Hi!

Very new to dynare. I’m trying to estimate a model very similar to the one used by Sims and Wu (2020 JME) and Karadi and Nakov (2021, JME).

I get this error

Error using chol

Matrix must be positive definite.

I’ve tried looking through the forum, and have done all the things suggested: plotting the priors, checking the data… but nothing seems to work.

My intuition is that there are deeper problems, but I’m not sure how to address them. For example, is the initial value of the log posterior meaningful? I guess no, but it seems very large. Second, I’m using mode_compute=6, and the value of the scale parameter is really small. Should I be worried about this? Finally, I had issues defining depending parameters and the steady state. What’s the best practice for this?

The data is the same as the one used by Anzoategui et al. (2019, AEJ: Macro), which is available online.

data_use.mat (3.1 KB)

model_estimation.mod (8.1 KB)

estimation_params.m (7.9 KB)