GA YAZ ACNE in China Phase III: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for GA YAZ ACNE in China Phase III (NCT00818519), a randomized phase 3 study. The primary outcome is Percent Change From Cycle 6 to Baseline in the Total Lesion Count (Open and Closed Comedones, Papules, Pustules, and Nodules) in the FAS (Full Analysis Set).

2. Clinical Question

The trial is identified as a study of YAZ for acne in China. Its stated purpose was to evaluate efficacy and safety over 6 treatment cycles. The primary comparison is between randomized treatment groups, not a before-and-after comparison within one group alone. The posted result is a group-level summary, so it does not describe the response of every participant or establish why an individual’s lesion count changed.

3. Trial Design

The registry identifies this as a Phase 3, randomized, double-blind, parallel-group, placebo-controlled study. The record reports enrollment of 179 and status as completed. The recorded start was 2008-12, and primary completion was 2010-05. Bayer is listed as sponsor.

Participants were assigned to YAZ or placebo. The active regimen used 24 consecutive days of active tablets and 4 consecutive days of inactive tablets; the placebo tablets were inert and matched in appearance and color. The primary endpoint was measured at baseline and at Cycle 6, on Day 15±3 days of Treatment Cycle 6. The trial also listed assessments at Cycle 1 and Cycle 3, as well as other lesion-count outcomes.

The primary outcome summaries include 87 participants in the YAZ group and 86 in the placebo group. These are the group counts reported for that outcome; they should not be read as a complete account of participant flow. The registry record does not report the randomization sequence method, allocation concealment, or the exact operational details of masking. It also does not report a protocol-level description of adherence or how treatment discontinuations were handled.

The primary endpoint names the FAS as its analysis population. The registry record does not report how the FAS was defined, which participants were excluded from that population, or whether missing endpoint measurements were imputed. Although the trial is described as double-blind, the information available in the registry record does not specify which roles were masked or when masking could be broken.

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: 193 participants screened, 14 failed screening: withdrawal of consent (7), inclusion/exclusion criteria not met (6), participant lost/no further information available (1). study drug intake was unknown (3) and 3 participants to whom study drug was never administered (withdrawal of consent or lost to follow-up) were excluded from FAS.

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 Percent Change From Cycle 6 to Baseline in the Total Lesion Count (Open and Closed Comedones, Papules, Pustules, and Nodules) in the FAS (Full Analysis Set), measured over Cycle 6 (Day 15±3 days of Treatment Cycle 6) and Baseline.

The primary endpoint is the percent change from baseline to Cycle 6 in total facial lesion count. A trained designee counted lesions across the entire face, separating non-inflammatory open and closed comedones from inflammatory papules, pustules, and nodules. The measure combines these lesion types into a total rather than treating each type as the primary outcome.

The registry defines the calculation as baseline total lesion count minus Cycle 6 total lesion count, divided by baseline total lesion count, multiplied by 100. The direction is therefore important: a larger percent change indicates a larger reduction in the counted lesions. The endpoint is a continuous measure, and the posted summaries report group means and standard deviations.

Using a change expressed relative to baseline can make results easier to interpret when participants begin with different lesion counts, although it does not remove all differences in starting values or measurement. The endpoint also gives a single summary across multiple lesion types, which can obscure patterns in individual components. The registry lists separate secondary assessments for some lesion types and for the Investigator Static Global Assessment (ISGA), but those do not replace the prespecified primary endpoint.

The primary endpoint was assessed at Cycle 6, specifically on Day 15±3 days of Treatment Cycle 6. The registry record does not report further details about the assessment procedures, such as inter-rater reliability or whether the same assessor evaluated a participant at each visit.

7. Results Posted in the Registry

• EE20/Drospirenone (YAZ, BAY86-5300): mean 66.79 versus 37.71 on control; difference 29.08 (95% CI 3.13 to 55.03), standardized effect d = 0.34; z-test p = 0.028.

