A Study That Evaluates the Decrease in Irritation When Using Additional Acne Treatment Products: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study That Evaluates the Decrease in Irritation When Using Additional Acne Treatment Products (NCT01313728), a randomized phase 4 study. The primary outcome is Expert Grader Assessment - Erythema.

2. Clinical Question

3. Trial Design

This was a randomized, Phase 4 study listed as completed. The registry describes the masking as single and the study model as single group; its official title calls the study investigator-blind and identifies a split-face model. Those labels describe different aspects of the record: a single-group model can include a within-person comparison when each participant receives both regimens on separate sides of the face. The record does not describe the procedures used to maintain masking or the details of how treatment sides were assigned.

In the split-face comparison, dapsone gel was applied first and tretinoin gel followed one hour later on the assigned side. Tretinoin gel alone was applied on the other assigned side. Both regimens were used once daily for two weeks. The brief summary says participants returned to the same study center every weekday during the two-week period for an investigator to assess facial irritation and have products applied. On weekends, participants applied the products at home. If one side was more irritated, a photograph could be taken.

The registry lists enrollment as 26. The primary-outcome description says the total score was calculated for the 25 participants measured. These figures are not reconciled in the registry record, so the reason for the difference is not reported. The study start and primary completion are both listed as 2010-12, and the status is completed. The sponsor is Bausch Health Americas, Inc.

The within-person structure is relevant to interpretation: each participant contributed observations under both regimens, so the intended comparison concerns the two sides of a face within participants. The registry record does not report the method used to account for that pairing in the analysis. Nor does it report a protocol-level statistical plan, sample-size justification, interim analyses, or further details about study conduct.

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.

Informed Consent to Baseline

Reasons for not completing this period:

Baseline to Completion

Analysis population for the primary outcome, as defined in the registry: Intention to Treat (ITT)

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 Expert Grader Assessment - Erythema, measured over Baseline to 2 Weeks.

The primary endpoint is titled “Expert Grader Assessment - Erythema.” It measures facial redness and related visible irritation using ordinal scores ranging from 0, meaning none, to 8, meaning severe scaling and fissuring. The record says assessments were collected on weekdays for two weeks, with the primary timeframe described as baseline to two weeks.

Although the underlying scores are ordinal, the registry describes a particular summary: the total daily score for all participants was treated as a single interval measurement for comparative assessment between treatment regimens. The description gives a minimum possible total of 0 and a maximum possible total of 2000 for the 25 participants measured. It explains the maximum using the highest possible score of 8, 10 assessment days, and 25 participants. These are details of the registry’s endpoint construction, not reported treatment results.

An expert-graded erythema assessment is intended to capture observable facial irritation rather than relying only on participants’ perceptions. The record also lists subject assessments of burning or stinging, itching, and tightness, as well as facial tolerance, among secondary outcomes. Those measures address other aspects of tolerability, but they do not replace the specified primary endpoint. The registry record does not report the observed primary scores, the between-regimen contrast, or a measure of uncertainty. It therefore does not establish how large or precise any difference in the primary endpoint was.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does a within-person comparison mean?

In a split-face design, the participant receives both regimens, one on each side of the face. Each person therefore serves as their own comparator. This structure can reduce the influence of personal characteristics that are shared across the face, because the comparison is made within a participant rather than between two unrelated groups. That advantage depends on an analysis that respects the paired observations. Treating the two sides as independent would ignore their connection and could misrepresent uncertainty. The registry record does not report the statistical procedure used for the comparison or state whether it accounted for this pairing.

The design also requires care in interpreting what is being compared. The treatment regimens differ in whether dapsone gel is used before tretinoin gel; tretinoin gel is present in both. The comparison therefore concerns the two specified regimens, not a comparison of tretinoin with no treatment. The registry record does not provide a result that would quantify the contrast.

How should an ordinal score be understood?

The erythema measure is described as an ordinal score from 0 to 8. An ordinal scale ranks observations, but the spacing between adjacent score levels is not necessarily equal. For example, a move from one level to the next need not represent the same change in irritation throughout the scale. The registry record says that the total daily score for all participants was treated as a single interval measurement for comparative assessment. That is the stated approach, but the record does not explain its statistical justification, identify a model, or report diagnostic checks.

More generally, treating ordinal observations as interval measurements can make summaries and comparisons easier to express, but it relies on an assumption about how score differences behave. If that assumption is not suitable, an analysis designed for ordinal data may better reflect the measurement scale. This is a general statistical consideration, not a claim about which approach was used beyond the description in the registry record.

Why does dependence matter?

When two measurements come from the same participant, they are often more alike than measurements from different participants. This relationship is called dependence. In a split-face study, the two sides share the participant’s general characteristics and study circumstances. Accounting for that dependence is important both for estimating the treatment contrast and for describing its uncertainty. The registry record does not report whether a paired test, a model with participant-level effects, or another method was used. It also does not report the within-participant covariance or other information that would allow the comparison to be reconstructed.

