What tests do I need to perform for VECM and VAR to be considered robust? I know LM test for residual autocorrelation is mandatory, but what about Jarque-Bera test? Is that necessary?And what should I do if my regressions don't pass that test?
Jarque-Bera test used to check the normality of residuals (whether residuals are symmetrically distributed or not) in VAR System or in a single equation regression. Yes, it is mandatory for taking care of adequacy of the selected model for empirical analysis. Since in small or large samples, t and F Chi-square tests require the normality assumption therefore it becomes more important in regression.
if regression don't pass this test please check the stationary of the series may be after that problem removed.
In reality, usually there is no linearity observed by data set. Ms. Gholia is right, check data set stationarity. I believe, checking stationarity is an essential prerequisite while dealing with time series. Moreover, there are other transformations available which may be considered.
as per standard econometric theory the error terms of the estimated model must be normally distributed so it becomes mandatory to test the normality property of the residuals. Jarque-Bera is most commonly used test to analyze the normality of the error terms.....
Respected members.Can u Please guide me that VECM using panel data,it is also important to apply LM serial correlation test,Hetereoscedasticity and normality test to check the vaidity of the model.Guidance needed regarded this issue.Thanks
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS