Xiaodong Liu, John H. Kagel, and Lung-fei Lee, "Learning from Peers in Signaling Game Experiments", Journal of Applied Econometrics, Vol. 27, No. 7, 2012, pp. 1037-1058. The data are in two files. Both are provided in two formats, Excel (.xlsx) and plain text (.txt). "high_cost_entrants" contains the data for experiments with high-cost entrants. "cost_cost_entrants" contains the data for experiments with low-cost entrants. The two .xlsx files are zipped in the file lkl-data-xlsx.zip. The two text files are zipped in the file lkl-data-txt.zip. The text files are ASCII files in DOS format, so Unix/Linux users should use "unzip -a". In "high_cost_entrants", there are 4360 observations. In "low_cost_entrants", there are 9136 observations. Both files have 13 variables (columns). The variables are: 1. Experimental session number. 2. Experimental cycle number. 3. Experimental period number (within a cycle). 4. Team ID. In this paper, we focus on individual decision-making instead of team decision-making, so a team has only one Player A and one Player B. 5. Player A (Monopolist) ID. 6. Player B (Entrant) ID. 7. Player A's type, which is 1 if A is a high-cost type and 2 if A is a low-cost type. 8. Player B's choice, which is 1 if B chooses OUT and 2 if B chooses IN. 9. Player A's output (or price) choice. 10. Player A's payoff in the current period. 11. Player B's payoff in the current period. 12. Player A's gender, which is 0 if male, 1 if female, and 2 if unknown. 13. A indicator variable for experimental treatment given by 100*exper+10*ctx+pitts, where exper is 1 if the session recruits experienced subjects and 0 otherwise, ctx is 1 if the session uses natural language (meaningful context) for instructions and 0 otherwise, and pitts is 3 if the session was conducted at the University of Pittsburgh and 0 if it was conducted at the Ohio State University. Xiaodong Liu Assistant Professor Department of Economics University of Colorado at Boulder 256 UCB Boulder, CO 80309-0256 http://spot.colorado.edu/~xiaodong