shock decomposition graphs

[scholar_26]

After using shock_decomposition command, we have many graphs. some of them only have only one graph, some of them have many colours. Could you please explain how to interpret them?

[jpfeifer]

From a soon to be published documentation:

Shock decomposition:
Shock decomposition plot generated by the shock_decomposition-command. It is stored in the main folder. The black line depicts the deviation of the smoothed value of the corresponding endogenous variable from its steady state at the specified parameter_set. Note that the steady state was not added. By default, the parameter_set is the posterior_mean if Bayesian estimation has been used and the posterior_mode otherwise. The colored bars correspond to the contribution of the the respective smoothed shocks to the deviation of the smoothed endogenous variable from its steady state, i.e. our “best guess” of which shocks lead to our “best guess” for our unobserved variables. “Initial values” in the graphs refers to the part of the deviations from steady state not explained by the smoothed shocks, but rather by the unknown initial value of the state variables. This influence of the starting values usually dies out relatively quickly.

[jpfeifer]

The guide Pfeifer (2014): "An Introduction to Graphs in Dynare" is now available at https://sites.google.com/site/pfeiferecon/dynare

[Oriana]

Hi,
I am working with a log-linearization model which means that the values of my variables are not log-deviations from steady state, but rather
the logarithm of the respective variables.

In this case I suppose that the black line doesn't depict the deviation of the smoothed value of the corresponding endogenous variable from its steady state at the specified parameter_set, but rather represents the log-levels of the corresponding endogenous variable at the specified parameter_set. Moreover, the colored bars correspond to the contribution of the the respective smoothed shocks to the log-levels of the corresponding endogenous variable at the specified parameter_set.

Can someone, please, confirm or refute the previous reasoning.

[jpfeifer]

shock_decomposition always provides the contribution of shocks to deviations of variables from their mean/steady state. If your model is in log, this means it is the contribution to percentage deviations.

[Oriana]

You are absolutely right. I see it know.

[Oriana]

Dear all,

I ask what is the algorithm implemented in Dynare to compute the shock decomposition graphs?
I have been looking for this information online, but unfortunately I haven’t found it yet.

[jpfeifer]

See http://www.dynare.org/phpBB3/viewtopic.php?f=1&p=19548

[moslem6333]

hi
where and how the background data of this graphs are stored? i found in oo_shock_decomposition some data but i can't distinguish which one is for which variables!
based on theory the summation of contribution of all shocks for each variable should be equal 1. but i cant find this

[jpfeifer]

From the header of shock_decomposition.m

Computes shocks contribution to a simulated trajectory. The field set is oo_.shock_decomposition. It is a n_var by nshock+2 by nperiods array. The first nshock columns store the respective shock contributions, column n+1 stores the role of the initial conditions, while column n+2 stores the value of the smoothed variables. Both the variables and shocks are stored in the order of declaration, i.e. M_.endo_names and M_.exo_names, respectively.