To Assess the Mildness of a Cosmetic Cleanser in Healthy Participants Using the Forearm-Controlled Application Technique (FCAT): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for To Assess the Mildness of a Cosmetic Cleanser in Healthy Participants Using the Forearm-Controlled Application Technique (FCAT) (NCT03119688), a randomized na study. The primary outcome is Change From Baseline in Visual Assessment of Dryness at Day 5.

2. Clinical Question

3. Trial Design

The registry describes a randomized, double-masked, parallel study of a cosmetic cleanser in healthy participants. Its title identifies the Forearm-Controlled Application Technique (FCAT), and the brief summary describes repeated application to the volar forearm using the FCAT wash procedure. The study status is completed. The listed start date is 2017-05-08 and the primary completion date is 2017-05-26. The phase is recorded as NA.

Four conditions appear in the arm descriptions: test cleanser, soap-bar positive control, sterile-water reference product, and no treatment. The cleanser and sterile water were applied topically to allocated forearm sites; the listed application volume for each was 0.09 ml. The positive control used a towel moistened with sterile water and rubbed onto a 100 g soap bar for 6 seconds to generate lather. The untreated area remained unwashed and served as a reference for treated areas. The registry lists the allocation as randomized, masking as double, and model as parallel.

Enrollment is listed as 50. The primary endpoint description identifies the ITT population as N=48 and states the population criteria, while the endpoint summaries report 44 participants per arm. The registry record does not explain the difference among these population counts. It also does not report the randomization sequence, concealment procedures, masking roles, wash frequency, or the rationale for the enrollment target. These details should not be inferred from the design labels or the FCAT description alone.

The recorded sponsor is GlaxoSmithKline. The study concerns a controlled forearm application procedure, not a broad assessment across all skin-care settings or application contexts. Its design permits comparison among the listed forearm conditions under the study procedures; what those comparisons represent depends on the outcome definition and analysis method described in the registry.

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 89 participants were screened, out of which 39 participants did not meet the study criteria. Remaining 50 participants were enrolled in the study, out of which 2 participants were not randomized to the study due to adverse events (AEs).

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: ITT population (N=48) was the primary population of analysis, which included all participants who were randomized and received at least one wash procedure, including sterile water, and had at least one post-baseline clinical assessment. Number of participants analyzed for this endpoint were part of the ITT population, evaluated on Day 5.

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: Baseline parameters were reported for safety population. The safety population (N=48) included all participants who had received at least one wash procedure.

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline in Visual Assessment of Dryness at Day 5, measured over At Baseline and Day 5 (3 hours post last wash procedure).

The primary endpoint was change from baseline in visual assessment of dryness at Day 5, recorded three hours after the last wash procedure. A trained examiner assessed dryness on a scale from 0 to 6. The scale descriptions range from no dryness at 0 to severe cracking and possible eczematous change or bleeding cracks at 6. The registry explicitly states that lower scores reflect less dry skin. The outcome is therefore a continuous score summary of an examiner-rated skin feature, rather than a count of participants who crossed a stated threshold.

Change from baseline is used to describe how the assessment at follow-up differs from the participant's baseline assessment. In general, comparing change scores can focus attention on change during the study period rather than the follow-up level alone. The registry reports mean changes and standard deviations for the endpoint summaries. A mean describes the average change in the group, while the standard deviation describes variation in individual changes around that average.

The endpoint is relevant to the study objective because the stated aim was to assess the relative mildness of a cleanser under repeated forearm application. Examiner-rated dryness provides one measure of the skin response included in that assessment. It does not by itself capture every aspect of mildness, and the endpoint does not establish how a product would perform in other body areas, use patterns, or populations. The registry record does not report a threshold for a change that would be considered important to participants or an explanation of how clinically meaningful change was defined.

7. Results Posted in the Registry

• Test: mean 0.48 versus 0.91 on control; difference -0.43 (95% CI -0.55 to -0.31), standardized effect d = -1.50; z-test p = <0.001.
• Negative Control: mean 0.56 versus 0.91 on control; difference -0.35 (95% CI -0.47 to -0.23), standardized effect d = -1.20; z-test p = <0.001.
• No Treatment: mean 0.63 versus 0.91 on control; difference -0.28 (95% CI -0.40 to -0.16), standardized effect d = -0.94; z-test p = <0.001.

8. Secondary Efficacy Endpoints

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

Change From Baseline in Visual Assessment of Redness at Day 5

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Test: mean 0.01 versus 0.00 on control; difference 0.01 (95% CI -0.01 to 0.03), standardized effect d = 0.19; z-test p = 0.376.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Test and the control. The interval gives the range of effects that remain compatible with the data.

