SH T00186 Phase II/ III Optimal Drospirenone (DRSP) Dose Finding and Placebo-controlled Comparative Study: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for SH T00186 Phase II/ III Optimal Drospirenone (DRSP) Dose Finding and Placebo-controlled Comparative Study (NCT00511797), a randomized phase 2, phase 3 study. The primary outcome is Change From Baseline in Total Dysmenorrheal Score at Final Evaluation.

2. Clinical Question

3. Trial Design

This was a randomized, double-blind, parallel-group Phase II/Phase III study with placebo control. It was multicenter and completed. The registry lists enrollment of 249. The study began in 2007-07 and primary completion was 2009-01. Bayer is identified as the sponsor. The registry’s brief summary states that the purpose was to investigate drospirenone efficacy for dysmenorrhea.

Participants were assigned to DRSP 1 mg/EE 20 μg, DRSP 2 mg/EE 20 μg, DRSP 3 mg/EE 20 μg, or placebo. In each active-treatment group, one tablet per day was taken for 24 days, followed by one placebo tablet per day for 4 days in each 28-day cycle. The placebo group took one placebo tablet per day throughout each 28-day cycle. Treatment was administered for 16 weeks, described in the official title as 4 cycles.

The primary outcome was change from baseline in total dysmenorrheal score at final evaluation, with the timeframe described as baseline and up to 4 cycles. The outcome population is identified as FAS. The record does not report the full eligibility criteria, allocation ratio, or details of how randomization and masking were implemented. The trial’s original sample-size justification and design assumptions are not reported in the registry record. Those omissions limit what can be concluded about the design rationale, but do not prevent describing the posted group summaries and comparisons.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Before assignment: Full Analysis Set (FAS) consisted of all patients who received at least one dose of study drug. Patients were analyzed as treated. FAS was the primary analysis set for all efficacy endpoints and safety analyses. Per Protocol Set (PPS) was a subgroup of the FAS. The PPS consisted of patients in the FAS who did not have major protocol deviations.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: FAS

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline in Total Dysmenorrheal Score at Final Evaluation, measured over Baseline and up to 4 Cycles (28 days per cycle).

The primary endpoint is change from baseline in total dysmenorrheal score at final evaluation, assessed over baseline and up to 4 cycles. The registry defines this score as the sum of two sub-scores: dysmenorrhea severity and use of analgesics. Each sub-score ranges from 0 for none to 3 for severe. The total score therefore has a best possible value of 0 and a worst possible value of 6.

This endpoint combines symptom severity with analgesic use, so it reflects two related dimensions of the trial’s clinical question in one measure. Change from baseline describes whether the average score at follow-up moved upward or downward relative to baseline. Because lower scores are better by definition, a negative change indicates a decrease in the measured score. The endpoint is continuous, and the registry reports means and standard deviations for the groups.

Using a defined composite can provide a compact summary, but it also means that the same total change could arise from different patterns in the component scores. The registry record does not report the separate primary-outcome component results in the information available for this analysis. Nor does it report a threshold for interpreting a change as important to participants. The outcome therefore supports comparison of recorded score changes, but does not by itself identify which component drove the group averages or how large a change would be meaningful in practice.

7. Results Posted in the Registry

• DRSP 1 mg/EE 20 μg: mean -2.50 versus -1.00 on control; difference -1.50 (95% CI -2.05 to -0.95), standardized effect d = -0.98; z-test p = <0.001.
• DRSP 2 mg/EE 20 μg: mean -2.10 versus -1.00 on control; difference -1.10 (95% CI -1.64 to -0.56), standardized effect d = -0.72; z-test p = <0.001.
• DRSP 3 mg/EE 20 μg: mean -1.90 versus -1.00 on control; difference -0.90 (95% CI -1.47 to -0.33), standardized effect d = -0.57; z-test p = 0.002.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Change From Baseline in Visual Analogue Scale (VAS) for Dysmenorrhea at Times Other Than During Menstruation at Cycle 4

