i am conducting the panel data analysis with R. i use the package 'urca' and 'tseries" to do the unit root test. the result shows that all of variables are stationary,including the GDP. it is quite different with my understanding of the reality. I think there must be something wrong with my codes.
my quetions are:
1. can the unit root test of time series data and panel data be done with the same R codes?
2. how to do the unit root test of panel data? can someone show me the correct codes.
Thank you !
Hi Yimin!
I suggest you using URCA package in R. I have enclosed a useful link for you.
Good luck!
Hi you can refer below ad:
http://stats.stackexchange.com/questions/33364/unit-root-tests-for-panel-data-in-r
Dear everyone, thank you for your seggestions. but the problem is still there. I paste the result of R and Eviews here and upload the data. could anyone conduct unit root test with data then tell me why.
the result of R shows unit root does not exist.
> adf.gdp summary(adf.gdp)
Value of test-statistic is: -5.4851 10.0762 15.0772
Critical values for test statistics:
1pct 5pct 10pct
tau3 -3.98 -3.42 -3.13
phi2 6.15 4.71 4.05
phi3 8.34 6.30 5.36
> adf.test(dd$gdp,k=1)
Augmented Dickey-Fuller Test
data: dd$gdp
Dickey-Fuller = -5.4851, Lag order = 1, p-value = 0.01
alternative hypothesis: stationary
the result of Eviews shows unit root exist.
Panel unit root test: Summary
Series: GDP
Date: 08/07/16 Time: 12:45
Sample: 2005 2014
Exogenous variables: Individual effects, individual linear trends
User-specified lags: 1
Newey-West automatic bandwidth selection and Bartlett kernel
Balanced observations for each test
ADF - Fisher Chi-square 43.8483 0.9610 31 248
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Statistical Software
- R