Evaluation of the Cosmetic Benefit of a Skin Cream in Healthy Females With Mild to Advanced Photo-damaged Facial Skin Who Have Undergone a Glycolic Acid Facial Peel Procedure: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Evaluation of the Cosmetic Benefit of a Skin Cream in Healthy Females With Mild to Advanced Photo-damaged Facial Skin Who Have Undergone a Glycolic Acid Facial Peel Procedure (NCT03103906), a randomized na study. The primary outcome is Number of Participants With Evaluator (Dermatologist) Global Assessment (EGA) Score for Well Tolerance of Product 14 Days Post-Procedure.

2. Clinical Question

3. Trial Design

This was a randomized, evaluator-blind, single-center, parallel-group study with two arms. The registry lists 106 participants as enrolled. The study population was healthy female participants with mild to advanced photo-damaged facial skin who had undergone a 70% glycolic acid facial peel procedure. The condition is listed as skin care, and the study is marked completed.

Group 1 was assigned the test product. Its description specifies topical application to the full face twice daily after cleansing, alongside cleanser use and morning sunscreen. Group 2 is labelled “No Test Product.” The record also describes cleanser and sunscreen use in that group, although its regimen description is incomplete. The interventions list a cream as the test product, with cleanser and sunscreen identified as reference products.

Randomization means assignment to groups was intended to occur by chance, but the method used to generate or implement the assignments is not reported in the registry record. Evaluator-blind indicates that the evaluator was masked, according to the design label; who else was masked, and how masking was maintained, are not reported in the registry record. The record identifies the study as single-center but does not name the center.

The primary outcome was assessed 14 days after completion of the facial peel procedure. The endpoint analysis included 36 participants in the test-product group and 39 in the no-test-product group. These are the outcome-specific analyzed counts, not the overall enrollment. The registry record does not report why the outcome analysis involved fewer participants than the enrolled total, or whether all participants completed follow-up.

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: A total of 141 participants were screened, out of which 106 participants were enrolled in the study. 35 participants were not enrolled as 30 did not met study criteria, 2 had adverse event and 3 were lost to follow up. Out of 106, 82 participants were randomized and 24 were not randomized because of other reasons (unspecified).

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Safety population included all participants with at least one application of product (i.e. test product for participants in Group 1 or sunscreen for participants in Group 2). Number of participants analyzed are the part of safety population analyzed for this outcome 14 days post-procedure.

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: Safety population included all participants with at least one application of product (i.e. test product for participants in Group 1 or sunscreen for participants in Group 2).

6. Primary Endpoint

The registry lists the primary outcome as Number of Participants With Evaluator (Dermatologist) Global Assessment (EGA) Score for Well Tolerance of Product 14 Days Post-Procedure, measured over 14 days after completion of the facial peel procedure.

The primary endpoint is the number of participants with an evaluator, or dermatologist, global assessment score indicating well tolerance of the product regimen 14 days after the facial peel. The scale classified a regimen as well tolerated when there was no clinically significant worsening of expected signs or symptoms and no new signs or symptoms during product use. A score indicating that the regimen was not well tolerated corresponded to clinically relevant worsening of expected signs or symptoms, or the appearance of new, unexpected signs or symptoms.

The dermatologist’s judgment was based on the total set of clinical and participant self-assessment data for each participant. The endpoint therefore represents a global evaluation rather than a result for one individual symptom or skin measurement. The registry record also lists outcomes concerning dermatologist assessments, participant self-assessments, transepidermal water loss, and corneometer measurements, but these are not the primary endpoint considered in this comparison.

A binary outcome is useful when the clinical question is whether each participant met a defined category, rather than how much a continuous measure changed. Counts and proportions make the frequency of the rated outcome visible in each group. The category is a judgment under the study’s stated assessment criteria; it should not be interpreted as a direct measure of every aspect of tolerance or as proof about outcomes beyond the assessed time and participants.

7. Results Posted in the Registry

• Group 2 (No Test Product): 97.4% (38/39) versus 100.0% (36/36) on control; risk difference -2.6 percentage points (95% CI -7.5 to 2.4), risk ratio 0.97 (0.93–1.03); unadjusted two-proportion z-test p = 0.333.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is binary: each analyzed participant was classified as having a well-tolerated or not-well-tolerated regimen. For a binary outcome, the group proportion is the number of participants with the event divided by the number assessed in that group. Here, the event is the well-tolerated classification. The posted counts show 36 of 36 in Group 1 and 38 of 39 in Group 2. The study’s definition of the event matters: it is a dermatologist’s global assessment using the clinical and participant self-assessment information, rather than a count of all symptoms considered separately.

What does a risk difference describe?