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.

Percentage of Participants Classified as "0" or "1" on the 6-point ISGA (Investigator Static Global Assessment) Scale at Cycle 1

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • EE20/Drospirenone (YAZ, BAY86-5300): 1.2% (1/84) versus 0.0% (0/84) on control; risk difference 1.2 percentage points (95% CI -1.1 to 3.5); unadjusted two-proportion z-test p = 0.316.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between EE20/Drospirenone (YAZ, BAY86-5300) and the control. The interval gives the range of effects that remain compatible with the data.

Percentage of Participants Classified as "0" or "1" on the 6-point ISGA (Investigator Static Global Assessment) Scale at Cycle 3

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • EE20/Drospirenone (YAZ, BAY86-5300): 2.5% (2/81) versus 4.9% (4/81) on control; risk difference -2.5 percentage points (95% CI -8.3 to 3.3), risk ratio 0.50 (0.09–2.65); unadjusted two-proportion z-test p = 0.405.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between EE20/Drospirenone (YAZ, BAY86-5300) and the control. The interval gives the range of effects that remain compatible with the data.

Percentage of Participants Classified as "0" or "1" on the 6-point ISGA (Investigator Static Global Assessment) Scale at Cycle 6

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • EE20/Drospirenone (YAZ, BAY86-5300): 49.3% (36/73) versus 18.3% (13/71) on control; risk difference 31.0 percentage points (95% CI 16.4 to 45.6), risk ratio 2.69 (1.56–4.64); unadjusted two-proportion z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically higher for EE20/Drospirenone (YAZ, BAY86-5300) than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The secondary outcomes extend the primary question in two ways: repeated ISGA assessments describe the proportion classified as “0” or “1” at different visits, while other listed outcomes address inflammatory and non-inflammatory lesions and individual inflammatory lesion types. The posted secondary findings therefore offer additional views of acne status and lesion change, rather than a single duplicate of the primary total-lesion-count measure.

The early and later ISGA results do not show one consistent pattern across visits. At Cycle 1, the group percentages were both near zero; at Cycle 3, the placebo percentage was higher; by Cycle 6, the YAZ percentage was higher. These assessments describe different points in the treatment period and a thresholded categorical outcome, whereas the primary result is a continuous percent change in total lesion count at Cycle 6. The two types of measure need not move in lockstep because they summarize different features of the data.

The Cycle 6 ISGA comparison is directionally consistent with the primary result in that its posted group percentages favor a higher share classified as “0” or “1” in the YAZ group. This is contextual support, not a replacement for the primary analysis. Different outcome definitions, assessment timing, and analysis populations can produce different estimates. The registry record does not report a prespecified testing hierarchy linking these outcomes to the primary endpoint.

Unadjusted secondary results carry less weight as confirmatory evidence when many outcomes and time points are examined. General statistical principle: the more comparisons considered, the greater the opportunity for some estimates to look notable by chance. The registry record does not report multiplicity adjustment or a statistical plan specifying which secondary tests were confirmatory. Secondary outcomes can help describe consistency and generate questions, but should be interpreted alongside the primary result and the limits of the reported analysis information.

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

• Percentage of Participants Classified as "0" or "1" on the 6-point ISGA (Investigator Static Global Assessment) Scale at Screening Visit
• Percentage of Participants Classified as "0" or "1" on the 6-point ISGA (Investigator Static Global Assessment) Scale at Cycle 1
• Percentage of Participants Classified as "0" or "1" on the 6-point ISGA (Investigator Static Global Assessment) Scale at Cycle 3
• Percentage of Participants Classified as "0" or "1" on the 6-point ISGA (Investigator Static Global Assessment) Scale at Cycle 6
• Percent Change From Cycle 6 to Baseline in Inflammatory Lesion Count (Papules, Pustules, and Nodules), Non-inflammatory Lesion Count
• Percent Change From Cycle 6 to Baseline in Lesion Count of Papules
• Percent Change From Cycle 6 to Baseline in Lesion Count of Pustules
• Percent Change From Cycle 6 to Baseline in Lesion Count of Nodules

9. Statistical Interpretation

10. Statistical Methods Explained

The primary endpoint is continuous: each participant’s outcome is a percent change in total lesion count, and the registry reports a mean and standard deviation for each group. A mean describes the group’s average outcome. A standard deviation describes how dispersed individual values are around that average; it is not a confidence interval and does not describe uncertainty in the mean itself.

