Set limits on variables to forecast in a VAR model (vars)

Machine Learning and Modeling
1

I've been using vars to forecast monetary policy variables, one of which is Canada's overnight interest rate. The lower bound for that as per policy is 0.25. How can ensure that the variable does not dip below a value of 0.25 when forecasting?

Thanks.

2

In general, forecasts from VARs are unbounded. However, there is a "trick" that sometimes works. If the interest rate is y, substitute in the var ln (y-0.25). As the forecast goes to -\infty, you get e^{ln(y-0.25)}=0=y-0.25, or y=0.25.

3

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.