I am trying to measure the effects of restrictions on immigration to a specific country on both real estate rental indices and real estate property price indices during the next 3 to 5 years. As a software, I am using Eviews and I would like to calculate two alternative scenarios. A VECM (vector error correction model) should be used for simulating the effects of changes in population numbers on different macroeconomic variables (GDP, consumer price index, interest rates). Rental prices are straightforward to estimate in an error correction setting. How would you derive a pricing formula for the real estate price index? Would you consider using FM-OLS (Fully Modified OLS) or DOLS (Dynamic OLS) using the mentioned macroeconomic variables as cointegrated variables? The equation structure will be linked by a model object within Eviews for running forecasting simulations.

  • $\begingroup$ You should not combine FM-OLS or DOLS with vector error correction, if you want to do VECM the long run equation will be estimated using the Johansen method which basically looks like VAR on level variables where you allow some roots to be at unit circle $\endgroup$ – 1muflon1 Mar 8 at 20:37
  • $\begingroup$ What is the deeper reason why I should not use FM-OLS or DOLS equation with the VECM in an Eviews model object? $\endgroup$ – Tintin Mar 8 at 21:57
  • $\begingroup$ I would just like to run VECM for the macroeconomic variables and estimate a separate cointegrating equation (FMOLS or DOLS) for the real estate prices and then combine it into a model object for forecasting two different scenarios under different assumptions of population growth. $\endgroup$ – Tintin Mar 8 at 22:13
  • $\begingroup$ your original post sounded like you wanted to use FMOLS to estimate the cointegrated part of your VECM $\endgroup$ – 1muflon1 Mar 9 at 8:25

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.