To Study Generic Clindamycin 1%/Benzoyl Peroxide 5% Topical Gel (Glenmark Generics, Ltd) in the Treatment of Acne Vulgaris.: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for To Study Generic Clindamycin 1%/Benzoyl Peroxide 5% Topical Gel (Glenmark Generics, Ltd) in the Treatment of Acne Vulgaris. (NCT02465632), a randomized phase 3 study. The primary outcome is Mean Percent Change in the Number of Inflamed Lesions (Papules/Pustules).

2. Clinical Question

3. Trial Design

The registry describes a randomized, phase 3, parallel-group, placebo-controlled study conducted at multiple sites. Its official title calls the study double-blind, while the registry masking field records triple masking. The record does not explain the difference between those descriptions or specify which parties were masked. Allocation is recorded as randomized, but the method used to generate or conceal the allocation is not reported in the registry record.

The study compared three topical gels: generic clindamycin 1%/benzoyl peroxide 5% from Glenmark Generics, Ltd; marketed BenzaClin containing the same listed active ingredients and strengths; and placebo. The arm descriptions say to apply a thin layer of gel to the face. Further details about application frequency, treatment adherence, permitted additional treatments, and treatment duration are not reported in the registry record.

The listed enrollment is 1100. The primary outcome is reported for the Test, Reference, and Placebo groups, with group sizes of 362.0, 368.0, and 176.0, respectively. These are the counts associated with the posted outcome, not a restatement of the enrollment field. The safety results use different group counts. The study is marked completed, with a start date of 2015-04 and primary completion of 2015-11.

The primary endpoint timeframe is baseline and 10 weeks. The registry lists two outcome measures, but no secondary outcome results are posted in the record. It lists zero analyses. The original statistical analysis plan, planned analysis populations, handling of missing outcome measurements, and any protocol deviations are not reported in the registry record.

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.

Overall Study

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.

Population: A total of 1100 subjects were randomized in the study; of these 27 subjects did not received the dose (Test=8, Reference=10, Placebo=9) and were excluded from the safety population randomized. Therefore the overall number of subjects in the Baseline Participants module is not consistent with any of the rows of the Participant Flow module.

6. Primary Endpoint

The registry lists the primary outcome as Mean Percent Change in the Number of Inflamed Lesions (Papules/Pustules), measured over Baseline and 10 Weeks.

The primary endpoint is mean percent change in the number of inflamed acne lesions, specifically papules and pustules, from baseline to 10 weeks. A lesion count measures the number of lesions meeting the study's stated inflammatory categories. Expressing change as a percentage relates the observed change to the starting count, so participants who begin with different counts can be described on a common relative-change scale. The record does not specify the formula or sign convention used to code this percentage change. It is therefore safest to describe the posted values as mean percent change, rather than to assign an unreported interpretation to a positive or negative value.

The registry states that lesion counts between treatment groups were estimated. The reported endpoint is a continuous measure, and the listed summary is a mean with standard deviation. The mean describes the group average; the standard deviation describes variability among individual observations around that average. A group mean does not reveal how many participants improved, stayed the same, or changed in the opposite direction. It also does not show the full distribution of lesion counts or whether the average reflects a similar pattern across participants.

Using an inflammatory lesion count provides a numerical outcome for comparing the treatments over the stated timeframe. The registry record does not report why this endpoint was selected over other acne measures, whether lesion assessments were performed by blinded assessors, or how the count was measured. Those details matter when evaluating how consistently the outcome represents change in the condition.

7. Results Posted in the Registry

• Test: mean 72.30 versus 71.10 on control; difference 1.20 (95% CI -2.57 to 4.97), standardized effect d = 0.05; z-test p = 0.532.
• Placebo: mean 39.10 versus 71.10 on control; difference -32.00 (95% CI -37.38 to -26.62), standardized effect d = -1.13; z-test p = <0.001.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous and summarized by a mean and standard deviation. In general, a mean is the arithmetic average of observed values, while a standard deviation describes the spread of individual values around the mean. These summaries are useful for comparing group averages, but they do not show the shape of the outcome distribution or whether a small number of observations strongly influence the average. The registry lists the endpoint as mean percent change and identifies standard deviation as its dispersion measure.

