tests/testthat/_snaps/independent-test-summary.gsDesign.md

In gsDesign: Group Sequential Design

Test - gsSurv

[1] "Asymmetric two-sided group sequential design with non-binding futility bound, 3 analyses, time-to-event outcome with sample size 314 and 57 events required, 90 percent power, 2.5 percent (1-sided) Type I error to detect a hazard ratio of 0.4. Enrollment and total study durations are assumed to be 0.5 and 2 months, respectively. Efficacy bounds derived using a Hwang-Shih-DeCani spending function with gamma = -4. Futility bounds derived using a Hwang-Shih-DeCani spending function with gamma = -2."

Test - gsSurv change in snapshot

[1] "Asymmetric two-sided group sequential design with non-binding futility bound, 3 analyses, time-to-event outcome with sample size 628 and 137 events required, 90 percent power, 2.5 percent (1-sided) Type I error to detect a hazard ratio of 0.56. Enrollment and total study durations are assumed to be 0.5 and 2 months, respectively. Efficacy bounds derived using a Hwang-Shih-DeCani spending function with gamma = -4. Futility bounds derived using a Hwang-Shih-DeCani spending function with gamma = -2."

Test - gsSurv - test.type = 1

[1] "One-sided group sequential design with 3 analyses, time-to-event outcome with sample size 298 and 54 events required, 90 percent power, 2.5 percent (1-sided) Type I error to detect a hazard ratio of 0.4. Enrollment and total study durations are assumed to be 0.5 and 2 months, respectively. Efficacy bounds derived using a Hwang-Shih-DeCani spending function with gamma = -4."

Test - gsSurv - test.type = 2

[1] "Symmetric two-sided group sequential design with 3 analyses, time-to-event outcome with sample size 298 and 54 events required, 90 percent power, 2.5 percent (1-sided) Type I error to detect a hazard ratio of 0.4. Enrollment and total study durations are assumed to be 0.5 and 2 months, respectively. Bounds derived using a  Hwang-Shih-DeCani spending function with gamma = -4."

Test - gsSurv - test.type = 3

[1] "Asymmetric two-sided group sequential design with binding futility bound, 3 analyses, time-to-event outcome with sample size 308 and 56 events required, 90 percent power, 2.5 percent (1-sided) Type I error to detect a hazard ratio of 0.4. Enrollment and total study durations are assumed to be 0.5 and 2 months, respectively. Efficacy bounds derived using a Hwang-Shih-DeCani spending function with gamma = -4. Futility bounds derived using a Hwang-Shih-DeCani spending function with gamma = -2."

Test for gsSurv - hr0 < 1

[1] "Asymmetric two-sided group sequential design with non-binding futility bound, 3 analyses, time-to-event outcome with sample size 1506 and 311 events required, 90 percent power, 2.5 percent (1-sided) Type I error to detect a hazard ratio of 0.6 with a null hypothesis hazard ratio of 0.4. Enrollment and total study durations are assumed to be 0.5 and 2 months, respectively. Efficacy bounds derived using a Hwang-Shih-DeCani spending function with gamma = -4. Futility bounds derived using a Hwang-Shih-DeCani spending function with gamma = -2."

Test: nSurvival object

[1] "Asymmetric two-sided group sequential design with non-binding futility bound, 3 analyses, time-to-event outcome with sample size 530 and 100 events required, 90 percent power, 2.5 percent (1-sided) Type I error. Efficacy bounds derived using a Hwang-Shih-DeCani spending function with gamma = -4. Futility bounds derived using a Hwang-Shih-DeCani spending function with gamma = -2."

Test gsDesign summary for nSurvival

[1] "Asymmetric two-sided group sequential design with non-binding futility bound, 3 analyses, time-to-event outcome with sample size 430 and 82 events required, 90 percent power, 2.5 percent (1-sided) Type I error. Efficacy bounds derived using a Hwang-Shih-DeCani spending function with gamma = -4. Futility bounds derived using a Hwang-Shih-DeCani spending function with gamma = -2."

Test: nBinomial object

[1] "Asymmetric two-sided group sequential design with non-binding futility bound, 3 analyses, sample size 1963, 90 percent power, 2.5 percent (1-sided) Type I error. Efficacy bounds derived using a Hwang-Shih-DeCani spending function with gamma = -4. Futility bounds derived using a Hwang-Shih-DeCani spending function with gamma = -2."

Test gsDesign summary -test.type = 2

[1] "Symmetric two-sided group sequential design with 4 analyses, sample size 2, 90 percent power, 2.5 percent (1-sided) Type I error. Bounds derived using a  Pocock boundary."

gsDesign documentation built on Feb. 15, 2026, 5:06 p.m.