What does the mean difference represent?

The posted comparison is a mean difference between the YAZ and placebo group summaries. It is reported as 29.08, with group means of 66.79 and 37.71. Since the endpoint is defined so that larger percent change indicates a larger reduction in lesions, a positive contrast in this direction corresponds to a higher average percent change in the YAZ group. This is a comparison of group averages, not a statement that every participant had a change of that size.

For a randomized parallel-group trial, comparing outcomes between assigned groups is the central contrast. Randomization is intended to support a fair comparison by distributing participant characteristics across groups on average, but it does not guarantee identical group composition. The registry record does not report the method for generating or concealing the allocation, nor does it give baseline summaries that would help describe the realized balance.

What does the standard deviation tell the reader?

The posted standard deviations are 31.45 in the YAZ group and 118.7 in the placebo group. The difference in spread matters because group means can hide heterogeneous participant outcomes. A large standard deviation may reflect a wide range of observed changes, and it can make a mean less representative of many individual values. General statistical principle: when variability differs substantially between groups, methods that assume a common variance may be less suitable than methods that allow group-specific variability. The registry record does not report the variance model or test used for the primary analysis.

The registry also lists a pooled standard deviation of 86.63 for the posted comparison. A pooled standard deviation combines group variability under a particular calculation. Its presence does not establish which inferential method the sponsor used, and the record does not report the assumptions behind that pooled value. The comparison includes a standardized effect value of 0.336; this is a scale-free summary based on the posted effect and variability, not a direct clinical outcome measure.

How should the p-value be read?

The unadjusted p-value for the primary comparison is 0.028. In general, a p-value describes how unusual data at least as incompatible with a specified null hypothesis would be if that null hypothesis and the test assumptions held. It is not the probability that the null hypothesis is true, nor the probability that the result occurred by chance. It does not measure the size or importance of the outcome difference. The registry record does not report the test statistic, the precise test, or the assumptions used to obtain this p-value.

“Unadjusted” indicates that the listed value is not reported as corrected for multiple comparisons. It does not mean that the estimate has been adjusted for baseline characteristics. No adjusted primary p-value or adjusted model result is reported in the registry record. The sponsor’s own analysis takes precedence when available; the registry record does not report a sponsor analysis output for this result.

What does the confidence interval add?

The interval from 3.131 to 55.03 describes uncertainty around the posted mean difference. General statistical principle: a confidence interval is constructed by a method that, under its assumptions and repeated use, has a stated coverage property. Its width reflects both the estimated variability and the amount of information available. A narrow interval indicates greater precision than a wide interval on the same scale. The registry record does not state the confidence level or interval-construction method, so those details should not be inferred.

The interval is not a range containing every participant’s outcome, and it is not a guarantee that the true difference lies within those exact endpoints. It is an uncertainty summary for the group contrast. Reading the point estimate, interval, and standard deviations together gives a fuller account than relying on the p-value alone.

What is and is not known about the analysis population?

The primary endpoint is labeled as analyzed in the FAS. An analysis population is the set of participants whose data enter a particular analysis. The registry record does not define the FAS or state whether it follows an intention-to-treat principle. It also does not report exclusions, missing-data handling, sensitivity analyses, or the number of participants with observed primary outcomes at each assessment beyond the group counts shown for the result. These gaps limit assessment of how robust the primary estimate is to choices about incomplete data.