What does a mean difference represent?

A mean difference subtracts one group's mean from another group's mean. The posted recalculated contrast for Test versus Reference is 1.2, consistent with the Test mean of 72.3 and Reference mean of 71.1. The Placebo contrast is reported as Placebo versus Reference and is -32.0, using means of 39.1 and 71.1. The sign identifies which group mean is numerically higher; the registry does not state the percentage-change coding convention, so the sign should not be translated into a clinical direction beyond the numeric contrast.

In general, a mean difference retains the outcome's original scale, whereas a standardized effect size expresses a difference relative to variability. The recalculated standardized effects are 0.046 for Test versus Reference and -1.131 for Placebo versus Reference. These are based on posted summary statistics and are not adjusted estimates. Their interpretation depends on the scale and variability of the measured outcome, and they do not replace examination of the means and intervals.

How should the p-values be read?

A p-value is, in general, a measure of how incompatible observed data are with a specified null model, assuming that model and its assumptions hold. It is not the probability that the null hypothesis is true, nor does it measure the size or clinical importance of a difference. The reported Test versus Reference p-value is 0.532; the Placebo versus Reference p-value is < 0.001. Both are identified as unadjusted. The registry record does not identify the test statistic, model, or exact hypotheses used by a sponsor analysis, and it lists zero analyses. These p-values accompany unadjusted recalculations from the posted summaries.

A p-value that does not indicate a detectable difference is not evidence that two treatments are equivalent. Equivalence assessment ordinarily requires a margin representing the largest acceptable difference, along with an appropriate inferential procedure. The equivalence margin and formal procedure are not reported in the registry record. The trial's stated aim and the available unadjusted contrast therefore answer different questions: an objective to evaluate equivalence is not itself an equivalence result.

What does an interval add?

An interval around an estimated difference communicates uncertainty about the estimate. In general, a narrower interval indicates greater precision than a wider interval, under the method used to construct it. The interval for Test versus Reference ranges from -2.566 to 4.966. The interval for Placebo versus Reference ranges from -37.38 to -26.62. The confidence level and method used to construct these intervals are not reported in the registry record. The first interval includes zero; the second does not. This supports describing the first contrast as uncertain about the direction of a mean difference and the second as separated from zero under the posted calculation, without claiming a sponsor-specified analysis.

The intervals are not a display of every individual participant's outcome. Nor do they establish that every value within an interval is equally plausible in a literal sense. They quantify uncertainty about the estimated group contrast under an underlying statistical procedure. Since the registry record does not describe that procedure, the intervals are most appropriately read as the posted uncertainty summaries accompanying the recalculated differences.

Why can variability matter?

General statistical principle: variability affects how precisely group means and their differences can be estimated. More variable outcomes make it harder to distinguish a group difference from random variation when other features are similar. Here, the reported standard deviations are 25.2 for Test, 26.7 for Reference, and 31.4 for Placebo. These summaries show that individual outcomes vary within each group, but they do not disclose the distributions or the correlation structure of repeated observations. The registry does not report whether a model used baseline values or other covariates to account for variability.

Standard errors describe the estimated uncertainty in a mean. The recalculations list standard errors of 1.392 for Reference and 1.324 for Test, and 2.367 for Placebo. A standard error is not the same as a standard deviation: it concerns precision of an estimated mean rather than spread among individuals. These quantities are posted as part of the recalculation and should not be attributed to a separately reported sponsor model.

What analysis details remain unknown?

