Dear colleagues,
I am capable of using linear estimations between X and Y variables via OLS or 2SLS (on Eviews, for example); however, I need to study how to estimate/model non-linear relationships as well. If you know any source which can explain it in a simple language based on time series, your recommendations are well-welcomed. Thank you beforehand.
Best
Ibrahim
You can try Greg N. Gregoriou, Razvan Pascalau books on Non linear financial econometrics. They have one relating to Markov switching and another relating to forecast. But I will also advice you to read articles that uses non linear methods such as Assymertic models, Non linear ardl, switching regression, threshold regression etc. They are mostly financial econometrics related methodology.
I recommend Data Analysis - Hossain Academy. You can join on facebook or youtube.
Thanks.
@ Paul Terhemba Iorember. Sir. The hossain academy platform is a good one indeed as I have been on the platform for years. However, I suggest he read more books and journals so as to have the requisite knowledge of what he seeks as there are many self acclaimed scholar in the group who don't seems to know much and might dissuade him or give him wrong information. As we cannot reference individual's opinion or video watched in a journal but can reference books or journal.
You can also consider the textbook "Dynamic Nonlinear Econometric Models: Asymptotic Theory", 1997. Authors - Benedikt M. Pötscher and Ingmar R. Prucha
Dear Ibrahim,
I also recommend Greg. N Gregorios and Raven Pascalau @Hamid Muili and google for more materials on non-linear relationship.
Regards
It is important you go to theory in order to set up a model where the relationships are not linear. Theory can guide you in this respect. For instance, there are theoretical reasons for which the effect of age on earnings can be a second-order polynomial.
- Badges
- Science topic