我尝试学习如何将 GMM 方法与 R（Arellano-Bond 估计器）结合使用。所以我使用pgmm包中的命令plm。
我复制了此示例的代码：https ://www.rdocumentation.org/packages/plm/versions/1.6-5/topics/pgmm
有了这些数据：
Date country credit a b c d e f g h i j
2000-01-01 Germany 3840,304 0 0 0 0 0 0 1 .b 0 -1
2000-04-01 Germany 3891,104 0 0 0 0 0 0 0 .b 0 0
2000-07-01 Germany 3916,966 0 0 0 0 0 0 0 .b 0 0
2000-10-01 Germany 3984,611 0 0 0 0 0 0 0 .b 0 0
2001-01-01 Germany 4003,066 0 0 0 0 0 0 0 .b 0 0
2001-04-01 Germany 4012,048 0 0 0 0 0 0 0 .b 0 0
2001-07-01 Germany 4053,672 0 0 0 0 0 0 0 .b 0 0
2001-10-01 Germany 4097,941 0 0 0 0 0 0 0 .b 0 0
2002-01-01 Germany 4108,002 0 0 0 0 0 0 0 .b 0 0
2002-04-01 Germany 4142,119 0 0 0 0 0 0 0 .b 0 0
2002-07-01 Germany 4210,727 0 0 0 0 0 0 0 .b 0 0
2002-10-01 Germany 4220,897 0 0 0 0 0 0 0 .b 0 0
2003-01-01 Germany 4280,548 0 0 0 0 0 0 0 .b 0 0
2003-04-01 Germany 4331,072 0 0 0 0 0 0 0 .b 0 0
2003-07-01 Germany 4322,555 0 0 0 0 0 0 0 .b 0 0
2003-10-01 Germany 4338,01 0 0 0 0 0 0 0 .b 0 0
2004-01-01 Germany 4370,032 0 0 0 0 0 0 0 .b 0 0
2004-04-01 Germany 4354,935 0 0 0 0 0 0 0 .b 0 0
2004-07-01 Germany 4375,466 0 0 0 0 0 0 0 .b 0 0
2004-10-01 Germany 4390,958 0 0 0 0 0 0 0 .b 0 0
2005-01-01 Germany 4396,222 0 0 0 0 0 0 0 .b 0 0
2005-04-01 Germany 4448,471 0 0 0 0 0 0 0 .b 0 0
2005-07-01 Germany 4471,893 0 0 0 0 0 0 0 .b 0 0
2005-10-01 Germany 4451,653 0 0 0 0 0 0 0 .b 0 0
2006-01-01 Germany 4477,181 0 0 0 0 0 0 0 .b 0 0
2006-04-01 Germany 4497,384 0 0 0 0 0 0 0 .b 0 0
2006-07-01 Germany 4545,383 0 0 0 0 0 0 0 .b 0 0
2006-10-01 Germany 4527,901 0 0 0 0 0 0 0 .b 0 0
2007-01-01 Germany 4523,691 0 0 0 0 0 0 1 .b 0 0
2007-04-01 Germany 4514,656 0 0 0 0 0 0 0 .b 0 0
2007-07-01 Germany 4510,95 0 0 0 0 0 0 0 .b 0 0
2007-10-01 Germany 4552,084 0 0 0 0 0 0 0 .b 0 0
2008-01-01 Germany 4577,551 0 0 0 0 0 0 0 .b 0 0
2008-04-01 Germany 4590,665 0 0 0 0 0 0 0 .b 0 0
2008-07-01 Germany 4619,162 0 0 0 0 0 0 0 .b 0 0
2008-10-01 Germany 4719,901 0 0 0 0 0 0 0 .b 0 0
2009-01-01 Germany 4747,204 0 0 0 0 0 0 0 .b 0 0
2009-04-01 Germany 4788,791 0 0 0 0 0 0 0 .b 0 0
2009-07-01 Germany 4794,392 0 0 0 0 0 0 0 .b 0 0
2009-10-01 Germany 4803,617 0 0 0 0 0 0 0 .b 0 0
2010-01-01 Germany 4832,948 0 0 0 0 0 0 0 .b 0 0
2010-04-01 Germany 4925,639 0 0 0 0 0 0 0 .b 0 0
2010-07-01 Germany 4971,252 0 0 0 0 0 0 0 .b 0 0
2010-10-01 Germany 5122,327 0 0 0 0 0 0 0 .b 0 0
2011-01-01 Germany 5041,913 0 0 0 0 0 0 1 .b 0 0
2011-04-01 Germany 5079,78 0 0 0 0 0 0 0 .b 0 0
2011-07-01 Germany 5207,961 0 0 0 0 0 0 0 .b 0 0
2011-10-01 Germany 5231,821 0 0 0 0 0 0 0 .b 0 0
2012-01-01 Germany 5280,251 0 0 0 0 1 0 0 .b 0 -1
2012-04-01 Germany 5392,063 0 0 0 0 0 0 0 .b 0 0
2012-07-01 Germany 5400,905 0 0 0 0 0 0 0 .b 0 0
2012-10-01 Germany 5412,811 0 0 0 0 0 0 0 .b 0 0
2013-01-01 Germany 5422,592 0 0 0 0 0 0 0 .b 0 0
2013-04-01 Germany 5430,467 0 0 0 0 0 0 0 .b 0 0
2013-07-01 Germany 5398,361 0 0 0 0 0 0 0 .b 0 0
2013-10-01 Germany 5432,462 0 0 0 0 0 0 0 .b 0 0
2014-01-01 Germany 5456,415 0 0 0 0 1 0 1 .b 0 0
2014-04-01 Germany 5504,142 0 0 0 0 0 0 0 .b 0 0
2014-07-01 Germany 5516,876 0 0 0 0 0 0 0 .b 0 0
2014-10-01 Germany 5532,75 0 0 0 0 0 0 0 .b 0 0
因变量是“信用”，a、b、c...是自变量。后者是宏观审慎政策和货币政策。因此，我试图了解这些政策（加上滞后因变量）对信贷增长的影响。
对于这些政策，收紧时该指数取值为 1，没有变化时为 0，宽松时为 -1。
我尝试了几次，但总是出现相同的错误： Terms.default(formula) 中的错误：没有术语组件或属性
一些尝试：
test <- pgmm(credit) ~ lag(credit)+lag(a)+lag(b), data = BDD)
pgmm(credit ~ lag((credit), 1) + lag((sscb_res), 1), data = BDD, effect = "twoways", model = "twosteps")
pgmm(credit ~ lag((credit), 0:1) + lag((sscb_res), 0:1), data = BDD, effect = "twoways", model = "twosteps")
等等。我不知道该怎么办。你认为它来自于数据中大量的“0”吗？
我按照这个例子：
data("EmplUK", package = "plm")
z1 <- pgmm(log(emp) ~ lag(log(emp), 1:2) + lag(log(wage), 0:1)
+ log(capital) + lag(log(output), 0:1) | lag(log(emp), 2:99),
data = EmplUK, effect = "twoways", model = "twosteps")
但是，我不明白为什么一个滞后是“0:1”而不是“1”。
你能帮我吗？
PS：请原谅我的英语
| 归档时间： |
|
| 查看次数： |
1257 次 |
| 最近记录： |