The record does not report the original analysis plan, a named analysis population, treatment of missing endpoint observations, handling of protocol deviations, or adjustment for baseline values. It also does not report an adjustment for multiple comparisons. Those details can influence both estimates and uncertainty, particularly if outcome availability differs among groups or if several comparisons were planned. The available results therefore permit a focused reading of the reported means and unadjusted contrasts, but not a reconstruction of the full statistical analysis.

General principle: missing outcome data can affect a comparison if the people with recorded measurements differ systematically from those without them. The posted outcome group counts do not explain why the counts differ from the enrollment field or from the safety counts. Without participant flow and missing-data information, the extent and consequences of missing primary outcome observations cannot be assessed from the registry record.

10. Confidence Intervals and Precision

The Test versus Reference mean difference is 1.2, with an interval from -2.566 to 4.966. This interval spans zero, so the posted estimate is compatible with a range that includes no mean difference and with differences in either numerical direction. The interval is relatively informative about the scale of the estimated contrast, but its confidence level and construction method are not reported in the registry record. The unadjusted p-value is 0.532.

The Placebo versus Reference mean difference is -32.0, with an interval from -37.38 to -26.62. This interval lies below zero and is separated from the Test-versus-Reference interval in the posted summaries. It describes uncertainty around the numerical contrast on the recorded outcome scale. Because the percent-change sign convention is not specified, the interval should not be recast as a direction of clinical benefit or harm.

In general, a confidence interval conveys precision by presenting a range of estimates consistent with the data and the interval procedure. It is not a guarantee that the true value lies in that range, and it does not describe variation among individual participants. The posted intervals address uncertainty in group mean differences. They do not address unreported sources of uncertainty, such as missing-data assumptions, protocol deviations, or the choice of analysis population.

The trial's stated equivalence objective cannot be assessed from interval width alone. A formal equivalence interpretation would require an acceptable-difference margin and an interval evaluated against that margin. Neither is reported in the registry record. Thus, the Test-versus-Reference result can be described as an estimate with an interval that includes zero, but the record does not establish whether the interval is sufficiently narrow for the intended equivalence question.

11. 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 sample-size figures are planning illustrations, not observed power. They are computed from the observed effect, with a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each planning row uses the stated fraction of the observed effect as the effect to detect. The figures are participants per arm for these continuous-outcome comparisons, not total event counts.

For Test versus Reference, the table gives participants per arm for 80% power and participants per arm for 90% power at 100% of the observed effect, 75% of the observed effect, and 50% of the observed effect. The corresponding figures are 7,351 and 9,841; 13,068 and 17,494; and 29,403 and 39,362. For Placebo versus Reference, the corresponding pairs are 13 and 17; 22 and 30; and 50 and 66.

In plain language, the 80% power column describes the illustrative number of participants per arm under which the assumed design would have an 80% chance of detecting the specified effect, if the calculation's assumptions hold. The 90% column uses a higher target chance of detection and therefore gives larger planning counts for the same contrast and effect fraction. Smaller effects require more participants to detect, as reflected by the increasing figures when planning for a smaller fraction of the observed effect.

These calculations are not the trial's original sample-size justification. The original design assumptions and any planned power calculation are not reported in the registry record. The plotted planning curve should be read under the same illustrative assumptions as the listed figures, rather than as a description of the completed study's achieved power.

12. 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 = 1.200; pooled standard deviation σ = 25.967.
2. n = 2 × (1.96 + 0.842)² × 25.967² / 1.200² = 7,350.5, rounded up to 7,351 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 <- 1.2                      # observed difference in means
sigma <- 25.9670138914655                     # 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(2465632)
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 = 7,351 (80% power), 9,841 (90% power)
 75% of observed effect: n per arm = 13,068 (80% power), 17,494 (90% power)
 50% of observed effect: n per arm = 29,403 (80% power), 39,362 (90% power)
power.t.test: 7351.5 
Simulated power at n = 7,351 per arm: 0.798 (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.

