(1)
panel data stationary:
Levin-Lin-Cho ,2000,and Harris - Tzavalis 1999, Breitung,2005. Choi 2001. states and implements a variety of tests ,these tests have as the null hypothesis , that all panels are (trend )stationary,all the panel contain a unit root .
the assorted tests makes different asymptotic assumption regarding the number of panels in your data set ,and the number of time periods;the majority of the test assume that you have balanced panel data,but IM - Pesaran - Shin and Fisher -type test allow for unbalanced panels.
(2)
The null hypothesis is that the series contains a unit root, and the alternative hypothesis is that the series is stationary. As the Levien -Lin - Chu test assumes a common auto regressive parameters for all panels.And the number of lags to include be selected according the criterion whether AIC or H-Q, BCS criterion to estimate the long -run variance of the series. Levien - Lin -Chu test requires the ratio of number of panels to time series period which tends to suited to data sets with large number of panels while Harris - Tzavallis test assume that the number of panels tends to infinity ,while the number of periods tends to be fixed.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Regression