Obtains the power given sample size or obtains the sample size given power for two-sample slope difference from the growth curve MMRM model.
getDesignSlopeDiffMMRM(
beta = NA_real_,
slopeDiffH0 = 0,
slopeDiff = 0.5,
stDev = 1,
stDevIntercept = 1,
stDevSlope = 1,
corrInterceptSlope = 0.5,
w = NA_real_,
N = NA_real_,
accrualTime = 0,
accrualIntensity = NA_real_,
piecewiseSurvivalTime = 0,
gamma1 = 0,
gamma2 = 0,
accrualDuration = NA_real_,
followupTime = NA_real_,
allocationRatioPlanned = 1,
normalApproximation = TRUE,
rounding = TRUE,
kMax = 1L,
informationRates = NA_real_,
efficacyStopping = NA_integer_,
futilityStopping = NA_integer_,
criticalValues = NA_real_,
alpha = 0.025,
typeAlphaSpending = "sfOF",
parameterAlphaSpending = NA_real_,
userAlphaSpending = NA_real_,
futilityBounds = NA_real_,
typeBetaSpending = "none",
parameterBetaSpending = NA_real_,
userBetaSpending = NA_real_,
spendingTime = NA_real_
)An S3 class designSlopeDiffMMRM object with three
components:
overallResults: A data frame containing the following variables:
overallReject: The overall rejection probability.
alpha: The overall significance level.
attainedAlpha: The attained significance level, which is
different from the overall significance level in the presence of
futility stopping.
kMax: The number of stages.
theta: The parameter value.
information: The maximum information.
expectedInformationH1: The expected information under H1.
expectedInformationH0: The expected information under H0.
drift: The drift parameter, equal to
theta*sqrt(information).
inflationFactor: The inflation factor (relative to the
fixed design).
numberOfSubjects: The maximum number of subjects.
studyDuration: The maximum study duration.
expectedNumberOfSubjectsH1: The expected number of subjects
under H1.
expectedNumberOfSubjectsH0: The expected number of subjects
under H0.
expectedStudyDurationH1: The expected study duration
under H1.
expectedStudyDurationH0: The expected study duration
under H0.
accrualDuration: The accrual duration.
followupTime: The follow-up time.
fixedFollowup: Whether a fixed follow-up design is used.
slopeDiffH0: The slope difference under H0.
slopeDiff: The slope difference under H1.
byStageResults: A data frame containing the following variables:
informationRates: The information rates.
efficacyBounds: The efficacy boundaries on the Z-scale.
futilityBounds: The futility boundaries on the Z-scale.
rejectPerStage: The probability for efficacy stopping.
futilityPerStage: The probability for futility stopping.
cumulativeRejection: The cumulative probability for efficacy
stopping.
cumulativeFutility: The cumulative probability for futility
stopping.
cumulativeAlphaSpent: The cumulative alpha spent.
efficacyP: The efficacy boundaries on the p-value scale.
futilityP: The futility boundaries on the p-value scale.
information: The cumulative information.
efficacyStopping: Whether to allow efficacy stopping.
futilityStopping: Whether to allow futility stopping.
rejectPerStageH0: The probability for efficacy stopping
under H0.
futilityPerStageH0: The probability for futility stopping
under H0.
cumulativeRejectionH0: The cumulative probability for
efficacy stopping under H0.
cumulativeFutilityH0: The cumulative probability for futility
stopping under H0.
efficacySlopeDiff: The efficacy boundaries on the slope
difference scale.
futilitySlopeDiff: The futility boundaries on the slope
difference scale.
numberOfSubjects: The number of subjects.
analysisTime: The average time since trial start.
settings: A list containing the following input parameters:
typeAlphaSpending: The type of alpha spending.
parameterAlphaSpending: The parameter value for alpha
spending.
userAlphaSpending: The user defined alpha spending.
typeBetaSpending: The type of beta spending.
parameterBetaSpending: The parameter value for beta spending.
userBetaSpending: The user defined beta spending.
spendingTime: The error spending time at each analysis.
allocationRatioPlanned: The allocation ratio for the active
treatment versus control.
accrualTime: A vector that specifies the starting time of
piecewise Poisson enrollment time intervals.
accrualIntensity: A vector of accrual intensities.
One for each accrual time interval.
piecewiseSurvivalTime: A vector that specifies the
starting time of piecewise exponential survival time intervals.
gamma1: The hazard rate for exponential dropout or
a vector of hazard rates for piecewise exponential dropout
for the active treatment group.
gamma2: The hazard rate for exponential dropout or
a vector of hazard rates for piecewise exponential dropout
for the control group.
w: The number of time units per measurement visit in a
period.
N: The number of measurement visits in a period.
stdDev: The standard deviation of the residual.
G: The covariance matrix for the random intercept and
random slope.
normalApproximation: The type of computation of the p-values.
If TRUE, the variance is assumed to be known, otherwise
the calculations are performed with the t distribution.
rounding: Whether to round up sample size.
The type II error.
The slope difference under the null hypothesis. Defaults to 0.
The slope difference under the alternative hypothesis.
The standard deviation of the residual.
The standard deviation of the random intercept.