13. Multiplicity, Missing Data and Analysis Populations

The posted primary outcome includes comparisons of Test with Reference and Placebo with Reference. Both recalculated p-values are unadjusted. The registry record does not report whether these comparisons were prespecified as a family, whether other comparisons were planned, or whether any multiplicity procedure was used in the original analysis. Since the record lists two outcome measures but no secondary outcome results, the scope of all intended statistical testing cannot be established from the posted information.

In general, when multiple hypotheses are tested, the chance of at least one false-positive finding can increase if each test is considered independently at a conventional threshold. Adjustment methods can address this issue, but they may also change the interpretation of individual results. No such method is reported for these contrasts. The unadjusted p-values should therefore be read as the results of separate comparisons, not as multiplicity-adjusted evidence across all study outcomes.

Missing-data handling is also not reported in the registry record. The outcome group counts are 362.0 for Test, 368.0 for Reference, and 176.0 for Placebo, whereas the safety groups have different counts. The record does not provide a participant flow account or explain why counts differ across these results. It does not state whether the outcome analysis used all randomized participants, participants with available measurements, or another population. These analysis populations should not be inferred from the posted counts.

In general, missing outcomes may affect estimates if availability is related to treatment assignment or to the outcome itself. The registry record does not describe imputation, a missing-at-random assumption, sensitivity analyses, or any other approach. It also does not report the handling of protocol deviations or treatment discontinuation. Without these details, the potential influence of missing data and analysis-population choices cannot be evaluated.

The trial's original statistical analysis plan, including any interim analyses, is not reported in the registry record. No assumptions about those procedures can be made from the completed status or the posted summary statistics.

14. 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.

The posted safety groups list 432 participants at risk in Test, 430 in Reference, and 211 in Placebo. The number affected by serious adverse events is recorded as 0 in each group. The number affected by other adverse events is also recorded as 0 in each group. These are the serious and other adverse-event figures as entered in the registry record; they are not the primary efficacy outcome counts.

In general, an affected-participant count indicates how many participants were recorded as experiencing at least one event in the stated category, whereas an event count may count repeated events. The record reports affected counts, not detailed event narratives. No serious-event terms are listed. Death counts are null, so deaths are not reported in the registry record; null should not be read as a documented count of zero.

Zero reported affected participants does not establish that an event was impossible or that risk was absent. The record does not provide further detail about event collection, severity grading, duration, relationship to treatment, or follow-up after treatment. The safety results should therefore be read as the registry's recorded counts, with those limits in mind.

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

The posted outcome summaries describe average percent change in inflamed lesion counts for the three groups from baseline to 10 weeks. The Test and Reference means are numerically close, at 72.3 and 71.1. Their recalculated mean difference is 1.2, and the interval from -2.566 to 4.966 includes zero. The unadjusted p-value is 0.532. These results do not show a statistically detectable mean difference under the recalculation, but that is not the same as demonstrating equivalence.

The stated trial objective was to evaluate therapeutic equivalence between the generic gel and BenzaClin. A conclusion of equivalence requires a prespecified margin defining what difference would be acceptable and an analysis designed for that question. The registry record does not report either. A non-significant difference test cannot substitute for an equivalence analysis, because it may reflect uncertainty rather than evidence that the treatments are sufficiently similar.

The Placebo mean is 39.1, and the recalculated mean difference for Placebo versus Reference is -32.0, with an interval from -37.38 to -26.62 and p < 0.001. This is a numerical separation on the recorded outcome scale. The registry record does not describe the sign convention for percent change, so the values should not be turned into an unqualified claim about the direction of clinical improvement.

The posted results do not show individual participant outcomes, the full outcome distributions, or how missing measurements were handled. They also do not report a sponsor analysis, an analysis population, or adjustment for multiple comparisons. The results support describing the posted group averages and unadjusted contrasts, but not broader claims about all participants, long-term outcomes, or a formal equivalence conclusion.

These findings are statistical descriptions of the registry record, not medical advice. Treatment decisions require clinical context beyond the information reported in this trial record.