The record lists 13 outcome measures, and it reports 11 secondary outcomes as posted. It does not report the analysis plan for selecting among those outcomes, the hierarchy of tests, or a correction for multiple testing. General statistical principle: testing many outcomes or time points increases the chance of seeing an apparently notable result even if no underlying differences exist. Adjustment methods and prespecified outcome hierarchies can address this issue, but neither is described in the registry record.

In short, the posted summary supports a clear description of the observed group means, their contrast, and its uncertainty. It offers less detail about the modeling, missing-data procedures, and multiplicity strategy behind the inferential results. Those distinctions matter when evaluating how strongly the registry results support a broader conclusion.

11. Confidence Intervals and Precision

The primary mean difference is 29.08, and its confidence interval runs from 3.131 to 55.03. The interval gives an uncertainty range for the estimated difference in mean percent change. The estimate is therefore not precise enough to identify one exact value: the endpoints allow for a range of plausible effect sizes under the interval’s method. The registry record does not report the confidence level or the method used to calculate the interval.

The interval’s lower endpoint is above zero, while the interval still spans values that differ substantially from the point estimate. This means the posted result is compatible with a positive group difference across the interval, but the magnitude remains uncertain. The unadjusted p-value is 0.028; it answers a different question from the interval and should not be used as a substitute for examining the range of estimates.

The group standard deviations, 31.45 for YAZ and 118.7 for placebo, also help describe the data. They reflect variation among endpoint values, whereas the confidence interval reflects uncertainty in the group contrast. The larger placebo spread suggests that the group average may conceal considerable variation in individual outcomes. Neither the standard deviations nor the interval show the full shape of the outcome distributions.

Precision depends on the analysis population and the amount and quality of available outcome data. The primary summaries list 87 participants for YAZ and 86 for placebo, but the registry record does not detail missing outcomes, exclusions, or sensitivity analyses. Those omissions make it harder to judge whether the reported interval fully captures uncertainty arising from incomplete data or analytic choices.

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 illustrations based on the observed effect, not the trial’s original design calculations. For this continuous primary outcome, 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 the two arms, and a normal approximation. Each planning scenario uses the stated fraction of the observed effect as the effect to detect. The trial’s own original sample-size assumptions are not reported in the registry record.

For planning for 100% of the observed effect, the illustration gives 140 participants per arm for 80% power and 187 participants per arm for 90% power. For planning for 75% of the observed effect, it gives 248 participants per arm for 80% power and 332 participants per arm for 90% power. For planning for 50% of the observed effect, it gives 558 participants per arm for 80% power and 746 participants per arm for 90% power.

In plain language, the 80% power column represents the illustrated number of participants per arm for a design with an 80% chance of detecting the specified effect under the stated assumptions, if that effect is real and the assumptions hold. The 90% column gives the corresponding planning target for 90% power. These are design concepts, not guarantees about a particular future study. Smaller effects require more participants to detect reliably, which is why the illustrated targets rise as the planned effect becomes a smaller fraction of the observed effect.

These figures are not observed power. They do not measure how much power the completed trial had after its results were known. They are planning illustrations calculated from the observed effect and the listed assumptions; different assumptions or an effect smaller than the observed estimate would lead to different planning requirements.

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 = 29.080; pooled standard deviation σ = 86.629.
2. n = 2 × (1.96 + 0.842)² × 86.629² / 29.080² = 139.3, rounded up to 140 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 <- 29.08                      # observed difference in means
sigma <- 86.6292736977721                     # 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(818519)
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 = 140 (80% power), 187 (90% power)
 75% of observed effect: n per arm = 248 (80% power), 332 (90% power)
 50% of observed effect: n per arm = 558 (80% power), 746 (90% power)
power.t.test: 140.3 
Simulated power at n = 140 per arm: 0.801 (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. Multiplicity, Missing Data and Analysis Populations

The registry record lists multiple outcomes, including the primary total-lesion-count endpoint, several ISGA assessments, and lesion-specific measures. It reports 13 outcome measures overall and 11 secondary outcomes as posted. The record does not report a multiplicity strategy, such as a hierarchy of hypotheses, a family of tests, or an adjustment to account for multiple comparisons. It also does not report whether any secondary outcomes were designated as confirmatory.

