For technical questions regarding estimation of single equations, systems, VARs, Factor analysis and State Space Models in EViews. General econometric questions and advice should go in the Econometric Discussions forum.
6 posts • Page 1 of 1
Glenn is right. Unless you have a priori knowledge/information on the type of nonlinearity, it is very difficult to decide the specific form of the model. For instance, there are tests for STAR-type nonlinearities, but they are not built-in. Nevertheless, I believe BDS test could be of help (Series-->View-->BDS Independence test). You can also apply this test to the residuals to see if there is any non-linear dependence after the linear model has been fitted.
To follow up on Trubador's comments The Ramsey RESET test and BDS would have power against nonlinear alternatives. The various forms of breakpoint testing also may be used to detect nonlinearities after a regression model has been fit. But I'm not certain that they'll give you much information on what model should be fit.
Who is online
Users browsing this forum: No registered users and 5 guests