Monthly parameters calibration from quarterly values

Estimation ML/Bayesian estimation
1

Hello,

For most of the parameters, it is easy to find the equivalent monthly calibration of quarterly calibration. However, I’m having problems with the transformation of 2 parameters : the habit formation (h) and the adjustment cost in investment (\kappa).

For the first the quarterly equation is:

U(C_t (j)) = log(C_t(j) - hC_{t-1}(j))

For the second one the equation is:

f\left(\frac{I_t}{I_{t-1}}\right)= \frac{\kappa}{2}\left( \frac{I_t}{I_{t-1}} - 1\right)^2

Usually, quarterly calibration of these values are h=0.7 and \kappa=5. Any ideas which are the equivalent of those for a monthly calibration?

2
  1. The habit parameter is akin to an autocorrelation. So when going to monthly data, I would expect something like the third root, i.e. about 0.9 for 0.7 in quarterly data.
  2. You may want to have a look at
    Investment adjustment costs in annual frequency
3

Hello. How about inflation indexation? Should I take the third root as well since it is vaguely a persistence-related parameter. Do you have any suggestions? Thank you.

4

Usually, yes.

1 Like