What does a confidence interval communicate?

In general, a confidence interval gives a range of values compatible with the data and the assumptions of a statistical procedure. It conveys uncertainty around an estimate; a narrow interval indicates greater precision than a wide interval, while an interval that includes values on different sides of a no-difference point may leave the direction of the contrast uncertain. A confidence interval is not a guarantee that the true effect lies in the interval, and it does not by itself establish clinical importance. No confidence interval or primary-outcome estimate is reported in this registry record, so precision cannot be evaluated.

What can a p-value tell a reader?

In general, a p-value describes how unusual data at least as inconsistent with a specified null hypothesis would be if that hypothesis and the analysis assumptions were true. It is not the probability that the null hypothesis is true, and it does not measure the size or practical importance of an effect. A small p-value cannot replace an effect estimate and its uncertainty. The registry record does not report a p-value for the primary comparison, so there is no reported hypothesis-test result to interpret.

How should the planning assumptions be read?

The record describes sample-size illustrations using a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. It says the effect to detect is a stated fraction of the observed effect. These are planning illustrations computed from an observed effect, not evidence of the study’s original design rationale. The record does not report the original sample-size calculation, the assumptions used when the trial was planned, or an analysis plan. A sample size calculated for a future study is a planning aid; it is not the observed power of the completed study and does not establish that the treatment contrast is reliable.

More generally, power is a design property tied to a specified effect, variability, significance criterion, and analysis. It should not be calculated retrospectively from the observed effect and then treated as evidence that the result is convincing. The registry’s stated normal approximation is an assumption of the planning illustration, not a reported description of the trial’s primary analysis. The record also does not report whether over-dispersion or other departures from a model assumption were considered.

What information is needed for a reproducible comparison?

A reproducible interpretation would need the actual regimen-specific outcome summaries or participant-level data, the paired comparison estimate, an uncertainty measure, and details of the analysis method. For an ordinal repeated measure, it would also help to know whether the analysis used individual daily scores, a participant-level summary, or the aggregate total described in the record. The registry record does not report these details. As a result, the endpoint can be described, but the primary statistical comparison cannot be independently checked or interpreted quantitatively.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists six outcome measures. The primary endpoint is expert grader assessment of erythema; secondary outcomes include subject assessment of burning or stinging, itching, and tightness, and facial tolerance. The record does not report a multiplicity adjustment, a hierarchy for testing outcomes, or a prespecified strategy for controlling the chance of false-positive findings across multiple comparisons. It would be inappropriate to assume that such a plan was or was not used outside what the registry states.

The registry describes the primary endpoint as collected on weekdays over two weeks, but does not report a separate analysis for each assessment day or explain how repeated measurements were handled beyond saying the total daily score was treated as a single interval measurement. It also does not report results for the secondary outcomes. The record lists zero analyses, and no comparison estimates or hypothesis-test results are reported.

The primary population is labelled Intention to Treat (ITT). This label ordinarily refers to analysing participants according to their assigned treatment groups, but the registry does not describe how that principle applies to the split-face design or how the analysis population was formed. Enrollment is listed as 26, whereas the primary outcome description refers to 25 participants measured. The reason for this difference is not reported in the registry record.

Missing-data amounts, reasons, and handling are not reported in the registry record. There is no account of incomplete weekday assessments, missed visits, exclusions, imputation, or sensitivity analyses. Without this information and without the outcome results, readers cannot assess whether missingness could have affected the comparison or how robust the findings were to alternative assumptions.

11. 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 0% reporting threshold.

Most frequent non-serious adverse event terms

The registry lists an overall study group with 25 participants at risk for serious adverse events and 0 affected by a serious adverse event. It lists 25 at risk for other adverse events and 2 affected. These are the registry’s reported counts; the record does not provide event descriptions, timing, severity detail beyond the serious-versus-other categorization, or a treatment-side breakdown.

A count of 0 serious adverse events in the listed group means that no serious adverse event was recorded among those counted in that group. It does not establish that serious events are impossible, nor does it quantify how frequently such events might occur in a broader population. Likewise, the other-adverse-event count does not by itself describe the type or clinical importance of the events. The registry record does not report deaths as a count; that information is not reported in the registry record.

These figures are safety summaries, not the primary efficacy comparison. The listed group is “Overall Study,” and the record does not connect the adverse-event counts to one regimen or the other. Because both regimens were used by each participant in a split-face model, the absence of a side-specific safety summary limits regimen-level interpretation. The counts should be read as the recorded study-level figures, not as proof of comparative safety.

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

The record identifies a focused statistical question: whether an expert-graded erythema score differed when dapsone gel followed by tretinoin gel was used on one side of the face, compared with tretinoin gel alone on the other side. It describes a randomized, investigator-blind, split-face study and specifies a two-week treatment period. The primary outcome definition and the reported safety counts provide information about what was measured and which adverse-event counts were entered in the registry.