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • DRSP 1 mg/EE 20 μg: mean -43.00 versus -10.30 on control; difference -32.70 (95% CI -42.11 to -23.29), standardized effect d = -1.37; z-test p = <0.001.
  • DRSP 2 mg/EE 20 μg: mean -39.50 versus -10.30 on control; difference -29.20 (95% CI -38.46 to -19.94), standardized effect d = -1.25; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for DRSP 1 mg/EE 20 μg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for DRSP 2 mg/EE 20 μg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Visual Analogue Scale (VAS) for Pelvic Pain at Times Other Than During Menstruation at Cycle 4

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • DRSP 1 mg/EE 20 μg: mean 5.90 versus 11.50 on control; difference -5.60 (95% CI -12.19 to 0.99), standardized effect d = -0.35; z-test p = 0.096.
  • DRSP 2 mg/EE 20 μg: mean 5.40 versus 11.50 on control; difference -6.10 (95% CI -12.75 to 0.55), standardized effect d = -0.38; z-test p = 0.072.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between DRSP 1 mg/EE 20 μg and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between DRSP 2 mg/EE 20 μg and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline in Endometrial Thickness After 4-cycle Treatment

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • DRSP 1 mg/EE 20 μg: mean -5.50 versus -0.10 on control; difference -5.40 (95% CI -6.76 to -4.04), standardized effect d = -1.52; z-test p = <0.001.
  • DRSP 2 mg/EE 20 μg: mean -7.10 versus -0.10 on control; difference -7.00 (95% CI -8.18 to -5.82), standardized effect d = -2.30; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for DRSP 1 mg/EE 20 μg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for DRSP 2 mg/EE 20 μg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The registry lists secondary outcomes covering pain and related symptoms, including dysmenorrhea outside menstruation, pelvic pain, lower abdominal and back pain, headache, nausea or vomiting, and other measures. Numeric summaries available for selected continuous outcomes show an overall pattern in which the two doses with reported VAS change summaries had more negative average change than placebo, and both reported comparisons had unadjusted intervals below zero. For the VAS pelvic-pain measure, the available recalculated intervals include zero. The endometrial-thickness summaries also show reductions in the active-dose groups relative to the placebo group, with recalculated intervals below zero for the reported comparisons.

These secondary findings are related to the primary question because they measure other aspects of pain or treatment-associated outcomes across the study period. They do not replace the primary endpoint, which combines dysmenorrhea severity and analgesic use. Secondary measures may help describe the broader pattern, but they are not proof that all symptoms changed in the same way. The registry does not report numerical results for every named secondary outcome in the information available for this analysis; detailed results for those outcomes are not reported in the registry record.

Unadjusted secondary results carry less weight when many outcomes and comparisons are examined. Even when each test is conducted correctly on its own, examining many tests increases the chance of at least one apparently unusual result arising by chance. The registry record does not report a multiplicity adjustment or a prespecified hierarchy for secondary outcomes. The observed secondary pattern is therefore best treated as supportive and descriptive, with particular caution around isolated p-values. It should not be used to make a broad claim that every measured symptom or outcome changed.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Change From Baseline in Total Dysmenorrheal Score at Cycle 1 up to Cycle 4
• Number of Participants With Severity of Lower Abdominal Pain During Menstruation at Cycle 4
• Number of Participants With Severity of Low Back Pain During Menstruation at Cycle 4
• Number of Participants With Severity of Headache During Menstruation at Cycle 4
• Number of Participants With Severity of Nausea or Vomiting During Menstruation at Cycle 4
• Number of Participants With Total Pelvic Pain Score at Times Other Than During Menstruation at Cycle 4
• Change From Baseline in Visual Analogue Scale (VAS) for Dysmenorrhea at Times Other Than During Menstruation at Cycle 4
• Visual Analogue Scale (VAS) for Pelvic Pain at Times Other Than During Menstruation at Cycle 4

9. Statistical Interpretation

10. Statistical Methods Explained

The primary endpoint is continuous: a score is measured at baseline and follow-up, and the reported quantity is change from baseline. The registry gives a mean and standard deviation for each group. A mean summarizes the group’s average change; a standard deviation describes how dispersed individual scores are around that average. Neither statistic shows the full distribution of individual outcomes.

