Catherine Y. Co, John S. Landon-Lane, and Myeong-Su Yun, "Inter-State Dynamics of Invention Activities, 1930-2000", Journal of Applied Econometrics, Vol. 21, No. 8, 2006, pp. 1111-1134. This file describes the data and programs used in the paper. The file patents.zip contains three files: ppc1930_2000.txt, runfomc.m, and patent.mat. The first two of these are ASCII files in DOS format, and the third is a MatLab data file. The data file (ppc1930_2000.txt) is in ASCII (text) format. The program (runfomc.m) is written in Matlab and utilizes the BACC program. The data file (patent.mat) is a Matlab data file that includes all the data, bin definitions and prior information needed as inputs to (runfomc.m). Data: The data used in this study are patent count per 100,000 inhabitants for each of the 48 continental states from 1930 to 2000. The data file contains 49 rows (48 states plus label) and 72 columns (71 years plus label). The states appear in alphabetical order, starting with Alabama and ending with Wyoming. Patent counts prior to 1963 include utility, design and plant patents. Data from 1930 to 1962 are from the U.S. Patent and Trademark Office, Technology Assessment and Forecast, Seventh Report. U.S. Department of Commerce, Arlington, VA: U.S. Dept. of Commerce, Patent and Trademark Office, Office of Technology Assessment and Forecast, March 1977. Data from 1963 to 1998 are from the U.S. Patent and Trademark Office, Information Product Division, Patenting Trends in the U.S., 1998, State/Country Report- All Years, 1963-1998. CD-Rom issued July 2000. Data for 1999 and 2000 are from the U.S. Patent and Trademark Office, Patent Counts by Country/State and Year, Utility Patents, January 1, 1963-December 31, 2001. Population data are from the Bureau of Economic Analysis, Department of Commerce, downloadable at http://www.bea.doc.gov/bea/regional/spi/. Programs: Supplied is a Matlab command file that will allow the user to replicate the computations reported in this paper. There is a file named (runfomc.m) that reproduces the results reported in the paper. Also attached is a Matlab data file (patents.mat) which contain the transformed data, bin and prior definitions used in the paper. This Matlab command file uses a number of functions from the Bayesian Analysis, Computation and Communication (BACC) project. You will need to install this program before running the routine. The routines needed can be obtained from the BACC homepage at the following WWW address: http://www2.cirano.qc.ca/~bacc/ All other subroutines used in the program are supplied within the file. To get help on how to use the Matlab file, type << help runfomc >> from within the directory that the command file is placed. Contact information: John S. Landon-Lane, 75 Hamilton St, New Brunswick, NJ 08901 USA. Fax: +-732-932-7416 Email: lane@econ.rutgers.edu