A risk difference compares two group proportions by subtraction. It is expressed on the same scale as the proportions, so a value of zero corresponds to equal proportions under the chosen group ordering. Positive or negative values indicate which group has the larger observed proportion, but the direction depends on which group is subtracted from which. The recalculated contrast uses Group 2 relative to Group 1. The registry’s reported contrast has the opposite displayed direction, and the record does not clearly identify its group ordering. This is why the signs should not be read as competing conclusions without first checking the contrast definition.

The risk difference is an absolute measure: it describes the gap between proportions, rather than a relative ratio. Absolute measures can be read in relation to the outcome frequencies in the groups. The sponsor reports its estimate in percentage-point units, whereas the recalculated contrast is represented as a fraction. The direction and units should be kept clear when comparing the estimates.

How should the p value be read?

A p value describes how compatible 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, and it does not measure the clinical importance of a difference. The recalculated p value is 0.333. The sponsor reports a p value that rounds to the same value at three decimal places. These results do not provide strong evidence against the null model of no group difference, but a p value alone cannot establish equivalence or rule out meaningful differences.

The sponsor’s reported method is chi-squared, with the parameter described as difference in proportion. A chi-squared test assesses whether observed categorical counts are compatible with equal group proportions under its null hypothesis. The record does not provide enough detail to establish every implementation choice, such as any continuity correction or additional adjustments. The posted recalculation is an unadjusted comparison of the group summaries, not an adjustment for participant characteristics or other outcomes.

What does a confidence interval add?

A confidence interval gives a range of estimates compatible with the observed data under the method used to construct it. It is useful alongside the point estimate because it communicates precision: a wider interval indicates that the data leave more uncertainty about the size and direction of the contrast. The sponsor reports a 95% confidence interval from -19.99 to 25.07 for its percentage-point difference. This range includes zero and includes values on both sides of zero. The recalculated interval likewise crosses zero. Neither interval establishes that the true difference is exactly zero.

Confidence intervals are method-dependent. The sponsor’s interval and the unadjusted recalculation need not be numerically identical if their calculation methods differ, even when they use the same counts. The registry identifies the sponsor’s chi-squared analysis, while the recalculation is an unadjusted recomputation from the posted summary statistics. The record does not report details of a prespecified analysis plan that would allow a fuller assessment of how the method was selected.

What is not established by these methods?

The registry includes planning assumptions for illustrative sample-size calculations, based on the observed effect, equal allocation, a two-sided significance level of 0.05, and a normal approximation. Such calculations are planning illustrations, not observed power and not evidence that the study was designed around a particular target effect. The trial’s own sample-size justification is not reported in the registry record. The record also does not report interim analyses, a multiplicity adjustment, or a detailed missing-data method. These omissions limit assessment of how the primary test fits into the full analysis strategy.

Because this is a binary count outcome, the issue of over-dispersion in continuous or count models is not the central concern for the posted comparison. More generally, over-dispersion occurs when variability exceeds that assumed by a statistical model and can make model-based uncertainty too small if not addressed. That general concern does not establish a problem with this analysis; the registry record does not report an over-dispersion assessment.

10. Confidence Intervals and Precision

The sponsor reports a 95% confidence interval for the difference in proportion from -19.99 to 25.07. The interval includes zero and extends in both directions. This means the posted analysis is compatible with no difference as well as with differences favoring either group, given the interval’s contrast convention and method. The point estimate should not be interpreted on its own while this broad range of plausible values remains.

The recalculated interval for the risk difference also crosses zero. Its bounds are expressed on a different scale from the sponsor’s percentage-point interval, and the recalculation uses the reverse group ordering. The recalculated estimate is therefore not a direct reproduction of the sponsor’s signed estimate. The two approaches nevertheless convey the same broad statistical message: uncertainty includes no difference, and the data do not pin down a precise group contrast.

A confidence interval is not a guarantee that the true value lies within its bounds, nor does it describe the range of individual participants’ outcomes. It quantifies uncertainty in the estimated group contrast under the assumptions of the method used. A wide interval can arise when the available information is limited; in this study, the endpoint analysis involved 36 participants in one group and 39 in the other. The interval width is relevant to interpretation because a non-significant result can still be consistent with a range of potentially important effects.

The record does not report a prespecified equivalence margin or non-inferiority margin. Without such a margin and a design and analysis aligned to it, an interval that includes zero cannot establish equivalence. The study’s own sample-size justification is not reported in the registry record, so the precision achieved cannot be compared with a documented target.