What does the mean difference compare?

The recalculated contrasts subtract the placebo group’s posted mean change from the mean change in each active-treatment group. A negative mean difference means the active-group average was lower than the placebo average on the change score. Since a lower total dysmenorrheal score is better by the endpoint definition, the direction of the contrast can be understood in that context. These are simple, unadjusted comparisons based on posted summary statistics, not adjusted model estimates.

The recalculated comparison for DRSP 1 mg/EE 20 μg is -1.5, with an interval from -2.048 to -0.952 and p <0.001. For DRSP 2 mg/EE 20 μg, it is -1.1, with an interval from -1.644 to -0.556 and p <0.001. For DRSP 3 mg/EE 20 μg, it is -0.9, with an interval from -1.468 to -0.332 and p = 0.002. The p-values are unadjusted, so they do not account for the full set of possible comparisons unless a separate adjustment was made; such an adjustment is not reported in the registry record.

What does a confidence interval convey?

In general, a confidence interval expresses the range of estimates compatible with the observed data under the method used. A narrower interval indicates greater precision, while a wider interval indicates more uncertainty about the contrast. An interval that excludes zero is consistent with a nonzero difference under the stated analysis, but it does not establish clinical importance. The registry reports 95% confidence intervals for the sponsor’s analyses. A confidence level for the unadjusted recalculated intervals is not stated in the record information used here, so no confidence level is assigned to those intervals.

The sponsor’s results are described as t-tests, one-sided, and the reported parameter is median difference in final values. The recalculation instead compares arithmetic means of change from baseline using group means and standard deviations. A mean and a median are different summaries, and final values are not the same estimand as change from baseline. Differences between the two sets of estimates are therefore not necessarily contradictions. The sponsor’s p-values are reported as <0.001 for each comparison, with 95% confidence intervals. The registry record does not report enough detail to reconstruct the sponsor’s analysis procedure fully.

Why does variability matter?

Standard deviations describe variation among participant scores. Greater variability generally makes a group mean less precise for a given amount of information, while lower variability tends to make it more precise. The primary group standard deviations are 1.52, 1.51, 1.63, and 1.53 for the 1 mg, 2 mg, 3 mg, and placebo groups, respectively. These values describe the spread of observed changes, not uncertainty in the mean difference itself. The latter also depends on the amount of information in the comparison and the statistical method.

General statistical explanation: when outcomes are more variable than a simple model assumes, a model may understate uncertainty if it does not account for that extra variation. Such over-dispersion can make confidence intervals too narrow and p-values too small. The registry record does not describe an over-dispersion assessment, and the endpoint is reported as a continuous score rather than a count outcome. The point is a general one about matching methods to data, not a claim that over-dispersion occurred in this trial.

What can the p-values say?

A p-value describes how incompatible the observed data are with a specified null model, under the assumptions of the test. It is not the probability that the null hypothesis is true, nor does it measure the size or importance of a difference. The recalculated p-values are unadjusted. The sponsor’s analyses use one-sided tests as reported; the registry record does not report a rationale for the direction of those tests. The p-values should be read alongside estimates, intervals, endpoint definitions, and the limits of the analysis.

The registry identifies the primary population as FAS, but a fuller definition of that population and the handling of missing measurements are not reported in the registry record. The statistical analysis plan, covariate adjustments, and detailed assumptions for the sponsor’s analysis are also not reported. Consequently, the recalculation is useful as a transparent summary-statistic comparison, but it does not replace the sponsor’s analysis or recover unreported methods.

11. Confidence Intervals and Precision

The recalculated primary contrasts are accompanied by intervals that convey uncertainty around the estimated mean differences. For DRSP 1 mg/EE 20 μg versus placebo, the estimate is -1.5 and the interval extends from -2.048 to -0.952. For DRSP 2 mg/EE 20 μg versus placebo, the estimate is -1.1 and the interval extends from -1.644 to -0.556. For DRSP 3 mg/EE 20 μg versus placebo, the estimate is -0.9 and the interval extends from -1.468 to -0.332. Each interval is entirely below zero, so each is compatible with a negative mean difference under the recalculation method.

