stata做面板数据单位根检验的方法汇总

ruthqi1989

首先,helpxtunitroot,就可以看到如下六种检验方法：

1、Levin-Lin-Chutest

xtunitroot llcvarname [if] [in] [, LLC_options]

2、Harris-Tzavalistest

xtunitroot htvarname [if] [in] [, HT_options]

3、Breitung test

        xtunitroot breitung varname [if] [in][, Breitung_options]

4、Im-Pesaran-Shin test

        xtunitroot ips varname [if] [in] [,IPS_options]

5、Fisher-type tests (combining p-values)

        xtunitroot fisher varname [if] [in],{dfuller | pperron} lags(#) [Fisher_options]

6、Hadri Lagrange multiplier stationarity test

        xtunitroot hadri varname [if] [in] [,Hadri_options]

其次，我们在搜集数据过程中难免遇到缺失数据，导致面板数据并非平衡面板，那了解如上六种方法哪个(些)是用于非平衡面板至关重要。

The LLC test requires that the panels be strongly balanced.
the HT test requires that the panels be strongly balanced(Harris-Tzavalis test).
The Breitung test requires that the panels be strongly balanced.
The IPS test does not require strongly balanced data, but there can be no gaps in each individual time series.
If the data are not strongly balanced, then T must be at least 9 for the asymptotic distribution to hold.
xtunitroot fisher does not require strongly balanced data, and the individual series can have gaps.
  The Hadri LM test requires that the panels be strongly balanced.