11. Analyses Reported by the Sponsor

The sponsor reports a chi-squared analysis of the difference in proportion, with an estimate of 2.56, a 95% confidence interval from -19.99 to 25.07, and a p value that rounds to 0.333 at three decimal places. The unadjusted recalculation from the posted group counts compares Group 2 with Group 1 and reports a risk difference on a fractional scale. Its sign is negative, while the sponsor’s estimate is positive. The contrast ordering is not clearly stated for the sponsor analysis, so the signs should not be treated as a disagreement about which group has the higher proportion.

The two analyses are broadly consistent in their uncertainty: both intervals include no difference, and the sponsor’s p value rounds to the same three-decimal value as the recalculated p value of 0.333. The sponsor’s estimate is stated in percentage-point units, while the recalculated contrast uses a risk-difference scale; the displayed direction also depends on group order. The registry entries identify no discrepancy between the analyses. The sponsor’s analysis is the registry-reported result, while the recalculation is an unadjusted check based on the posted counts rather than a replacement for the sponsor’s method.

12. Multiplicity, Missing Data and Analysis Populations

The registry lists six secondary outcomes in addition to the primary outcome. They include dermatologist and participant assessment scores, individual symptom assessments, transepidermal water loss, and corneometer measurements. The record does not report results for these secondary outcomes in the registry record for this analysis. It also does not report whether the study used a prespecified hierarchy, adjusted for testing multiple outcomes, or treated secondary analyses as exploratory.

Multiplicity matters when several hypotheses are tested: the chance of at least one apparently unusual result can increase as the number of tests grows if no adjustment or interpretation strategy is used. This is a general statistical consideration, not evidence that any particular false-positive finding occurred in this study. Without a reported multiplicity plan, the strength of any claims based on multiple endpoints cannot be evaluated from this record. The primary endpoint should be distinguished from the secondary outcome family.

The registry describes the endpoint population as the safety population, including participants with at least one application of product, and notes that the outcome analysis used the portion of that population analyzed 14 days after the procedure. The analyzed counts were 36 in Group 1 and 39 in Group 2. The record does not report the number of participants with missing endpoint assessments, reasons for missingness, imputation methods, or sensitivity analyses. It is therefore not possible to assess how missing outcomes were handled or whether missingness could have influenced the observed group comparison.

Although 106 participants were enrolled, the registry entries do not explain how the outcome-specific analysis population was derived from enrollment. The record does not report a full participant flow or a detailed analysis-population definition beyond the safety-population description. It also does not report interim analyses, a protocol-level statistical analysis plan, or the trial’s sample-size justification. These omissions constrain assessment of analysis choices and the potential for selective reporting; they do not establish that such problems occurred.

13. Safety Results

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

Deaths

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 serious adverse event figures report zero participants with serious adverse events in both groups. The serious-event populations at risk were 37 in Group 1 and 40 in Group 2. The record also reports zero deaths in each group. For other adverse events, the figures are one affected participant among 37 at risk in Group 1 and two among 40 at risk in Group 2. These are counts, not a comparison adjusted for differences between groups.

These safety counts should be read separately from the primary endpoint, which was a dermatologist’s global tolerance assessment 14 days after the peel and used a distinct outcome-specific population. The safety denominators differ from the primary endpoint denominators. The registry entries do not provide event descriptions for the other adverse events, attribution to product, severity, timing, or a detailed definition of the reported categories. No serious-event terms are listed in the record.

Zero observed serious events in these groups does not demonstrate that serious events cannot occur, nor does it establish a comparative safety conclusion. The counts describe what was recorded in this study’s safety population. The record does not report inferential testing for these safety counts, and the small number of reported events makes the counts more informative as descriptive observations than as precise estimates of event frequency.

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

The result describes a dermatologist-rated global tolerance outcome in a specific study setting: healthy female participants with mild to advanced photo-damaged facial skin after a 70% glycolic acid facial peel. At the assessment 14 days after the procedure, all 36 analyzed participants in the test-product group were classified as having a well-tolerated regimen, compared with 38 of 39 in the no-test-product group. These counts are the direct observations reported for the primary endpoint.

The statistical comparison does not establish a clear difference between groups. The recalculated p value is 0.333, and the interval for the estimated contrast includes zero. The sponsor’s reported confidence interval also includes zero. This does not prove the regimens have identical effects. It means the available data do not precisely determine whether there is a difference, or how large and in which direction a possible difference might be.

The result is limited to the endpoint definition, assessment time, and analyzed participants. It does not answer whether the groups differed on every symptom, participant self-assessment, skin measurement, or longer-term outcome. Those questions require their own results and, where relevant, a clear approach to multiple comparisons. The registry lists six secondary outcomes but their findings are not reported in the registry record for this analysis.

The group comparison also should not be treated as a randomized comparison of cream alone unless the intervention contrast supports that interpretation. Group 1 received the test product along with cleanser and sunscreen, while Group 2 is labelled no test product and its description is incomplete. The endpoint concerns the regimen in the context of the peel. The record does not provide enough detail to isolate the effect of one product from the rest of the regimen.