Precision is not the same as importance. An interval can indicate that a contrast is estimated with relatively limited uncertainty while still leaving open whether its size matters to participants. The registry record does not report a threshold for a clinically meaningful change in total dysmenorrheal score. The interval estimates also do not remove uncertainty about analysis choices, missing data, or multiplicity.

The sponsor reported 95% confidence intervals for final-value median differences: -2.00 to -0.89 for DRSP 1 mg/EE 20 μg, -1.64 to -0.55 for DRSP 2 mg/EE 20 μg, and -1.49 to -0.34 for DRSP 3 mg/EE 20 μg. These are sponsor-reported intervals and relate to the stated final-value median-difference analysis. They should be distinguished from the intervals around recalculated mean changes. The registry record does not report a confidence level for the recalculated intervals.

In general, an interval summarizes sampling uncertainty under a statistical method; it does not capture every source of uncertainty, such as measurement limitations or selective reporting. A confidence interval that excludes zero does not automatically imply a large or consequential effect. Its interpretation depends on the scale, endpoint definition, analysis method, and context of the study.

12. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The planning figures are illustrative estimates based on the observed effect, not the original trial design calculations. The registry record does not report the trial’s own sample-size assumptions or justification. For these continuous-outcome comparisons, the figures are participants per arm, not total events. The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The effect to detect is a stated fraction of the observed effect.

The 80% power column gives the estimated participants per arm for a planning scenario designed to have an 80% chance of detecting the specified effect under those assumptions, if the assumptions hold. The 90% power column gives the corresponding estimate for a 90% chance. These are planning concepts: power is the probability of detecting a specified effect under a particular design and model when that effect is present. The figures are not observed power.

Each scenario uses a different fraction of the observed effect. The full observed effect is the most optimistic planning target among the listed scenarios. Planning for 75% of the observed effect, or 50% of the observed effect, asks the study to detect a smaller difference. Smaller effects are harder to distinguish from random variation, so they require more participants per arm under otherwise similar assumptions. This explains why the estimates rise as the target effect becomes smaller.

The planning figures do not determine whether the completed study was adequately powered for its original question. They are retrospective illustrations tied to observed results and should not be treated as a substitute for a prospective design calculation. The trial’s original assumptions, including its intended target effect, are not reported in the registry record.

13. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = -1.500; pooled standard deviation σ = 1.525.
2. n = 2 × (1.96 + 0.842)² × 1.525² / -1.500² = 16.2, rounded up to 17 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
delta <- -1.5                      # observed difference in means
sigma <- 1.52487998687076                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(511797)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 17 (80% power), 22 (90% power)
 75% of observed effect: n per arm = 29 (80% power), 39 (90% power)
 50% of observed effect: n per arm = 65 (80% power), 87 (90% power)
power.t.test: 17.2 
Simulated power at n = 17 per arm: 0.795 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

14. Analyses Reported by the Sponsor

The registry reports sponsor analyses comparing each active dose with placebo. They are described as one-sided t-tests, with the parameter labelled median difference in final values. The reported estimates are -1.44 for DRSP 1 mg/EE 20 μg, -1.10 for DRSP 2 mg/EE 20 μg, and -0.92 for DRSP 3 mg/EE 20 μg. Each has a reported 95% confidence interval, and each reported p-value is <0.001.

The recalculated comparisons use the posted group means and standard deviations for change from baseline. They are unadjusted mean differences, with estimates of -1.5, -1.1, and -0.9, respectively. The sponsor’s final-value median-difference analyses and the recalculated mean-change analyses do not describe precisely the same quantity. Their estimates can therefore differ without indicating an inconsistency in the record.

The registry record does not report all details of the sponsor’s analysis, including its full model specification and missing-data procedures. The recalculation is a transparent, simple comparison of the posted summaries and should be read as a supplementary check, not as a replacement for the sponsor’s method. The record does not flag a discrepancy between the reported analyses and recalculation.

