Skip to main content

Table 2 Comparison of original data and simulated data covariate distributions

From: Generating high-fidelity synthetic time-to-event datasets to improve data transparency and accessibility

 

Original Data (%)

Simulated Data (%)

Absolute Difference (%)

Stage at Diagnosis

 Localized

3716 (40.91)

3724 (41.28)

0.37

 Regional

1148 (12.64)

1140 (12.64)

0.00

 Distant

2907 (32.00)

2836 (31.46)

0.54

 Missing

1313 (14.45)

1319 (14.62)

0.17

Anatomical Tumour Subsite

 Coecum and Ascending

3239 (35.66)

3227 (35.77)

0.11

 Transverse

1607 (17.69)

1569 (17.39)

0.30

 Sigmoid and Descending

3660 (40.29)

3659 (40.56)

0.27

 Other and NOS

578 (6.36)

566 (6.27)

0.07

Age Group

  < 45

379 (4.17)

368 (4.08)

0.09

 45–60

1338 (14.73)

1448 (16.05)

1.32

 60–75

3699 (40.72)

3604 (39.95)

0.77

  > 75

3688 (40.38)

3601 (39.91)

0.47

Sex

 Male

3799 (41.82)

3724 (41.28)

0.54

 Female

5285 (58.18)

5297 (58.72)

0.54

Vital Status

 Alive

3557 (39.16)

3467 (38.43)

0.73

 Dead

5527 (60.84)

5554 (61.57)

0.73