Power analysis and sample size calculation for survival studies using Lachin-Foulkes and Schoenfeld methods from gsDesign package.
Usage
survivalpower(
data,
calculation_type = "sample_size",
method = "lachin_foulkes",
hazard_control = 0.083,
hazard_treatment = 0.042,
hazard_ratio = 0.6,
study_duration = 24,
accrual_duration = 12,
dropout_rate = 0,
allocation_ratio = 1,
alpha = 0.025,
beta = 0.1,
power = 0.9,
sided = "1",
entry_type = "unif",
gamma = 0,
sample_size_input = 100,
events_input = 50,
show_summary = TRUE,
show_formulas = FALSE,
show_interpretation = TRUE
)Arguments
- data
The data as a data frame (optional for power calculations).
- calculation_type
Type of power calculation to perform.
- method
Method for power/sample size calculation.
- hazard_control
Event hazard rate for control group (events per person-time unit).
- hazard_treatment
Event hazard rate for treatment group (events per person-time unit).
- hazard_ratio
Hazard ratio (treatment/control) for Schoenfeld method.
- study_duration
Maximum study duration (months or years).
- accrual_duration
Patient accrual (recruitment) duration.
- dropout_rate
Equal dropout hazard rate for both groups.
- allocation_ratio
Randomization ratio (treatment:control).
- alpha
Type I error rate (significance level).
- beta
Type II error rate (1 - power).
- power
Statistical power (1 - beta).
- sided
One-sided or two-sided statistical test.
- entry_type
Pattern of patient entry into the study.
- gamma
Rate parameter for exponential entry (0 if uniform entry).
- sample_size_input
Total sample size when calculating power.
- events_input
Number of events when calculating power with Schoenfeld method.
- show_summary
Whether to display comprehensive study design summary.
- show_formulas
Whether to display mathematical formulas used.
- show_interpretation
Whether to include clinical interpretation of results.
Value
A results object containing:
results$instructions | a html | ||||
results$power_results | a html | ||||
results$formulas | a html | ||||
results$interpretation | a html |
Examples
# \donttest{
# Example usage:
library(gsDesign)
#>
#> Attaching package: ‘gsDesign’
#> The following object is masked from ‘package:crosstable’:
#>
#> as_gt
# Sample size for survival study
nSurvival(lambda1 = 0.2, lambda2 = 0.1, Ts = 24, Tr = 12)
#> Fixed design, two-arm trial with time-to-event
#> outcome (Lachin and Foulkes, 1986).
#> Study duration (fixed): Ts=24
#> Accrual duration (fixed): Tr=12
#> Uniform accrual: entry="unif"
#> Control median: log(2)/lambda1=3.5
#> Experimental median: log(2)/lambda2=6.9
#> Censoring only at study end (eta=0)
#> Control failure rate: lambda1=0.2
#> Experimental failure rate: lambda2=0.1
#> Censoring rate: eta=0
#> Power: 100*(1-beta)=90%
#> Type I error (1-sided): 100*alpha=2.5%
#> Equal randomization: ratio=1
#> Sample size based on hazard ratio=0.5 (type="rr")
#> Sample size (computed): n=98
#> Events required (computed): nEvents=87
# Number of events required
nEvents(hr = 0.6, alpha = 0.025, beta = 0.1)
#> [1] 161.0686
# }