stata面板数据单位根检验LLC

42949

收藏 2014-11-19

用stata12做面板数据的单位根检验
用LLC检验的时候，出现了错误，如下：
. levinlin aincome, lag(1)

Levin-Lin-Chu test for aincome Deterministics chosen: constant
w1 ambiguous abbreviation
r(111);

希望哪位高手能够知道一下这是为什么？
但是我做IPS检验的时候就没有出现这种情况，这是为什么呢？
. ipshin x, lag(1)

Im-Pesaran-Shin test for cross-sectionally demeaned x
Deterministics chosen: constant

t-bar test, N,T = (39,8)       Obs = 234
Augmented by 1 lags (average)

t-bar    cv10    cv5    cv1 W[t-bar] P-value
2.825 -1.700 -1.750 -1.850 24.044    1.000
还有一个问题想问问：
例如做LLC检验的时候，我可以输入LLC x, lag(1)命令；也可以输入 xtunitroot llc x, lag(1)命令，  这两个有区别吗？

扫码加我拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

全部回复

ariera

2014-11-20 15:08:26

这个楼主其实完全可以自己看help 解决。
我也是闲的没事帮你看了一下的。
首先，明确的是levinlin 这个不是stata自带的，这个东西可以通过findit 搜索安装的，来源是BC的服务器。
而xtunitroot 则是stata自带的用于面板数据单位根检验的函数。
值得一提的是，这个许多stata用户自己写的程序托管于BC的服务器上。WISC网站上有这么一个page：
http://www.ssc.wisc.edu/sscc/pubs/4-16.htm
其中提到：
Most of these programs are stored at Boston College's Statistical Software Componentsarchive (or SSC, but not to be confused with the UW's Social Science Computing Cooperative or SSCC) .
什么意思就不用翻译了吧。
再次，这个levinlin 和xtunitroot  是有区别的。
根据我的查阅，xtunitroot 是能够使用多种检验方法进行单位根test的，包括不限于LLC test，LM test，IPS等，stata help 中提到：
xtunitroot performs a variety of tests for unit roots (or stationarity) in panel datasets. The Levin–
Lin–Chu (2002), Harris–Tzavalis (1999), Breitung (2000; Breitung and Das 2005), Im–Pesaran–Shin
(2003), and Fisher-type (Choi 2001) tests have as the null hypothesis that all the panels contain a unit
root. The Hadri (2000) Lagrange multiplier (LM) test has as the null hypothesis that all the panels
are (trend) stationary. The top of the output for each test makes explicit the null and alternative
hypotheses. Options allow you to include panel-specific means (fixed effects) and time trends in the
model of the data-generating process.
具体自己查看一下吧。
而levinlin 描述如下：
levinlin estimates the panel unit root test developed by Levin, Lin and Chu (LLC, 2002).  The test assumes that each individual unit in the panel
shares the same AR(1) coefficient, but allows for individual effects, time effects and possibly a time trend. Lags of the dependent variable may be
introduced to allow for serial correlation in the errors. The test may be viewed as a pooled Dickey-Fuller test, or an Augmented Dickey-Fuller
(ADF) test when lags are included, with the null hypothesis that of nonstationarity (I(1) behavior).  After transformation by factors provided by
LLC, the t-star statistic is distributed standard normal under the null hypothesis of nonstationarity.
意思就是这就是LLC test.......
用法区别没仔细看，楼主要多学学看help，小问题就不要发问了。stata帮助文档其实很不错的！