General statistical principle: when multiple outcomes, visits, or subgroup comparisons are examined, the chance of at least one apparently notable result can increase. A plan set before results are known can help distinguish confirmatory testing from exploratory description. Without the plan or adjustment details in the registry record, the secondary p-values should be treated as unadjusted evidence and not as though they were protected against multiple testing.

The primary comparison also has an unadjusted p-value. The registry record does not explain whether it was part of a larger testing family or whether an ordered testing strategy was intended. The reported p-value and confidence interval remain useful descriptions of the posted primary contrast, but the broader inferential context is not fully documented.

The primary outcome population is labeled FAS, but the registry record does not define that population. It does not report how participants with missing Cycle 6 measurements were handled, whether any imputation was used, or whether analyses under alternative missing-data assumptions were conducted. The group counts in the endpoint summary describe the reported analysis, but they do not explain why other enrolled participants may not appear in that summary.

Missing-data handling can matter if the availability of a measurement is related to treatment assignment or participant outcome. General statistical principle: complete-case summaries describe participants with observed data, and may not represent all randomized participants when missingness is informative. The available record does not establish whether that concern affected this trial. Nor does it report a sensitivity analysis to assess the effect of alternative assumptions. These are reporting limitations, not proof that the analysis was biased.

15. 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 1% reporting threshold.

Most frequent non-serious adverse event terms

The registry reports zero serious adverse events among 87 participants at risk in the YAZ group and zero among 86 participants at risk in the placebo group. These figures describe serious adverse events recorded for the listed groups during the reporting period. They do not establish that no serious events could occur, and the registry record does not give further event definitions or a detailed account of the reporting window.

Other adverse events were reported for 34 participants at risk in the YAZ group and 19 participants at risk in the placebo group. These are participant counts with other adverse events, not counts of all event episodes or a description of their severity, duration, or relationship to study treatment. The record does not report a list of the most common event terms in the information available for this analysis.

Death counts are not reported in the registry record. Safety counts should be interpreted as descriptive reporting from this trial, not as a complete comparison of every potential risk. The record’s adverse-event summary alone cannot establish whether a treatment is safe or unsafe.

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

The primary result describes the average percent change in total lesion count at Cycle 6 for participants included in the FAS summaries. The YAZ group had a higher mean percent change than the placebo group, and the posted unadjusted mean difference is 29.08. The registry defines larger percent change as a greater reduction in counted lesions. This is a group-level finding at a specified follow-up point, within the trial’s population and treatment regimen.

The estimate does not mean that every participant in the YAZ group had a larger reduction than every participant in the placebo group. The standard deviations show variation in participant outcomes, particularly in the placebo group. Nor does the result tell the reader how participants felt, how acne affected daily life, or whether the observed change was important to individual participants; those outcomes are not described by the primary endpoint.

The confidence interval, from 3.131 to 55.03, conveys uncertainty in the estimated group contrast, and the unadjusted p-value is 0.028. These statistical summaries do not establish clinical importance. The registry record does not provide a threshold for a meaningful difference in this endpoint or describe an adjusted analysis. It also does not provide enough detail about missing data or the analysis plan to resolve all concerns about robustness.

The secondary results add descriptive context but include multiple assessments and are not reported with a multiplicity adjustment. The adverse-event counts are also limited summaries and cannot by themselves establish a full safety profile. Conclusions should therefore remain tied to the measured outcomes and reporting available for this trial.

