ERIC Number: ED399341
Record Type: Non-Journal
Publication Date: 1996-Apr
Reference Count: N/A
Student Choices: Using a Competing Risks Model of Survival Analysis.
Denson, Katy; Schumacker, Randall E.
By using a competing risks model, survival analysis methods can be extended to predict which of several mutually exclusive outcomes students will choose based on predictor variables, thereby ascertaining if the profile of risk differs across groups. The paper begins with a brief introduction to logistic regression and some of the basic concepts of survival analysis necessary to understand the competing risks survival analysis method. A data set is used to illustrate conducting the competing risks survival analysis, and results of that analysis for each competing risk and predictor variable are presented and interpreted. The procedure for conducting a competing risks survival analysis is similar to that of conducting a survival analysis with only one outcome. Data are prepared and coded in a like manner, and survival and hazard functions are interpreted by the same guidelines. However, in a competing risks survival analysis, the hazard probabilities for each competing outcome are recombined to create a complete profile of each risk for each time period in question. Data from the Dallas (Texas) public schools for 7,748 students (ninth graders in 1990-91) with no more than one of the defined competing risks (school leaving or completion) illustrate the analysis approach. Appendixes contain a Statistical Analysis System program for the analysis, withdrawal and dropout reasons for the student cohort, and a discussion of the transformation of data from person-data to person-period-data. (Contains 2 figures, 12 tables, and 33 references.) (SLD)
Publication Type: Reports - Evaluative; Speeches/Meeting Papers
Education Level: N/A
Authoring Institution: N/A