Change From Baseline in Transepidermal Water Loss (TEWL) at Day 5

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Test Product: mean 0.91 versus 1.95 on control; difference -1.04 (95% CI -1.91 to -0.17), standardized effect d = -0.50; z-test p = 0.019.
  • Negative Control: mean 0.94 versus 1.95 on control; difference -1.01 (95% CI -1.79 to -0.23), standardized effect d = -0.54; z-test p = 0.012.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Test Product than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Negative Control than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline in Skin Moisturisation at Day 5

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Test: mean 2.35 versus -4.57 on control; difference 6.92 (95% CI 4.68 to 9.16), standardized effect d = 1.29; z-test p = <0.001.
  • Negative Control: mean 2.13 versus -4.57 on control; difference 6.70 (95% CI 4.57 to 8.83), standardized effect d = 1.32; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Test than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Negative Control than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The secondary outcomes cover examiner-assessed redness and dryness, transepidermal water loss (TEWL), and skin moisturisation. The posted numerical secondary results span different types of measures: some are visual scores, while TEWL and moisturisation use their own measurement units. Their direction and practical meaning should therefore be read according to each outcome's scale, rather than treating the numerical values as interchangeable indicators.

Across the posted comparisons, the secondary results do not all tell the same statistical story. Redness changes are close to zero in the arm summaries, while the TEWL and moisturisation summaries show more separation between the positive control and other conditions. The simple unadjusted comparisons also vary in their statistical evidence. This broad pattern is not a single composite result and should not be taken as confirmation or contradiction of the primary dryness finding. The primary result concerns a specific examiner-rated dryness measure at Day 5; secondary outcomes assess related but distinct aspects of skin response.

Some secondary outcomes are listed by name in the record, including dryness and redness assessments at earlier days, but numerical results for every listed assessment are not reported in the registry record. The posted results also include secondary measures at Day 5. No missing numerical result should be inferred from a related endpoint or timepoint.

Unadjusted secondary findings carry less weight because multiple outcomes and comparisons create more opportunities for a chance-positive result. In general, multiplicity procedures can control the overall false-positive risk across a family of tests, but the registry record does not report whether such an adjustment was planned or applied to these secondary analyses. The secondary outcomes are useful as supporting descriptive evidence, but should not be treated as independent definitive proof or as a substitute for the primary endpoint and sponsor's formal analysis.

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

• Change From Baseline in Visual Assessment of Redness at Day 5
• Change From Baseline in Visual Assessment of Dryness at Day 2, 3, and 4
• Change From Baseline in Visual Assessment of Redness at Day 2, 3, and 4
• Change From Baseline in Transepidermal Water Loss (TEWL) at Day 5
• Change From Baseline in Skin Moisturisation at Day 5

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is a mean change in a continuous score. For a continuous measure, a mean difference expresses the contrast between two group averages in the scale's own units. Here, the score is an examiner assessment of dryness, and lower scores represent less dryness. A negative recalculated difference for Test compared with Positive Control means the Test mean is lower under that subtraction convention. The sponsor's net mean difference uses a reported analysis whose direction and detailed model are not fully described in the registry record, so signs should not be assumed to match the simple recalculation.

What does a standard deviation describe?

A standard deviation describes the spread of individual observations around a group mean. It is not the same as the uncertainty in the mean itself. A group can have a relatively variable set of individual changes while its estimated mean is more precise because the mean is calculated from multiple observations. The posted summaries report standard deviations for the outcome changes. General statistical interpretation treats the standard deviation as a description of observed variability, not as a measure of clinical importance.

What is a confidence interval?

In general, a confidence interval gives a range of values compatible with the data and the method used to calculate it. It helps show the precision of an estimated effect: a narrower interval indicates less statistical uncertainty than a wider interval, all else equal. An interval that includes zero is compatible with no difference under the model and confidence level used; an interval that excludes zero is less compatible with no difference under that same framework. The sponsor reports 90% confidence intervals for its ANOVA comparisons. The simple recalculations report confidence intervals as well, but these are not a substitute for the sponsor's model-based estimates.

Why do the recalculation and sponsor results differ?

The simple recalculated estimates use posted group means and standard deviations and are unadjusted comparisons. The sponsor's reported analyses are ANOVA results expressed as mean differences (net), and include superiority and non-inferiority classifications. These methods can differ in estimand, model, adjustment, or comparison direction. The registry record does not provide enough detail to identify which feature explains the difference. Since the discrepancy flag is true, the sponsor's own analysis takes precedence for describing the formal trial result. A recalculation is useful as a transparent check on the summary statistics, but it should not be portrayed as the trial's prespecified or definitive analysis.

What does 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 null model were true. It is not the probability that the null hypothesis is true, and it does not measure the size or importance of an effect. An unadjusted p-value also does not account for the number of outcomes or comparisons considered. The recalculated comparison p-values are explicitly unadjusted. The sponsor's posted analyses have their own reported p-values, but the registry record does not state a multiplicity strategy.

