Autcovariances output

I have some trouble in finding the matrices of autocovariances in the global output variable “oo_” when running Alt_Ex1.mod. As it is mentionned in the dynare user guide (p.41) , “by default, dynare will return autocovariances with a lag of 5 plus the variance decomposition” but unfortunately i could not find it.

i will be gratefull for any help,

After running the model, you will find the variable “oo_” in the Matlab workspace. It is a structure. So if you double-click on it, you see the fields of this structure. One of them is named “autocorr”. It is a 1 by 5 cell array, where each cell stores one matrix.
Alternatively, if you type “oo_.autocorr{1,number}” in the command window after running the mod-file, where number is between 1 and 5 , Matlab outputs the corresponding autocorrelation matrix in the command window.

Jpfeifer, thanks for your response, i have seen this “oo_autocorr” in the workspace but not the “oo_gamma_y” (the matrices of autocovariances) which i am looking for, as specified in the user guide by Tommaso M.G. p.41, it is said that dynare gives it by default but i could’nt find it in the oo_ structure.

The user guide is somewhat out of date. The more current Dynare manual does not even mention this variable, so it is most probably deprecated. The manual states on p. 31:

So this variable should be what you are looking for.

that i was thinking, thanks again for the information,

Dear all,

I would like to check if the autocovariances of the replication file matches the autocovariances of the original paper. Unfortunately, after running the replication file I cannot find the output for the autocovariances. If I have understood correctly, I can call the autocovariances in the folder oo_.gamma_y. But given the huge differences in the values of the replication file compared to the original file, I’m very confident that there is a mistake on my behalf.
Could someone tell me, where I can find the autocovariances? Do I need an additional command for it?

Thank you very much for your help!


I would need to see the file. Are you looking for autocorrelations or covariances?

Dear Professor Pfeifer,

I’m sorry, I’ve missed to attach the mod file. I’m looking for the autocovariances and cross-covariances that results from the replication file.

rep_figure3_ALLV.mod (26.6 KB)


But oo_.gamma_y{1+i} contains autocorrelations, not covariances. You would have to compute them.

I did not know that. Many thanks for the clarification!