Finally, this result is not a clinical recommendation. It is an account of the posted outcome counts and their statistical uncertainty. The record does not report enough information about missing assessments, analysis planning, or a prespecified equivalence criterion to support stronger claims about equivalence or about populations beyond those studied.

15. Why This Trial Matters Statistically

This study illustrates why outcome counts, effect estimates, and uncertainty should be read together. The raw results are easy to state: 36 of 36 analyzed participants in the test-product group and 38 of 39 in the no-test-product group received the well-tolerated classification. The inferential question, however, concerns the group contrast and how precisely it is estimated. The confidence intervals and p values add information that the counts alone cannot provide.

It also shows the importance of defining the event and contrast direction. The endpoint is a dermatologist’s global judgment based on clinical and participant self-assessment data, not a simple measure of one symptom. The sign of a risk difference depends on group ordering. When the registry’s reported estimate and an unadjusted recalculation use different presentation conventions, the apparent sign reversal needs to be distinguished from a substantive disagreement.

Another statistical lesson is that a result that does not provide strong evidence against no difference is not the same as evidence of equivalence. Equivalence requires a defined margin and an analysis designed to evaluate whether effects fall within it. No such margin is reported in the registry record. The uncertainty in the posted estimates therefore remains important even though the p value is not small.

Finally, enrollment and endpoint analysis counts answer different questions. The registry reports 106 enrolled participants, while the primary endpoint analysis includes 36 and 39 participants in the two groups. A clear account of participant flow, missing data, and analysis populations helps readers judge how representative the analyzed data are of the randomized groups. Those details are not reported in the registry record, which limits what can be concluded from the statistical summary.

16. 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 endpoint analysis covers 36 participants in Group 1 and 39 in Group 2, compared with an enrollment of 106. The registry record does not explain the difference, describe participant flow, or report reasons for participants not appearing in the outcome analysis. Without those details, the influence of exclusions or missing assessments cannot be evaluated.

The outcome is a global evaluator judgment with a defined category, but the record does not report information about evaluator training, consistency between evaluators, or any reliability assessment. The study is labelled evaluator-blind, but details about how masking was maintained and whether participants or other study personnel were masked are not reported in the registry record. These factors may matter when interpreting a subjective assessment.

The comparator is labelled “No Test Product,” while its description is incomplete. The intervention list includes a cream, cleanser, and sunscreen, and the arm descriptions mention cleanser and sunscreen use. Because the full comparator regimen is not available in the record, the contrast cannot be confidently attributed to the test cream alone. The results concern the studied regimens in the post-peel context.

The registry does not report the trial’s sample-size justification, a detailed statistical analysis plan, missing-data methods, or a multiplicity strategy. It also does not report an equivalence or non-inferiority margin. These omissions limit assessment of whether the analysis was fully prespecified and whether the observed precision was adequate for a particular decision threshold. They are reporting limitations, not evidence that the study necessarily departed from a plan.

The primary result is restricted to the stated population and assessment 14 days after the peel. Results for the listed secondary outcomes are not reported in the registry record for this analysis. The study’s single-center design and narrowly described participant group also limit how far the findings can be extended beyond the enrolled population and study setting. The registry record does not provide enough information to resolve these limitations.

17. Related Tutorials

18. Related Statistical Calculators

19. Sources

• ClinicalTrials.gov: Evaluation of the Cosmetic Benefit of a Skin Cream in Healthy Females With Mild to Advanced Photo-damaged Facial Skin Who Have Undergone a Glycolic Acid Facial Peel Procedure — NCT03103906.
• Registry record last updated 2019-02-20; status last verified 2019-02.
• Results first posted 2019-02-20.
• 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.

20. Record Summary

NCT03103906 is a completed, randomized, evaluator-blind, single-center, parallel two-arm study of a topical skin-care formulation in healthy female participants with mild to advanced photo-damaged facial skin after a 70% glycolic acid facial peel. The registry reports 106 enrolled participants. The primary outcome was dermatologist-rated well tolerance 14 days after the procedure.

The endpoint analysis recorded 36 of 36 participants in the test-product group and 38 of 39 in the no-test-product group as having a well-tolerated regimen. The unadjusted recalculation reports a p value of 0.333, and the estimated contrast’s interval includes zero. The sponsor reports a 95% confidence interval from -19.99 to 25.07 for its difference in proportion and a p value that rounds to 0.333 at three decimal places.

The registry lists six secondary outcomes. The sample-size justification, detailed missing-data approach, multiplicity strategy, and participant flow from enrollment to the endpoint analysis are not reported in the registry record.