A question about mode check plot?

Dear Professor Pfeifer,

When I running the Bayesian estimation, the mode check plot I got is very strange. What kind of problem might it be ?

Any reply will be appreciated. Thank you very much!

Difficult to say since we do not know how you ended up here… These kind of shapes for the standard deviations of the innovations often appear when there is an issue with the measurement equations (mismatch between the data and the theoretical counterpart in your model). So I would first check the consistency of the data and the model. Common issues you may encounter when confronting models to data are well described in this paper by Johannes Pfeifer.

Best,
Stéphane.

Given the scaling of the y-axis, I suspect some combination of data treatment and error codes.