数据
但长期内数据测试也批评。由于数据周期很长,所以它将涉及多种不同的汇率制度。此外,真正的外部冲击可能引起实际汇率的结构破坏或均衡汇率变化,和长期的使用数据很难测试结构。此外,由于长期历史数据只是从工业国家,测试结果可能被夸大了。这些测试结果造成大量的样品已经确认在一些研究中,如恩格尔、金(1999),恩格尔(2000)。提供一个令人信服的平稳性测试实际汇率后布雷顿森林体系,有必要设计一个测试只使用数据从这个时间,所以应用面板数据实证测试的购买力平价。
解决单位根测试效率低下的问题,而长期历史数据长度的垂直扩展更大数量的样本,面板数据的横向膨胀示例数据。这个方法是一个截面分析不延长时间的数据,并检查一群许多国家的实际汇率来克服低效率造成的小样本。Hakkio(1984),Abuaf和Jorion(1990)测试了购买力平价与面板数据方法在早期的时间。魏、欧芹(1995),弗兰克尔和玫瑰(1996),哦(1996),吴(1996),Papell(1997),Papell和Theodoridis(1998),希金斯和委员会(1999),麦当劳,艾伦和克(2002),赵(2002)证明了长期购买力平价是有效利用交叉数据从不同的工业国家。另一方面,面板数据的研究在发展中国家有不同的结果。Phylaktis和Kassimatis(1994)发现,购买力平价是有效的基于八个太平洋国家的考验和1974 – 1987年的数据。但吴和陈(1999)得到了相反的结论相同的八个太平洋国家基于1980 – 1996年的数据。使用面板数据的单位根检验和方差比检验技术,Luintel(2000)证明,购买力平价是有效的基于数据从8个亚洲国家。
数据
But long-time period data test is also criticised. Since the data period is very long, so it will involve a variety of different exchange rate regimes. Moreover, the real external shocks may cause the structural break of the real exchange rate or the equilibrium exchange rate shifting, and the use of long-term data is difficult to test the structural break. Also, because the long-term historical data is only from the industrial countries, the test results may be exaggerated. These test results caused by the large amount of samples has been confirmed in some studies, such as Engel, Kim (1999), Engel (2000). To provide a convincing test to the stationarity of real exchange rate in latter Breton Woods’s system, it is necessary to design a test only using data from this period of time, so panel data is applied in empirical tests of PPP.
To solve the problem of inefficiencies of unit root tests, compared to long-time historical data which is the vertical extension of length to get the larger amount of samples, panel data is a lateral expansion of the sample data. This method is a sectional analysis which does not extend the time period of data, and it examines a group of the real exchange rates in many countries to overcome inefficiencies caused by small samples. Hakkio (1984), Abuaf and Jorion (1990) tested PPP with panel data method in the early time. Wei, Parsley (1995), Frankel and Rose (1996), Oh (1996), Wu (1996), Papell (1997), Papell and Theodoridis (1998), Higgins and Zakrajsek (1999), McDonald, Allen and Cruickshank (2002), Chiu (2002) all proved the long-term PPP is valid by using cross data from different industrial countries. On the other hand, panel data studies in developing countries have got mixed results. Phylaktis and Kassimatis (1994) found that PPP is valid based on the test of eight Pacific countries and 1974-1987 years of data. But Wu and Chen (1999) got the opposite conclusion with the same eight Pacific countries based on 1980-1996 years of data. Using unit root test and variance ratio test of panel data technique, Luintel (2000) proved that PPP is valid based on the data from eight Asian countries.
