I have a question about Markov switching regression (sry for the horrible formula... I couldn't find a writing manual). I want to estimate the following regression equation:
x_t = c + a x_t-1 + b D
Where x_t is the parameter I want to estimate with x_t-1 as a lag and a as the coefficient; c is a constant and D is a dummy variable (notice that I didn't use a time index) with b as the coefficient. The dummy variable is either 1 or 0. I only have data for x from 2000 to 2010 and I want to estimate the above regression using a markov switching regression for this time span. But I have a much longer time span for the dummy variable from 1900-2010.
So I want to estimate the switching probability for the dummy variable with a maximum likelihood estimation based on the longer time span from 1900-2010 and use this probability for the markov switching regression. I'm using EVIEWS 10.
Thank you for your help.
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.
1 post • Page 1 of 1
Who is online
Users browsing this forum: No registered users and 8 guests