15. Multiplicity, Missing Data and Analysis Populations

The study includes a primary outcome, multiple dose-versus-placebo comparisons, and numerous secondary outcomes. Testing several hypotheses creates a multiplicity issue: the more comparisons considered, the greater the chance of obtaining at least one small p-value by chance if all corresponding null hypotheses are true. Statistical approaches can address this through adjustment, a prespecified testing sequence, or other design and analysis choices. The registry record does not report whether any such approach was planned or used.

The recalculated primary p-values are explicitly unadjusted. The sponsor’s reported analyses give p-values for each active dose versus placebo, but the registry information does not describe a family-wise multiplicity procedure or another adjustment. The secondary results are also reported without information on multiplicity control. Consequently, the individual p-values should not be interpreted as if they necessarily represent a single, prespecified test of the whole set of outcomes and comparisons.

The primary population is named as FAS, but its definition is not reported in the registry record. The handling of participants with missing endpoint measurements, withdrawals, protocol deviations, or incomplete follow-up is also not reported in the registry information available for this analysis. These details matter because the population included in an analysis and the assumptions used for missing data can affect estimates and uncertainty.

The record also does not report a detailed statistical analysis plan, the planned model for the primary endpoint, or whether adjustments were made for baseline measurements or other covariates. It identifies the sponsor’s method as a one-sided t-test for the reported comparisons, but does not give enough information to reconstruct all analytic decisions. These omissions do not establish that the analyses were inappropriate; they mean that readers cannot fully evaluate those decisions from the registry record. The findings should therefore be considered in light of the available definitions and results, while recognizing that multiplicity and missing-data methods remain unclear.

16. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: henoch-schonlein purpura (1.6%), lipoma (1.6%), appendicitis (1.6%), cervix carcinoma stage 0 (1.6%).

The registry reports participants at risk and participants affected for serious adverse events and for other adverse events. For serious adverse events, the affected counts are 1 in the DRSP 1 mg/EE 20 μg group, 2 in the DRSP 2 mg/EE 20 μg group, 0 in the DRSP 3 mg/EE 20 μg group, and 1 in the placebo group. The corresponding at-risk counts are 62, 63, 62, and 62. These are counts as recorded, not comparative estimates adjusted for differences in follow-up or participant characteristics.

The registry lists Henoch-Schonlein purpura, lipoma, appendicitis, and cervix carcinoma stage 0 among the serious-event terms, each at 1.6%. The record does not identify an arm for each listed term in the information available for this analysis. Death counts are not reported in the registry record.

Serious adverse event counts are not a complete safety comparison. The record also gives counts for participants affected by other adverse events, but the totals alone do not describe event severity, duration, recurrence, or causality. Safety interpretation depends on the full event details and observation period; these details are not reported in the registry record.

17. What the Result Does, and Does Not, Mean

The posted primary summaries show decreases in average total dysmenorrheal score from baseline in all four groups. The active-dose group averages were more negative than the placebo average. The unadjusted recalculated mean differences were also negative, and their intervals were below zero. The sponsor reported one-sided comparisons of final values with estimates in the same general direction. Together, these results describe an observed separation between the active-dose groups and placebo on the recorded primary outcome.

That description is not the same as a claim that a treatment works or does not work. Statistical summaries quantify the data under specific definitions and methods; they do not establish how an individual will respond, whether a difference is important to participants, or whether a result applies to people outside the study. The registry does not report a threshold for a clinically meaningful change in the total score, so the practical importance of the estimated differences cannot be determined from these statistics alone.

The findings also do not establish that one dose is superior to another. The reported primary comparisons are each against placebo, and the registry information does not report direct statistical comparisons among the three doses. The ordering of the group averages is not by itself evidence of a dose-response relationship. A pattern across group means can arise without a reliable difference between dose levels.

