[求助]求教STATA中面板数据单位根检验的做法

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

<P>正打算做一些面板数据的单位根检验问题，但很难查到详细的stata如何进行面板数据单位检验的命令和操作方法。</P>
<P><STRONG>我在STATA8.0和9.0版本中都看到了“time  series ”项的检验（tests）中发现dfuller,dfgls和pperron 三种检验命令菜单中都在“time setting”中有panel id varable的选项，因此就相应用面板数据并加以设置，但三各命令试下来结果都是"sample may not include multiple panels"的错误提示，这难道说明这一选项不能使用呢？还是使用时需要升级软件，还是要有什么条件？还是我选择的命令项有误呢？真是非常着急想搞明白啊。</STRONG></P>
<P>有那位高手能指导一下stata软件如何处理<STRONG>面板数据</STRONG>的<STRONG>单位根检验、协整以及因果检验</STRONG>方法。</P>
<P>能否给些例子？盼望好心的高手指点一二，先表示万分万分感谢了。</P>[em14]

[此贴子已经被作者于2006-7-6 15:16:37编辑过]

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

分享0 收藏19 回帖

关键词：求教stata Stata 单位根检验 tata 面板数据 multiple include setting 如何 软件

one needs to install dfuller.ado,dfgls.ado & pperron.ado first before using. The easiest way to get it is search all in Help.

or directly search in google.

once you get the ado. files, save it under STATA\ado\ , then use ssc install *.ado  to install it.

after installing them, you can freely use them, for help , just type: help dfuller/dfgls/pperon.

Personally, I don't think these tests can solve any problem. It is very difficult to get good data.

 It is very difficult to get good data.

----------------------------------------------------------------------------------------------------------
help for hadrilm                                                     (StataList distribution 20 July 2001)
----------------------------------------------------------------------------------------------------------

Hadri panel stationarity test

        hadrilm varname [if exp] [in range]

hadrlim is for use with panel data.  You must tsset your data before using hadrilm, using the panel form
of tsset; see help tsset.

varname may contain time-series operators; see help varlist.

Description

hadrilm performs a test for stationarity in heterogeneous panel data (Hadri, 2000). This Lagrange
Multiplier (LM) test has a null of stationarity, and its test statistic is distributed as standard normal
under the null.  The series may be stationary around a deterministic level, specific to the unit (i.e. a
fixed effect) or around a unit-specific deterministic trend.  The error process may be assumed to be
homoskedastic across the panel, or heteroskedastic across units. Serial dependence in the disturbances can
also be taken into account using a Newey-West estimator of the long run variance.  The residual-based test
is based on the squared partial sum process of residuals from a demeaning (detrending) model of level
(trend) stationarity.

Test results and p-values are placed in the return array.

Examples

        . use http://fmwww.bc.edu/ec-p/data/hayashi/sheston91.dta,clear

        . hadrilm rgdppc if country<11

        . hadrilm D.rgdppc if country<11

References     

Hadri, Kaddour. Testing for stationarity in heterogeneous panel data.
The Econometrics Journal, 3, 2000, 148-161.

Acknowledgements       

Thanks to Kameliia Petrova for assistance with validation of this code.

Author

Christopher F Baum, Boston College, USA
baum@@bc.edu

Also see
On-line:  kpss (if installed), nharvey (if installed)

hadrilm rgdppc if country >11

Hadri (2000) panel unit root test for rgdppc
with 26 observations on 114 cross-sectional units
-----------------------------------------------------------
 eps       Z(mu)    P-value      Z(tau)    P-value
-----------------------------------------------------------
Homo     154.963     0.0000      71.917     0.0000

Hetero   125.520     0.0000      66.136     0.0000

SerDep    30.674     0.0000      17.132     0.0000
-----------------------------------------------------------
H0: all 114 timeseries in the panel are stationary processes
Homo: homoskedastic disturbances across units
Hetero: heteroskedastic disturbances across units
SerDep: controlling for serial dependence in errors (lag trunc = 4)

.
结果怎么解释？求教！！

1.面板单位根检验（Fisher Test for panel unit root）：xtfisher(需安装)
webuse grunfeld,clear
xtfisher invest, trend lag(1)
xtfisher mvalue, lag(2) pp

2.面板协整检验（Panel cointegration）：xtwest(需安装)
use http://fmwww.bc.edu/repec/bocode/x/xtwestdata.dta
xtwest loghex loggdp, westerlund constant trend lags(1 3) leads(0 3) lrwindow(3)
xtwest loghex loggdp, westerlund constant trend lags(1) leads(1) lrwindow(3) bootstrap(100)

谢谢分享

看了很受益，多谢！

请问您现在会做了吗 这个问题也困扰着我啊 不知道怎么看结果

谢谢分享

虽说Eviews在这方面相对简单多
譬如
虚无假设是Stationary的 Panel Stationary Test (Hadri学者发展的,其idea源于KPSS)
虚无假设是Unit root的Panel Unit Root Test (IPS或LL多位学者发展的,其idea源于ADF或PP)
另外在Cointegration(协整,或称共整合)方面
一派是基于虚无假设为no Cointegration的Panel no-Cointegration Test
其idea源于Engle及Granger的ECM去执行
而一派是基于虚无假设为有Cointegration的Panel Cointegration Test
其idea源于Shin,这方面有名的学者为Kao(高志华)

To 5楼
据p-value得知
似乎都拒绝虚无假设为Stationary
换句话说 就是实证结果显示 为Panel no-stationary
您的实证结果支持具有单根啰!!!