Variations in NHL attendance: the impact of violence, scoring, and regional rivalries - Discrimination and The NHL

American Journal of Economics and Sociology, The, April, 2003 by Rodney J. Paul

Appendix I: Data Sources

Attendance (ATTN)--NHL.com--Team Logs

Opening Night (OPNIGHT)--NHL.com--Team Logs

Weekend (Fri, Sat, Sun)--NHL.com--Team Logs

Months (OCT, LATE)--NHL.com--Team Logs

Points Per Game--both Home and Visitor (PPG, VPPG)--NHL.com--Team Logs

Goals Per Game--both Home and Visitor (GPO, VFPG)--NHL.com--Team Logs

Fights Per Game-both Home and Visitor (FPG, VFPG)--NHL.com--Team Logs

Playoff Appearance (PLAYOFF)--The Hockey News Yearbook

Winning a Round in Playoffs (RD2)--The Hockey News Yearbook

Points (PTS)--The Hockey News Yearbook

Penalty Minutes (PM)--The Hockey News Yearbook

Goals For (GF)--The Hockey News Yearbook

Division Opponent (DIV)--The Hockey News Yearbook

Non-Conference Opponent (NONCON)--The Hockey News Yearbook

Canadian Opponent (CAN)--The Hockey News Yearbook

Population (POP)--For U.S. teams, from the US. Statistical Abstract for the Metro Area. For Canadian teams, data is from Statistics Canada.

Income Per Capita (INC)--For U.S. teams, from the US. Statistical Abstract for the Metro Area. For Canadian teams, data is from Statistics Canada. For conversion of income figures into U.S. dollars, exchange rate data from International Financial Statistics were used.

Appendix II: Penalty Minute Regression

The following are the results of the regression using penalty minutes per game (PMPG) as a proxy for violence instead of fights per game. The implications of the model are the same, except that the results appear slightly stronger and the R-squared of the regression is higher with the use of fights per game.