by Winkler (1981) to synthesize management and analyst forecasts. In order to estimate the variance-covariance matrix, we used the forecast data for TSE 1st section listed companies from 2009 to 2016, and we estimated the combined forecast for 2017. As a result of the analysis, the prediction error of the combined forecast is lower than the forecast of management and analysts in both earnings per share and ordinary income.
For the ordinary profit, we obtained statistically significantly lower prediction error and the possibility that the combined forecast is useful.