New Applications of Survival Analysis Modeling: Examining Intercollegiate Athletic Relationship Dissolution9. 0
.25
.5
.75
1
0 2 4 6 8 10
Analysis Time (Years)
95% CI Survivor function
Kaplan-Meier Survival Estimate
.05
.1
.15
.2
0 2 4 6 8 10
Analysis Time (Years)
95% CI Smoothed hazard function
Smoothed Hazard Estimate
11. Table 2.
Hierarchical survival analysis modeling results
Predictor Variables Model 1 Model 2 Model 3 Model 4
Economic
Lifetime Giving -0.92 (.00) -1.01 (.00) 6.23 (.00) 6.36 (.00)
Inflation 0.43 (.02) 0.43 (.02) 1.28 (.02) 1.00 (.02)
Economic Growth 0.54 (.02) 0.63 (.02) -0.06 (.02) 0.82 (.02)
Demographic
Alumni 1.53 (.72) 1.29 (.57) 1.23 (.57)
Live in State -7.24** (.04) -7.23** (.04) -7.30** (.04)
Years Since Graduation -0.62 (.00) 0.99 (.00) 1.02 (.00)
Retired -1.28 (.07) -2.77* (.06) -2.74* (.06)
Marketing
Times Contacted -5.78** (.00) -5.79** (.04)
Athletic
NCAA Tourney Wins -2.82* (.04)
Bowl Wins 0.21 (.07)
Log-likelihood -6551.93 -6633.79 -6604.31 -6600.83
Wald χ² 1.57 57.40** 33.43** 9.56*
Results from Cox model, with the Breslow method for handling ties; Standard errors clustered
by person. Standardized coefficients are listed, with standard errors in parentheses.
* p < .01; ** p < .001.
16. .05
.1
.15
.2
2 4 6 8
Analysis Time (Years)
Live in State = 1 Live in State = 0
Cox Model: Donor Location Differentials
.06.08
.1
.12.14.16
Smoothedhazardfunction
2 4 6 8
Analysis Time (Years)
Retired Currently Employed
Cox Model: Donor Employment Differentials