What is the role of randomization and masking?

Random allocation is intended, in general, to reduce systematic differences between groups at the start of a trial. Double masking is intended to limit influence from knowledge of assigned condition, although the registry record does not specify who was masked or how masking was maintained across products and an untreated area. The terms in the record identify design features, but do not establish that allocation was concealed or that masking was successful. The parallel model indicates separate groups or conditions rather than a reported crossover design; the exact allocation process and analysis of the forearm sites are not described in enough detail to infer further.

Why can variability matter?

General statistical methods rely on assumptions about how observations vary. When variability is greater than a model expects, standard errors and confidence intervals based on that model may be too optimistic unless the analysis accounts for it; this is one reason over-dispersion matters in outcomes suited to count models. For this continuous endpoint, the posted summaries include standard deviations, but the registry does not describe diagnostics or model assumptions. The general point is that an effect estimate should be read together with its uncertainty and the assumptions used to obtain it.

The outcome is a change score, and the registry identifies a primary analysis population, but it does not report the precise ANOVA specification, covariates, handling of repeated assessments, missing-data method, or whether baseline adjustment was included. These omissions limit reproducibility. They do not justify guessing that a particular model, correction, or imputation method was used.

11. Confidence Intervals and Precision

Precision concerns how much uncertainty surrounds an estimated comparison. The recalculated Test-versus-Positive-Control mean difference for the primary dryness outcome is -0.43, and its interval lies below zero. That interval is based on the posted summary statistics and the simple unadjusted recalculation. It does not incorporate any unknown features of the sponsor's ANOVA or address multiplicity. The interval therefore describes the recalculation, not a replacement for the sponsor's formal result.

The sponsor reports a 90% confidence interval for its Test-versus-Positive-Control net mean difference of 0.427. The reported interval is on the positive side of zero, and the sponsor classifies the comparison as superiority. For Test versus Negative Control, the sponsor reports a 90% confidence interval for a net mean difference of -0.077; that interval spans zero, alongside the sponsor's non-inferiority classification. The registry record does not include the non-inferiority margin, so the interval alone cannot reconstruct the decision rule. The reported analyses and the simple recalculation differ, and the discrepancy flag means the sponsor's analysis should be given precedence.

In general, an interval's width reflects both the amount of information and the variability in the data, as well as the method and confidence level used. A confidence interval is not a guarantee that the true value lies within the particular reported range. It also does not answer whether an effect matters to participants. The registry record does not report an important-difference threshold for the dryness scale, and it does not provide baseline values or participant-level data to examine the score distribution.

Precision should consequently be considered alongside the design and reporting limitations: the stated ITT population is N=48, while the posted primary endpoint arm summaries list 44 participants per arm; the reason is not reported in the registry record. The results offer evidence about group mean changes under this study's conditions, but not a complete account of uncertainty under every possible model or use context.

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 sample-size figures are planning illustrations based on the observed effect, not the original trial's design assumptions. The listed assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation; each planning scenario uses a stated fraction of the observed effect. For these continuous outcomes, the figures are participants per arm, not total events. The registry record does not report the original sample-size justification or the assumptions used to choose enrollment of 50.

The 80% power column gives an illustrative number of participants per arm for a design with an 80% chance of detecting the specified effect under those assumptions, if that effect and the statistical model are correct. The 90% column describes the analogous planning target with a higher chance of detecting that same effect. In general, seeking higher power requires more participants, all else equal. The listed rows scale the target effect to 100%, 75%, or 50% of the observed effect. Smaller effects are harder to distinguish from random variation and therefore require more participants per arm in these illustrations.

These figures are not observed power. They do not tell how likely the completed study was to find its result after the data were collected, and they should not be read as a post-hoc assessment of success. They are hypothetical design calculations built from the observed comparison and the stated assumptions. A planning value should not be interpreted as the trial's actual enrollment target, nor does it account for unreported features such as multiplicity, attrition assumptions, or a model different from the normal approximation.

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 = -0.430; pooled standard deviation σ = 0.288.
2. n = 2 × (1.96 + 0.842)² × 0.288² / -0.430² = 7.0, rounded up to 8 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 <- -0.43                      # observed difference in means
sigma <- 0.287521303558536                     # 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(3119688)
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 = 8 (80% power), 10 (90% power)
 75% of observed effect: n per arm = 13 (80% power), 17 (90% power)
 50% of observed effect: n per arm = 29 (80% power), 38 (90% power)
power.t.test: 8.1 
Simulated power at n = 8 per arm: 0.795 (20000 replicates)

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

14. Analyses Reported by the Sponsor

The sponsor's own reported analyses are the formal registry results and take precedence over the simple recalculations because the discrepancy flag is true. For the primary dryness outcome, the sponsor reports an ANOVA net mean difference of 0.427 for Test versus Positive Control, a 90% confidence interval, and a superiority classification with p <.0001. It also reports a net mean difference of -0.077 for Test versus Negative Control, a 90% confidence interval, and a non-inferiority classification with p=0.177.