However, the registry record does not report the primary outcome values, a comparative estimate, a confidence interval, or a p-value. Without those results, it is not possible to determine the direction or size of the observed difference, or how precise an estimate would be. The fact that the study is marked completed does not supply the missing comparison, and the outcome definition alone is not evidence that one regimen resulted in more or less irritation.

The record also does not report the statistical method used for the paired split-face comparison, how repeated assessments were handled, or how missing data were addressed. These details matter because measurements from the two sides of one participant are related, and the primary scale is ordinal even though the description says its total was treated as an interval measurement. The registry’s sample-size illustrations are planning calculations and should not be mistaken for evidence about the strength or reliability of an observed result.

The safety entries report 0 serious adverse events among 25 at risk and 2 other adverse events among 25 at risk. They are overall study counts without a reported regimen-specific breakdown. They do not establish a comparative safety profile or predict what would occur in other settings.

In short, the registry record supports a description of the study design, treatment schedules, endpoint construction, and recorded safety counts. It does not support a conclusion about whether the regimens differed on the primary outcome, the magnitude of any difference, or the clinical importance of a difference.

13. Why This Trial Matters Statistically

This study is statistically interesting because each participant received both regimens on separate sides of the face. A within-person design can make a comparison less sensitive to participant characteristics shared across both sides. At the same time, it calls for an analysis that respects the paired structure. The registry record does not report whether the analysis did so, illustrating why a clear description of the statistical method is important alongside the study design.

The endpoint also raises a measurement question. The erythema score is ordinal, while the record says a total daily score was treated as a single interval measurement. Readers need the analysis method and the observed results to judge how that choice affected the estimate and its uncertainty. A precise definition of the score is useful, but it cannot substitute for reporting the comparative result.

The record highlights the value of complete results reporting. It identifies the primary outcome and names secondary outcomes, yet lists zero analyses and does not report an estimate or uncertainty for the primary comparison. Without those quantities, the reader cannot distinguish a potentially small difference from a larger but imprecise one, or evaluate whether the data were compatible with more than one interpretation.

It also illustrates why participant accounting matters. Enrollment is listed as 26, while the endpoint description refers to 25 participants measured. The explanation is not reported. A transparent account of analysis populations, missing assessments, and exclusions would help readers understand which observations informed the result.

Thus, the statistical importance of this record lies both in its split-face design and in the limits of what can be interpreted from registry reporting. Knowing how a comparison was structured is only one part of evaluating evidence; the analysis, estimate, uncertainty, and handling of incomplete data are also necessary.

14. 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 limitations of interpretation are specific to the information recorded for this trial. The main limitation is that the registry does not report a primary-outcome estimate, regimen-specific summaries, a confidence interval, or a statistical test. The endpoint is described in detail, but no observed erythema result is available in the registry record. The record also lists zero analyses, so a comparative result cannot be reconstructed from the registered material.

The primary endpoint description refers to 25 participants measured, while enrollment is listed as 26. The reason for the difference is not reported. The record does not state whether the difference reflects missing assessments, withdrawal, an analysis exclusion, or another circumstance, and none should be assumed. Missing-data methods and sensitivity analyses are not reported in the registry record.

The record identifies an ordinal score but says its total was treated as a single interval measurement. It does not explain how the score was aggregated for each regimen, how the within-participant pairing was incorporated, or how repeated weekday observations were handled. Without these details, the statistical analysis cannot be evaluated for alignment with the scale and split-face design.

The registry lists six outcome measures but does not report how multiple outcomes were handled, whether a hierarchy was prespecified, or whether any adjustment for multiplicity was used. The named secondary outcomes are not accompanied by reported results in this record. There is also no reported protocol-level statistical plan or sample-size justification.

Finally, adverse-event counts are presented for the overall study, without a regimen-specific breakdown or event descriptions. These counts are limited for assessing the relative safety of the two sides. The record provides no basis for extending the findings beyond the study’s described setting, and, because the primary comparison is not reported, it provides no quantitative basis for judging the outcome’s magnitude or precision.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: A Study That Evaluates the Decrease in Irritation When Using Additional Acne Treatment Products — NCT01313728.
• Registry record last updated 2012-02-15; status last verified 2012-02.
• Results first posted 2012-01-19.
• 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.

18. Record Summary

The completed Phase 4 study was randomized and used a single-masking, split-face design in people with acne vulgaris. Participants applied dapsone gel followed by tretinoin gel on one side of the face and tretinoin gel alone on the other side once daily for two weeks. The primary outcome was an expert grader assessment of erythema, using an ordinal scale from 0 to 8. The record lists enrollment as 26 and says 25 participants were measured for the primary endpoint.

The registry lists six outcome measures and zero analyses. It does not report the primary comparison estimate, uncertainty, or statistical test. Serious adverse events were recorded for 0 of 25 at risk, and other adverse events for 2 of 25 at risk; the event details and regimen-specific safety results are not reported. The record also does not report missing-data handling, a multiplicity strategy, or the method used to account for paired observations.