Estimation takes so long

Occbin
1

Hi professor, I am running a model to estimate parameters, however, It takes as long as more than one hour.Is it usual to take so long? In this model, there are 44 variables and 9 shocks. Is it because there are so many shocks so that it takes long?

I was eager to get some results. So that I delete 8 shocks and only estimate one parameter of beta (discount factor). However, it still takes as long as more than one hour. That puzzles me a lot. How can I speed up the estimation? Any suggestion is appreciated.

In addition, I came across another error before I delete 8 shocks. It said as follows:

2022-07-04 00.01.06
2022-07-04 00.01.062210×970 100 KB

I have no idea why this happens. However, when I truncate the estimated parameters to only one parameter (beta) and write it directly in .mod files, it didn’t appear. I still want to know how to solve this problem. I would appreciate a lot if you can give me any hint.

I upload my mod file which consists of all shocks and all estimated parameters. To summarize, I have to questions: first, how to solve the error of “The steady state file internally changed the values of the following estimated parameters”; Second, how to speed up the estimation.
test.zip (12.2 KB)

2
  1. You steady state file is wrong. You are not supposed to load hard-coded parameters there. Rather, Dynare passes the parameter values of the current draw to the steady state file.
  2. You are using the inversion filter which is slow and you enable the debugging mode. That will take time.