Estibration
Edward J. Balistreri
Spring 2016
While office mates at the USITC Russell Hillberry and I coined
the term estibration to describe the procedures we were using
to replicate the non-linear empirical analysis of Anderson and van
Wincoop (2003). Inspired by Dawkins, Srinivasan, and Whalley's
chapter in the Handbook of Econometrics, "Calibration," the
intent of the new word was to push back on
Anderson and van Wincoop's argument that their model and method was
more credible because it was estimated rather than calibrated. An
argument they made most vehemently in their Brookings Trade
Forum paper. In company with Dawkins, Srinivasan, and Whalley (2001), we argued
that under consistent identifying assumptions estimation is
calibration and calibration is estimation. Our illustration of
this point using the Anderson and van Wincoop example was
eventually published in Economic Inquiry (in 2008, after
years of review at various other journals) under the title "The
Gravity Model: An Illustration of Structural Estimation as
Calibration." A reviewer advised us to adopt the published title, but the
original title is preserved here on the working paper
version, "Estibration: An
Illustration of Structural Estimation As Calibration"
(2005).
This page also includes the following link to the zip archive with the data and GAMS code used
in the analysis: estib.zip
References
Anderson, J.E., and E. van Wincoop (2002) "Borders, Trade, and
Welfare," in Brookings Trade Forum: 2001, edited by S.M.
Collins and D. Rodrik. Washington DC: Brookings Institution Press,
207-230.
Anderson, J.E., and E. van Wincoop (2003) "Gravity with Gravitas: A
Solution to the Border Puzzle," American Economic Review, 93,
170-191.
Balistreri, E.J., and R.H. Hillberry (2008) "The Gravity Model: an
Illustration of Structural Estimation as Calibration," Economic
Inquiry, 46(4), 511-527.
Dawkins, C., T.N. Srinivasan, and J. Whalley (2001) "Calibration," in
Handbook of Econometrics, Vol 5, Chapter 58, edited by J.J.
Heckman and E.E. Leamer. Amsterdam: Elsevier, 3655-3705.