关于oecd数据和triangulization的问题，求解答

rangbing1993

1679

收藏 2016-03-31

悬赏 15 个论坛币未解决

我需要把sources and propagation of international output cycles: common shocks or transmission这篇文章的第三部分重做一边有几个疑问
1. 文章里使用了quarterly real GDP data for US Germany and Japan from OECD between 1960 Q1 to 1994 Q4, 我在OECD上下载数据时，只有dataset :quarterly national accounts; gross domestic product-expenditure approach; VPVOBARSA:US dollars, volume estimates, fixed PPPs, OECD reference year, annual levels, seasonally adjusted 这份数据里有这个时间段的这三个国家的数据。但是我进行分析时，发现和文章结果有差，美国相差不大，但是日本却差的特别多。我看到OECD里提到change of regerence year from2005 to 2010, 是因为这个原因我下载的数据其实和原数据不同, 所以结果有差？
2. 文中提到

We estimate a VAR with 9 lags and a constant on the log of detrended outputs and report responses when the contemporaneous
correlation matrix of the shocks is triangularized in the order US, Germany and Japan outputs. 这里的triangulaize 我是不是用eviews 做unrestricted var. 然后impulse里选cholesky ordering：US GERMANY JAPAN就好了？

sources and propagation of international output cycles common shocks or transmission.pdf