16. Why This Trial Matters Statistically

This study presents a useful statistical distinction between testing for a difference and testing for equivalence. The registry states that the trial was designed to evaluate therapeutic equivalence between a generic topical gel and the marketed product. Yet the posted Test-versus-Reference comparison is an unadjusted difference estimate, with an interval that includes zero and p = 0.532. That result alone does not establish equivalence. The equivalence margin and formal procedure needed to answer that question are not reported in the registry record.

The placebo comparison gives a different statistical perspective. Its recalculated mean difference is -32.0, with an interval that lies below zero and p < 0.001. Comparing active groups with placebo can help describe separation on the recorded measure, but it does not resolve whether two active products meet a prespecified equivalence standard. Each contrast answers a distinct question and should be read on its own terms.

The endpoint is also a reminder that the meaning of a numerical result depends on clear measurement conventions. The outcome is labeled mean percent change in inflamed lesion count, but the registry does not report how the percentage change was coded. That omission limits the interpretation of direction even when the means and contrasts are available.

Finally, posted summary statistics can be informative while leaving important analytical details unresolved. The registry lists zero analyses and does not report the original model, analysis population, missing-data handling, or multiplicity plan. Separating the available recalculations from an unreported sponsor analysis helps readers avoid assigning greater certainty or a different inferential purpose to the numbers than the record supports.

17. 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.

Several trial-specific limitations follow from gaps in the registry record. It does not report the full eligibility criteria or a detailed description of the primary outcome population. The outcome counts differ from the safety counts, but no participant flow information explains the differences. The record also does not state which participants were included in the primary analysis or how missing lesion counts were handled.

The endpoint is described as mean percent change in inflamed lesion count, but the formula and sign convention are not given. This makes it difficult to interpret the direction of the posted values clinically. The record does not report how lesion counts were assessed, whether assessors were masked, or whether any quality-control procedures were used.

The official title describes double-blinding, while the masking field records triple masking. The registry record does not explain which people were masked or reconcile the two descriptions. Allocation is listed as randomized, but the randomization sequence and concealment procedures are not reported. Details on treatment frequency, duration beyond the stated outcome timeframe, adherence, and additional permitted treatments are also not reported.

The record lists the study objective as therapeutic equivalence but does not report an equivalence margin, a formal equivalence analysis, or a sponsor analysis. It lists zero analyses, and the contrasts discussed are unadjusted recalculations from posted summary statistics. The confidence-interval level and method are not reported. Neither multiplicity adjustment nor the approach to protocol deviations is described.

Safety entries report zero affected participants for serious and other adverse events, but do not provide event narratives or further collection details. Death counts are not reported in the registry record. These limitations do not change the recorded numbers, but they constrain the conclusions that can be drawn from them.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: To Study Generic Clindamycin 1%/Benzoyl Peroxide 5% Topical Gel (Glenmark Generics, Ltd) in the Treatment of Acne Vulgaris. — NCT02465632.
• Registry record last updated 2017-06-28; status last verified 2015-12.
• Results first posted 2017-06-28.
• 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.

21. Record Summary

The registry record describes a completed randomized phase 3, parallel-group study in acne vulgaris, with placebo control and multiple sites. It lists an enrollment of 1100 and compares generic clindamycin 1%/benzoyl peroxide 5% topical gel with BenzaClin and placebo. The primary outcome is mean percent change in inflamed lesion count from baseline to 10 weeks.

The posted outcome means are 72.3 for Test, 71.1 for Reference, and 39.1 for Placebo. The unadjusted recalculated Test-versus-Reference difference is 1.2, with an interval from -2.566 to 4.966 and p = 0.532. The Placebo-versus-Reference difference is -32.0, with an interval from -37.38 to -26.62 and p < 0.001. The record does not report the endpoint sign convention or a formal equivalence margin and analysis.

The safety record lists zero affected participants for serious and other adverse events in each group. The original statistical plan, analysis populations, missing-data methods, and multiplicity approach are not reported in the registry record.