Shahram Amini and Christopher F. Parmeter, "Comparisons of Model
Averaging Techniques: Assessing Growth Determinants", Journal of
Applied Econometrics, Vol. 27, No. 5, 2012, pp. 870-876.

The file ap-files.zip contains two versions of the same R program
(MMA-Full-Version.R and MMA-Short-Version.R), plus three data files
(dw.txt, fls.txt, and mp.txt). These are all ASCII files in DOS
format. Unix/Linux users should use "unzip -a".

The file ap-dta.zip contains dw.dta, fls.dta, and mp.dta, which are
Stata data files. Since these are binary files, Unix/Linux users
should *not* use the "-a" option.


Computer program:
-----------------

The econometric models used in this study were implemented using the
programming language R and a recently-developed package, the BMS
package. The R codes to implement the estimation methods are written
by the authors and are available under in two versions of MMA.R. Both
the R package and BMS are publicly available under the terms of the
GNU General Public License. The documentation for the BMS package can
be found in:

Zeugner, S. & Feldkircher, M. (2009), "Benchmark Priors Revisited: On
Adaptive Shrinkage and the Supermodel Effect in Bayesian Model
Averaging", IMF Working Papers.


Data Description:
-----------------

All three datasets used in this study are publicly available on the
Journal of Applied Econometrics online data archive. Due to the fact
that these datasets are well documented, we briefly discuss them here
and direct the reader to more detailed treatments.

1. The fls.txt dataset is originally used in:

Fernandez, C., Ley, E. & Steel, M. (2001b), "Model uncertainty in
cross-country growth regressions", Journal of Applied Econometrics
16(5), 563-576.

There are 72 countries along with 41 potential growth determinants for
the period 1960 to 1992. This dataset is taken from the larger dataset
used by Sala-i-Martin (1997) for his study on robust determinants of
growth.

2. The dw.txt dataset comes from:

Doppelhofer, G. & Weeks, M. (2009), "Jointness of growth
determinants", Journal of Applied Econometrics 24(2), 209-244.

who used the data to study jointness of growth determinants. This data
set comprises 88 countries and 67 candidate variables in a cross
section for the period 1960 to 1996. All 67 of the variables used can
be found in data appendix B in their paper.

3. The mp.txt dataset that is used in:

Masanjala, W. & Papageorgiou, C. (2008), "Rough and Lonely Road to
Prosperity: A reexamination of the sources of growth in Africa using
Bayesian Model Averaging", Journal of Applied Econometrics 23(5),
671-682.,

They used the 37 sub-Saharan African countries within the FLS dataset
along with 24 of the 41 variables. See the appendix in MP for the
countries and variables used in this study.