search

rpact-com / rpact

rpact: Confirmatory Adaptive Clinical Trial Design and Analysis
https://rpact-com.github.io/rpact/
23 stars 5 forks source link

Efficacy boundary (treatment effect scale) for two-sided tests not shown in summary() since version 4.0.0 #44

Closed wyf88 closed 3 months ago

wyf88 commented 3 months ago

I have noticed a change in the output of the summary function for the sample size/power calculation in version 4.0.0 compared with 3.5.1, where the efficacy boundary (treatment effect scale) for two-sided tests is not shown any more. The output for one-sided tests is not affected. I was wondering if this change is intended or not, as it was helpful to show the efficacy boundary for the study design.

rpact 4.0.0:

summary(sampleSizeResult <- getSampleSizeMeans(
    alternative = 10, stDev = 24, sided = 2,
    alpha = 0.05, beta = 0.2
))
Sample size calculation for a continuous endpoint

Fixed sample analysis, significance level 5% (two-sided).
The results were calculated for a two-sample t-test, H0: mu(1) - mu(2) = 0, 
H1: effect = 10, standard deviation = 24, power 80%.

Stage                               Fixed 
Efficacy boundary (z-value scale)   1.960 
Number of subjects                  182.8 
Two-sided local significance level 0.0500 
summary(sampleSizeResult <- getSampleSizeMeans(
    alternative = 10, stDev = 24, sided = 1,
    alpha = 0.025, beta = 0.2
))
Sample size calculation for a continuous endpoint

Fixed sample analysis, significance level 2.5% (one-sided).
The results were calculated for a two-sample t-test, H0: mu(1) - mu(2) = 0, 
H1: effect = 10, standard deviation = 24, power 80%.

Stage                               Fixed 
Efficacy boundary (z-value scale)   1.960 
Number of subjects                  182.8 
One-sided local significance level 0.0250 
Efficacy boundary (t)               7.006 

Legend:
  (t): treatment effect scale

rpact 3.5.1:

summary(sampleSizeResult <- getSampleSizeMeans(
    alternative = 10, stDev = 24, sided = 2,
    alpha = 0.05, beta = 0.2
))
Sample size calculation for a continuous endpoint

Fixed sample analysis, significance level 5% (two-sided).
The results were calculated for a two-sample t-test, H0: mu(1) - mu(2) = 0, 
H1: effect = 10, standard deviation = 24, power 80%.

Stage                               Fixed 
Efficacy boundary (z-value scale)   1.960 
Number of subjects                  182.8 
Two-sided local significance level 0.0500 
Lower efficacy boundary (t)        -7.006 
Upper efficacy boundary (t)         7.006 

Legend:
  (t): treatment effect scale
summary(sampleSizeResult <- getSampleSizeMeans(
    alternative = 10, stDev = 24, sided = 1,
    alpha = 0.025, beta = 0.2
))
Sample size calculation for a continuous endpoint

Fixed sample analysis, significance level 2.5% (one-sided).
The results were calculated for a two-sample t-test, H0: mu(1) - mu(2) = 0, 
H1: effect = 10, standard deviation = 24, power 80%.

Stage                               Fixed 
Efficacy boundary (z-value scale)   1.960 
Number of subjects                  182.8 
One-sided local significance level 0.0250 
Efficacy boundary (t)               7.006 

Legend:
  (t): treatment effect scale

Thank you!