These results do not establish effects in populations, settings, or treatment schedules not represented by the study. They do not predict an individual’s response, establish the cause of every observed change, or answer questions about outcomes not measured in the registry record. They are statistical evidence about one randomized comparison, with uncertainty and reporting limitations that remain relevant to interpretation.

17. Why This Trial Matters Statistically

This trial illustrates why a statistical reading should distinguish a point estimate from its variability and uncertainty. The primary group means describe average percent change, while the standard deviations show that participant outcomes varied, with especially wide spread in the placebo group. The confidence interval adds uncertainty around the mean contrast. Each statistic contributes different information; none alone gives a complete account of the results.

It also demonstrates the importance of matching interpretation to endpoint definition. Total lesion count combines several lesion types and uses a specific baseline-to-Cycle 6 calculation. ISGA is a separate categorical assessment at multiple time points. Even when outcomes address related aspects of acne, they need not have identical patterns or answer precisely the same question.

The posted secondary outcomes also make multiplicity relevant. A trial can report many outcome measures and visit-specific results, but unadjusted secondary comparisons do not carry the same inferential weight as a clearly prespecified primary comparison. The record does not report a testing hierarchy or multiplicity adjustment, so the secondary findings are best treated as contextual rather than as a collection of independent confirmatory results.

Finally, registry summaries can be informative while leaving important analytical details unavailable. Here, the primary population is named but not defined, and missing-data procedures and the statistical model are not reported. Recognizing those gaps is part of sound statistical interpretation: the posted estimates can be described accurately without claiming more certainty or generality than the record supports.

18. 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 registry record leaves several trial-specific details unavailable for evaluating the primary result. It names the FAS but does not define it, describe exclusions, or explain how missing Cycle 6 outcomes were handled. The primary summary gives group counts, but not a participant-flow account that would explain inclusion in the endpoint analysis. No sensitivity analysis for missing data is reported.

The inferential method is also not described in enough detail to reproduce or assess it fully. The record does not report the test used for the primary comparison, the model specification, covariate adjustment, or the method and confidence level used for the confidence interval. The group standard deviations differ markedly, but the variance assumptions or method used to account for that difference are not reported.

The record does not provide the protocol-level analysis plan, the primary sample-size justification, or details of interim analyses. It also does not report the method for generating the randomization sequence or allocation concealment. These omissions limit assessment of design and analysis decisions; they do not establish that a particular procedure was or was not used.

The trial reports multiple secondary outcomes and visit-specific assessments, while the record does not report a multiplicity strategy or testing hierarchy. This limits the strength of conclusions that can be drawn from unadjusted secondary results. Finally, the safety summary is brief: serious events are reported as zero in both groups, other adverse-event counts are available, and death counts are not reported in the registry record. The summary does not provide enough detail to characterize the full safety experience.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: GA YAZ ACNE in China Phase III — NCT00818519.
• Registry record last updated 2015-08-25; status last verified 2015-08.
• Results first posted 2011-06-09.
• 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.

22. Record Summary

NCT00818519 is a completed Phase 3, randomized, double-blind, parallel-group, placebo-controlled study sponsored by Bayer. It evaluated YAZ against placebo over 6 treatment cycles in women with moderate acne. The primary outcome was percent change from baseline to Cycle 6 in total facial lesion count, analyzed in a population identified as the FAS.

The posted primary means were 66.79 for YAZ and 37.71 for placebo. The registry comparison reports a mean difference of 29.08, a confidence interval from 3.131 to 55.03, and an unadjusted p-value of 0.028. The endpoint is defined so that larger percent change indicates a larger reduction in total lesion count.

The registry also lists ISGA and lesion-related secondary outcomes. It does not report a multiplicity strategy, a definition of the FAS, missing-data procedures, or detailed methods for the primary inferential analysis. Serious adverse events were reported as zero in both groups; other adverse events were reported for 34 participants in the YAZ group and 19 in the placebo group. Death counts are not reported in the registry record.