They interpret the first as supply disturbances, the second as demand disturbances. Copyright by American Economic Association. More about this item Statistics Access and download statistics. Christiano, Lawrence J, You can help correct errors and omissions. Corrections All material on this site has been provided by the respective publishers and authors.
|Country:||Bosnia & Herzegovina|
|Published (Last):||1 November 2012|
|PDF File Size:||5.65 Mb|
|ePub File Size:||2.31 Mb|
|Price:||Free* [*Free Regsitration Required]|
Data in the Federal Reserve Economic Database are updated over time because of the addition of new observations and revisions to existing observations, so the data I use will not be identical to those that Blanchard and Quah used. The dataset I use can be downloaded here. Blanchard and Quah use quarterly data from to , which is shown below. The authors adjust the raw data by removing the mean from GNP growth separately for the pre and post subsamples and by removing a linear time trend from the unemployment series.
Place GNP growth first in the ordering. In this matrix, three entries are free set to missing , and the remaining entry is forced to zero.
The authors use eight lags in the VAR, which I follow here. We estimate the SVAR and create impulse—responses with. We can view the impulse—responses with. One step is one quarter, so the figure depicts the impulse—response over a period of 10 years. Because GNP growth is ordered first, what Stata calls the "growth impulse" is what Blanchard and Quah call the "supply" shock. Similarly, the "unrate impulse" is the "demand" shock.
The top row shows the response of GNP growth and unemployment to a supply shock. GNP growth rises; the unemployment rate rises on impact, then falls after about one year, troughs after about two years, then slowly returns to its steady-state value. The bottom row shows the response to a "demand" shock.
In response to a "demand" shock, output growth falls initially before recovering after one year. Unemployment rises, peaking about a year after the shock before returning to its steady-state value. It is common instead to graph the response of the level of GNP.
This involves creating an impulse—response graph that cumulates the response of GNP growth but leaves the response of unemployment unchanged. This section looks inside the. Graphing the response of the level of GNP will also more clearly show the identification assumption we have made. You can access it with use just like any other dataset, and you can modify it just like any other dataset.
The following code block creates a new variable, csirf, that holds the cumulative impulse—response of GNP growth to each shock and does nothing to the impulse—response to the unemployment rate.
The second line guarantees that the data are sorted in the correct order: first by irfname, then by the impulse variable, then by the response variable, and finally by step. The third line generates our new variable, csirf, and loads it initially with the values in sirf. I save the results to a new irf file, lrirf2. The result is a variable that holds the cumulated response to changes in GNP growth and leaves the responses to unemployment unchanged, which is what we sought. We can graph the cumulated responses with.
This figure can be compared with figure 1 in Blanchard and Quah The figures match aside from the scale. Differences in the scale of the impulse—responses are due to differences in the size of the initial impulse. Stata uses a one-standard-deviation impulse, while Blanchard and Quah use a one-unit impulse. In the top-left panel we see that the supply shock increases the level of GNP permanently. In the bottom-left panel, we see that GNP falls in response to a demand shock but returns to zero or trend over time.
The long-run zero response in the bottom-left panel visually displays our identification assumption. Conclusion In this post, I outlined a procedure to estimate a SVAR with long-run restrictions and showed how to modify the resulting IRF file to contain a series that displays cumulative structural impulse—responses for some variables in the VAR.
Reference Blanchard, O. The dynamic effects of aggregate demand and supply disturbances. American Economic Review —
BLANCHARD AND QUAH 1989 PDF
Fischer, Stanley, Full references including those not matched with items on IDEAS More about this item Access and download statistics Corrections All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. See general information about how to correct material in RePEc. For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Michael P. If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item.
The Dynamic Effects of Aggregate Demand and Supply Disturbances
Data in the Federal Reserve Economic Database are updated over time because of the addition of new observations and revisions to existing observations, so the data I use will not be identical to those that Blanchard and Quah used. The dataset I use can be downloaded here. Blanchard and Quah use quarterly data from to , which is shown below. The authors adjust the raw data by removing the mean from GNP growth separately for the pre and post subsamples and by removing a linear time trend from the unemployment series. Place GNP growth first in the ordering. In this matrix, three entries are free set to missing , and the remaining entry is forced to zero.