Helmut Lütkepohl and Aleksei Netsunajev, "Disentangling Demand and Supply Shocks in the Crude Oil Market: How to Check Sign Restrictions in Structural VARs", Journal of Applied Econometrics, Vol. 29, No. 3, 2014, pp. 479-496. The data are in ASCII and Excel formats in the files oil-shock-data.txt and oil-shock-data.xls, respectively. The data were originally used in the article Kilian, L., Park, C. 2009. "The impact of oil price shocks on the U.S. stock market", International Economic Review 50(4): 1267-1287. We thank Lutz Kilian for making the data available. The variables are: percent change in global crude oil production log detrended index of real economic activity log of real price of crude oil The data are monthly for 1973m2 - 2006m12 (407 observations). The related estimation code is provided in Matlab. Various subprograms are called from the main program in main.m. Requirements for running the code: Matlab, Optimization_Toolbox, Statistics_Toolbox. To get the main results for the MS(3)-VAR(3) model considered in the paper, open the main.m file in Matlab and let it run. It will take a while to complete. The results will be printed on the Matlab command window, and then Figures 2b, 3, 4, and 5 will appear. All files except oil-shock-data.xls are ASCII text files in DOS formatted. These files are zipped in the file "ln-files.zip". Unix/Linux users should use "unzip -a". The file oil-shock-data.xls is a binary file. It is zipped in the file ln-data-xls.zip.