Modeling Time-Variation Over the Business Cycle (1960-2017): An International Perspective

Enrique Martinez-Garcia
Federal Reserve Bank of Dallas and SMU
emg.economics@gmail.com
Date: 10/1/2018



I use the real GDP series in levels for each country and apply the matlab code
one_sided_hp_filter_kalman.m in order to extract the cyclical component. This is 
the measure of domestic slack (removing the trend component and potential) from the data
which I use to estimate the reduced-form Phillips curve in this excel file.

I compute the decomposition using the standard lambda of 1600 often used with 
quarterly data (the series y) and the following command:

[ytrend,ycycle]=one_sided_hp_filter_kalman(y)

I save the slack series (ycycle) in this excel file after implementing a one-sided version of the standard HP-filter,
then I perform all the calculations to estimate the reduced-form representation of the closed-economy Phillips.



DATE: 7/1/2018