Table 3.
A Wide Data Structure With 1 Record per Risk Set for a Hypothetical Case-Cohort Study With 2 Casesa
| SETNO | Variable | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| z 1 | z 2 | z 3 | z 4 | z 5 | z 6 | z 7 | z 8 | z 9 | n tot | y | |
| 1 | 1.6 | 0.0 | 0.0 | 1.1 | 1.3 | 1.0 | 0.8 | 0.0 | 0.0 | 9 | 1 |
| 2 | 0.0 | 1.3 | 1.0 | 0.8 | 0.0 | 0.0 | 6 | 1 | |||
Abbreviation: SETNO, set number.
a “SETNO” indexes the risk set formed at each failure time, and z1 ... z9 denote covariate information, where z1 denotes the case’s covariate information and z2 ... z9 denote the other risk set members’ covariate information. The variable ntot indicates the size of each risk set (i.e., the total number of people in the risk set), and y is set to 1 and serves as the outcome variable associated with each record.