Data Sets
-
Innovation and Appropriability Survey
Replication package for “Innovation, Patenting and Appropriability: Survey Evidence from a Nationally Representative Sample of U.S. Firms,” Review of Economics and Statistics, forthcoming. Hosted at Harvard Dataverse.
-
Learning When to Quit
Replication package for “Learning When to Quit: An Empirical Model of Experimentation in Standards Development,” American Economic Journal: Microeconomics, 2025. Hosted at openICPSR.
-
R&D Tax Credits
Replication package for “Tax Credits and Small Firm R&D Spending,” American Economic Journal: Economic Policy, 2020. Hosted at openICPSR.
-
Intellectual Property Disclosures Data
Based on public disclosures of standards-related intellectual property at thirteen Standard Setting Organizations. The data are used in several of my papers, and include information on SSO, company, disclosure date, patent and/or application numbers, and licensing terms (when available). If you use these data, please cite our NBER Working Paper.
-
LEED Differentiation
Code, data and documentation for Rysman, Simcoe and Wang, “Differentiation Strategies in the Adoption of Environmental Standards: LEED from 2000 to 2014,” Management Science, 2020.
-
UPC Adoption
Although we cannot share the raw UPC registration files, we have posted our concordance between 1987 4-digit manufacturing and wholesale SIC codes and the merchandise line codes from the 1977, 1982, 1987 and 1992 Census of Retail Trade. We have also posted data and code to reproduce Figure 6 in the paper, along with data and code for creating the revenue-share weights described in Appendix A. If you use these data, please cite the NBER Working Paper.
-
eBay and Innovation
Data and code for “Patent Policy and American Innovation After eBay: An Empirical Examination.”
-
Standard Setting Committees
Stata code, IETF publication data and documentation for “Standard Setting Committees: Consensus Governance for Shared Technology Platforms,” American Economic Review, 2012. The files can be used to generate all tables and figures in the working paper. Please cite me if you use these data or programs. The AEA replication package is hosted at openICPSR.
-
Missing Names Data
Data (csv and Stata format) and code for “Status, Quality and Attention: What’s in a (Missing) Name?”, Management Science, February 2011, 274–290, co-authored with David Waguespack.
-
Patent Citation Age Profiles
The Stata code, data and documentation for Mehta, Rysman and Simcoe, “Identifying the Age Profile of Patent Citations: New Estimates of Knowledge Diffusion,” are available via the Journal of Applied Econometrics Data Archive. To find our materials, search the archive on any of the author last names.
-
Forms from the 1992 Census of Retail Trade
Download here.
-
Utah Diffs-in-Diffs Talk
Slides, data and example code for my survey of the recent diff-in-diffs literature for the Utah Winter Strategy Conference.
Stata Code
-
IV Fixed Effects Poisson
Stata code for the GMM estimators and simulation described in my paper on the Canadian R&D tax credit with Ajay Agrawal and Carlos Rosell.
-
Robust Standard Errors in the Fixed Effects Poisson (xtpqml)
In Stata, type
ssc install xtpqml. N.B. this code is superseded by thevce(robust)option in updates to Stata 11.
Wooldridge (JOE 1999) shows that the fixed effects Poisson estimator produces consistent estimates of the parameters in an unobserved components multiplicative panel data model under very general conditions. In fact, all that is required is an assumption about the conditional mean of the dependent variable. This is quite useful for two reasons. First, it implies that fixed effects Poisson estimation is appropriate for any non-negative dependent variable, not just count data that follow a Poisson distribution. Second, the estimator is robust to arbitrary patterns of serial correlation. In spite of these obvious attractions, the fixed-effect Poisson estimator does not appear to be widely used in practice. This is partly because statistical software does not generally allow computation of the appropriate (robust) standard errors for inference. This ado file runs Stata’s pre-packaged fixed effects Poisson estimator and then computes the robust standard errors suggested by Wooldridge (1999). -
Multinomial Agglomeration/Dispersion Test (mtad)
In Stata, type
ssc install mtad. A Stata r-class routine for calculating the index of agglomeration (or dispersion) proposed in Rysman and Greenstein (2003). This statistic is closely related to the Ellison and Glaeser (1998) “dartboard index” and can be used to test for dispersion.
NOTE: This Feb 2017 version supersedes the old MTAD code, which computes incorrect p-values!