Statistical inference of transformed non-stationary time series models and its applications to economic analysis.

• Project/Area Number: 22730175
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Single-year Grants
• Research Field: Economic statistics
• Research Institution: Otaru University of Commerce
• Principal Investigator: TERASAKA Takahiro 小樽商科大学, 商学部, 教授 (60313920)
• Project Period (FY): 2010 – 2012
• Project Status: Completed (Fiscal Year 2012)
• Budget Amount: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000); Fiscal Year 2012: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000); Fiscal Year 2011: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000); Fiscal Year 2010: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
• Keywords: Box-Cox変換 / 時系列モデル / Box-Coｘ変換 / 多変量ARMAモデル / 修正Box-Cox変換 / ARMAモデル / 共和分 / ATMAモデル

Research Abstract

I propose a new estimation procedure of the modified Box-Cox transformed stationary autoregressive-moving average models and examine the performance of the algorithm. The order selection is mostly successful and proposed estimation procedure works very well. I apply this model to the Japanese stock market data.