Charles Bellemare, Alexander Sebald, and Martin Strobel, "Measuring the 
Willingness to Pay to Avoid Guilt: Estimation using Equilibrium and 
Stated Belief Models", Journal of Applied Econometrics, Vol. 26, No. 3, 
2011, pp. 437-453.

A single data file is available, containing all data used to compute the
results of the paper.  The data are freely distributed by CentERdata
(http://www.centerdata.nl/en/).  

All data are in the file combinedtreatments.csv, which is an ASCII file in
DOS format. It is zipped in the file bss-data.zip. Unix/Linux users should
use "unzip -a".

The data file is organized as follows. The number of rows (N=1618)
corresponds to the number of cross-sectional observations.  Each column is a
separate variable. 

The variables used in the paper are the following (please refer to game tree
presented in the paper). 

choiceb1: Binary variable = 1 if choice of player B is r, 0 otherwise 
allocb11: Payoff of player A when player B chooses l. 
allocb12: Payoff of player B when player B chooses l
allocb21: Payoff of player A when player B chooses r
allocb22: Payoff of player B when player B chooses l
allocb13: Payoff of player C when player B chooses l
allocb14: Payoff of player D when player B chooses l
allocb23: Payoff of player C when player B chooses r
allocb24: Payoff of player D when player B chooses r
secblfl:  second-order beliefs of Player B associated with choosing l
newtreat: binary variable taking a value of 1 if data from treatment X,
          0 otherwise. 
 
For questions please contact

Charles Bellemare
Département d'économique
Université Laval
Québec (QC), Canada
G1V 0A6

cbellemare [AT] ecn.ulaval.ca