Uncertainty remains about several aspects of interpretation. The registry record does not report the original sample-size justification, detailed handling of missing data, or whether multiplicity was addressed. The sponsor’s reported final-value median-difference analyses differ in estimand from the recalculated mean-change contrasts. Secondary results can add context, but multiple outcomes and incomplete reporting of some secondary results limit their evidential weight. The appropriate conclusion is therefore a description of the posted results with attention to their methods and limits, not a broad clinical recommendation.

18. Why This Trial Matters Statistically

This trial provides a useful example of how a clinical question can be represented by a composite continuous endpoint and evaluated across several randomized groups. Total dysmenorrheal score combines symptom severity with analgesic use, while the reported change from baseline captures movement on that scale during follow-up. The score’s defined range and direction make the sign of a change interpretable, but the composite also makes it important to know whether its components moved together. Separate component results are not reported in the registry information available for this analysis.

The record also illustrates why estimates should be read alongside the methods used to produce them. The sponsor reports final-value median differences from one-sided t-tests, while the recalculation uses mean changes from baseline. Both summarize comparisons with placebo, but they do not estimate precisely the same quantity. Giving the estimand and method plainly helps prevent readers from treating similar-looking numbers as identical analyses.

Another statistical lesson is that a collection of favorable-looking comparisons needs context. The primary endpoint is only part of a study that also lists many secondary outcomes and dose comparisons. Unadjusted p-values do not account for that broader testing context unless a multiplicity strategy is specified. Here, such a strategy is not reported in the registry record.

Finally, planning illustrations based on observed effects are distinct from prospective design assumptions. They can show how a smaller target effect generally calls for more participants, but they cannot recover the trial’s original rationale or serve as evidence of observed power. The registry does not report the original sample-size justification, leaving that part of the design history uncertain.

19. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The primary score is a composite of dysmenorrhea severity and analgesic use. The registry defines how those components contribute to the score, but does not report their separate primary-outcome results in the information available for this analysis. A total-score change can therefore be described without determining which component accounts for it. The record also does not state a threshold for a meaningful change, limiting interpretation of the size of the differences.

The trial compares three active doses with placebo, but the posted primary comparisons are each against placebo. Direct dose-to-dose comparisons are not reported in the record information. Thus, the group averages should not be used to rank doses as statistically different. The trial’s original sample-size assumptions and justification are also not reported, so the planning illustrations cannot be used to judge its prospective design rationale.

Important analysis details are absent, including a full definition of FAS, handling of missing outcomes, detailed model specification, and multiplicity procedures. The sponsor’s comparisons are described as one-sided t-tests of final-value median differences, but the registry does not report enough information to reconstruct every analysis decision. The recalculation is unadjusted and uses mean changes, so it is a different summary rather than a reproduction of the sponsor’s analysis.

For secondary outcomes, the available numeric summaries cover selected measures, while the registry lists other outcomes without the corresponding results in the information available for this analysis. The safety counts likewise provide limited detail about event timing, severity, recurrence, and attribution. These limitations constrain the conclusions that can be drawn from the registry record without implying that unreported analyses or information were absent from the full study files.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: SH T00186 Phase II/ III Optimal Drospirenone (DRSP) Dose Finding and Placebo-controlled Comparative Study — NCT00511797.
• Registry record last updated 2017-01-26; status last verified 2016-11.
• Results first posted 2010-10-04.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

23. Record Summary

NCT00511797 is a completed, randomized, double-blind, parallel-group, placebo-controlled Phase II/Phase III study sponsored by Bayer. The registry lists enrollment of 249 and describes a 4-cycle comparison of DRSP 1 mg/EE 20 μg, DRSP 2 mg/EE 20 μg, DRSP 3 mg/EE 20 μg, and placebo for dysmenorrhea.

The primary endpoint was change from baseline in total dysmenorrheal score at final evaluation. Group mean changes were more negative in the three active-dose groups than in the placebo group. The registry reports sponsor comparisons of final values and supports simple unadjusted recalculations from posted summary statistics; these analyses differ in their stated estimands.

The record also lists secondary outcomes and adverse-event counts. Important details, including original sample-size assumptions, multiplicity handling, and missing-data procedures, are not reported in the registry record. The results describe the posted data and should be interpreted with those limitations in mind.