The standard deviation of the random slope.
The correlation between the random intercept and random slope.
The number of time units per measurement visit in a period.
The number of measurement visits in a period.
A vector that specifies the starting time of
piecewise Poisson enrollment time intervals. Must start with 0, e.g.,
c(0, 3) breaks the time axis into 2 accrual intervals:
[0, 3) and [3, Inf).
A vector of accrual intensities. One for each accrual time interval.
A vector that specifies the starting time of
piecewise exponential survival time intervals. Must start with 0, e.g.,
c(0, 6) breaks the time axis into 2 event intervals:
[0, 6) and [6, Inf).
Defaults to 0 for exponential distribution.
The hazard rate for exponential dropout, or a vector of hazard rates for piecewise exponential dropout for the active treatment group.
The hazard rate for exponential dropout, or a vector of hazard rates for piecewise exponential dropout for the control group.
Duration of the enrollment period.
Follow-up time for the last enrolled subject.
Allocation ratio for the active treatment versus control. Defaults to 1 for equal randomization.
The type of computation of the p-values.
If TRUE, the variance is assumed to be known, otherwise
the calculations are performed with the t distribution. The
degrees of freedom for the t-distribution for testing the slope
difference is calculated using the containment method, and
is equal to the total number of observations minus two times
the total number of subjects. The exact calculation using the
t distribution is only implemented for the fixed design.
Whether to round up sample size. Defaults to 1 for sample size rounding.
The maximum number of stages.
The information rates. Defaults to
(1:kMax) / kMax if left unspecified.
Indicators of whether efficacy stopping is allowed at each stage. Defaults to true if left unspecified.
Indicators of whether futility stopping is allowed at each stage. Defaults to true if left unspecified.
Upper boundaries on the z-test statistic scale for stopping for efficacy.
The significance level. Defaults to 0.025.
The type of alpha spending. One of the following: "OF" for O'Brien-Fleming boundaries, "P" for Pocock boundaries, "WT" for Wang & Tsiatis boundaries, "sfOF" for O'Brien-Fleming type spending function, "sfP" for Pocock type spending function, "sfKD" for Kim & DeMets spending function, "sfHSD" for Hwang, Shi & DeCani spending function, "user" for user defined spending, and "none" for no early efficacy stopping. Defaults to "sfOF".
The parameter value for the alpha spending. Corresponds to Delta for "WT", rho for "sfKD", and gamma for "sfHSD".
The user defined alpha spending. Cumulative alpha spent up to each stage.
Lower boundaries on the z-test statistic scale
for stopping for futility at stages 1, ..., kMax-1. Defaults to
rep(-6, kMax-1) if left unspecified. The futility bounds are
non-binding for the calculation of critical values.
The type of beta spending. One of the following: "sfOF" for O'Brien-Fleming type spending function, "sfP" for Pocock type spending function, "sfKD" for Kim & DeMets spending function, "sfHSD" for Hwang, Shi & DeCani spending function, "user" for user defined spending, and "none" for no early futility stopping. Defaults to "none".
The parameter value for the beta spending. Corresponds to rho for "sfKD", and gamma for "sfHSD".
The user defined beta spending. Cumulative beta spent up to each stage.
A vector of length kMax for the error spending
time at each analysis. Defaults to missing, in which case, it is the
same as informationRates.
Kaifeng Lu, kaifenglu@gmail.com
We use the following random-effects model to compare two slopes: $$y_{ij} = \alpha + (\beta + \gamma x_i) t_j + a_i + b_i t_j + e_{ij},$$ where
\(\alpha\): overall intercept common across treatment groups due to randomization
\(\beta\): slope for the control group
\(\gamma\): difference in slopes between the active treatment and control groups
\(x_i\): treatment indicator for subject \(i\), 1 for the active treatment and 0 for the control
\(t_j\): time point \(j\) for repeated measurements, \(t_1 = 0 < t_2 < \ldots < t_k\)
\((a_i, b_i)\): random intercept and random slope for subject \(i\), \(Var(a_i) = \sigma_a^2\), \(Var(b_i) = \sigma_b^2\), \(Corr(a_i, b_i) = \rho\)
\(e_{ij}\): within-subject residual with variance \(\sigma_e^2\)
By accounting for randomization, we improve the efficiency for estimating the difference in slopes. We also allow for non-equal spacing of the time points and missing data due to dropouts.
Daniel O. Scharfstein, Anastasios A. Tsiatis, and James M. Robins. Semiparametric efficiency and its implication on the design and analysis of group-sequential studies. Journal of the American Statistical Association 1997; 92:1342-1350.
(design1 <- getDesignSlopeDiffMMRM(
beta = 0.2, slopeDiff = log(1.15)/52,
stDev = sqrt(.182),
stDevIntercept = sqrt(.238960),
stDevSlope = sqrt(.000057),
corrInterceptSlope = .003688/sqrt(.238960*.000057),
w = 8,
N = 10000,
accrualIntensity = 15,
gamma1 = 1/(4.48*52),
gamma2 = 1/(4.48*52),
accrualDuration = NA,
followupTime = 8,
alpha = 0.025))
Run the code above in your browser using DataLab