. Author manuscript; available in PMC: 2016 Jan 21.

Published in final edited form as: Ann Intern Med. 2015 Jul 21;163(2):127–134. doi: 10.7326/M14-1741

Table 3.

Treatment Contrast Measures by Sample Size: the Saxagliptin Study

	Entire study population (n=16,492)	Sub-samples of the total study population^** 25% (n=4123)	20% (n=3298)	15% (n=2474)
Hazard Ratio	(0.89, 1.12)	(0.80, 1.26)	(0.78, 1.29)	(0.76, 1.36)
RMST Difference^*	(−5, 4) days	(−9, 9) days	(−11,10) days	(−12, 12) days
Risk Difference on Day 900	(−1.2%, 0.9%)	(−2.3%, 2.0%)	(−2.6%, 2.2%)	(−2.9%, 2.6%)

Abbreviation: RMST = restricted mean survival time

The numbers are presented as point estimates (95% CI) and contrasts relative to the placebo group. For the difference metrics, a positive value indicates an increased risk of saxagliptin treatment.

Data are reconstructed from the original report. See Appendix 3 for details.

Restricted mean survival times are calculated to day 900.

^**

Estimates are based upon 1,000 repeated random samples of size 25%, 20% and 15% of the total study population.