Analysis of the long-run and one-way causality between macroeconomic index

就项目而言，我们得到了以下结果：将作者在上位机SX4上编写的程序代码成功地传输到个人计算机上。基于PC，我们开发了一些程序，通过这些程序可以方便地进行单向因果度量的计算。基于协整时间序列模型，给出了时域和频域单向效应测度的计算算法。提出的新方法有助于降低仿真成本。明确了长期和短期（局部）单向效应的计算算法。此外，我们还基于Pro Fortran开发了必要的计算程序。通过使用这些程序，可以详细地研究复杂的因果关系。为了将单向效应因果测度方法应用于基于PC的高频金融时间序列分析，阐述了该算法。为了利用互联网上及时发布的数据，特别是中国的金融和市场数据，明确了将数据库文件转换为文本格式的方法。通过这种方式，我们更新了美国、日本和中国的时间序列数据库。为了开展该项目的研究，我们在国内外会议上报告了我们的研究成果，并进行了海外研究。在这三年的时间里，我们发表了5篇研究论文，在会议上报告了4次。其中一些新结果将在2006年7月9日至12日在中国北京清华大学举行的2006远东计量经济学会会议上报告。

In term of the project, we get the following results.1.Succeeded in transferred the program code written by the author at supper computer SX4 to personal computer (PC). Based on PC, we developed some programs by witch the calculation of one-way causal measures can be easily conducted.2.Based on cointegrated time series model, we showed the calculation algorithm of the one-way effect measures at time domain and at frequency domain. The proposed new method can contributed to reduce the cost of simulation.3.The calculation algorithms of long-run and short-run (local) one-way effects are made clearly. In addition, we developed the necessary calculation program based on Pro Fortran. By the use of these programs, it is possible to investigate the complex causal relationships in details.4.To apply the approach of one-way effect causal measures to the analysis of high frequency financial time series based on PC, the algorithm is made cleared5.To make use of the timely data published at internet, especially Chinese financial and market data, the way of transforming the date base file to text format is made cleared. By this way, we renew our time series data base of America and Japan as well as China.6.To conduct the project, we reported our research results at internal and international conferences and also have had made oversea researches.7.In this three years period, we published 5 research papers and reported 4 times at conference. Some of the new results will be reported at the 2006 Far Eastern Meeting of the Econometric Society which will be held in Tsinghua University, Beijing, China, on July 9-12, 2006.