The recalculation instead directly contrasts the posted means and standard deviations, giving a Test-versus-Positive-Control difference of -0.43 and an unadjusted p < 0.001. The opposite signs reflect that the two result presentations do not use an evidently identical subtraction convention, and the numerical estimates differ. The registry record does not report enough analysis detail to reconcile the differences or the non-inferiority margin. The simple calculation is best treated as a check based on summaries, not as the sponsor's estimate or decision.

The other reported sponsor analyses compare Negative Control with Positive Control, and Negative Control with No Treatment. Their classifications and estimates are part of the record, but the central issue remains that the full analysis specification and comparison conventions are not reported. A reader should distinguish the sponsor's stated formal conclusions from the descriptive arm means and recalculated statistics.

15. Multiplicity, Missing Data and Analysis Populations

The registry record lists a primary endpoint and multiple secondary outcomes, along with several reported comparisons. Testing several outcomes or contrasts increases the chance that at least one result will appear statistically notable by chance if every test is treated separately. In general, multiplicity methods address this issue by adjusting inference across a defined family of tests or by specifying a hierarchy of primary and secondary questions. Whether such an approach was used in this study is not reported in the registry record.

The simple recalculated p-values are unadjusted. They should therefore be read as individual comparisons, not as controlling the overall error rate across the collection of outcomes and contrasts. The sponsor's reported ANOVA p-values and classifications are also available, but the registry does not describe a multiplicity plan for interpreting them. The result classifications should be attributed to the sponsor rather than reconstructed from the simple calculations.

The registry identifies the primary analysis population as ITT (N=48), with inclusion requiring randomization, at least one wash procedure including sterile water, and at least one post-baseline clinical assessment. The primary outcome arm summaries list 44 participants per arm. How these populations relate, why the reported counts differ, and whether the same analysis population applies to every endpoint are not reported in the registry record. The endpoint population description includes incomplete wording about the number analyzed, so it does not resolve the count difference.

Missing-data handling is also not reported in the registry record. There is no stated method for participants lacking baseline or post-baseline assessments, no account of withdrawals or exclusions by arm, and no description of imputation or sensitivity analyses. The randomization label does not by itself establish how missing outcomes were addressed. These omissions matter because an analysis based only on observed assessments can be affected if missingness is related to outcomes or assigned condition.

The sponsor's ANOVA specification, covariates, repeated-measure structure, assumptions, and exact analysis populations are not reported. The registry record also does not report an interim-analysis plan or the original sample-size justification. None of these details can be inferred from the posted summary statistics or the design labels.

16. 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 registry reports zero serious adverse events in each listed study group, zero deaths, and zero serious events overall. The serious-event figures use 48 participants at risk in each group and list no serious-event terms. This means no serious adverse events were recorded in the posted safety summary; it does not establish that serious events are impossible or that the study could rule out uncommon events.

The record also lists other, non-serious adverse events: 4 in Test, 4 in Positive Control, 4 in Negative Control, and 2 in No Treatment, with 6 listed overall. These are counts, not rates, and the registry does not provide event types, timing, severity detail, or participant-level descriptions in the registry record. The overall count should not be derived by adding arm counts because the record presents it separately and does not explain the counting structure.

Safety observations apply to the study conditions and recorded period. The registry does not report follow-up beyond the listed primary completion date or enough detail to assess events by exposure duration. These figures describe the posted adverse-event summary; they do not determine the safety of use outside the trial conditions.

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

The result addresses a narrow question: how a cosmetic cleanser compared with specified control conditions on examiner-rated forearm dryness after repeated FCAT wash applications, with the primary assessment made at Day 5. The scale's direction is clear: lower scores correspond to less dry skin. The posted mean summaries put the Test arm below the Positive Control mean, and the simple recalculation indicates a mean difference below zero. The sponsor separately reports a formal superiority result for Test versus Positive Control.

Because the discrepancy flag is true, the sponsor's analysis takes precedence. Its comparison is not interchangeable with the simple recalculation, and the registry does not provide enough detail to reconcile their signs and estimates. The sponsor also reports a non-inferiority classification for Test versus Negative Control, but the non-inferiority margin is not reported in the registry record. The reported classification can be described, but its decision criterion cannot be independently reconstructed from the record.

These results do not establish that the cleanser is universally mild, that it is equivalent to water under every definition, or that it will produce the same response in other contexts. The study assesses a forearm application procedure in healthy participants, not every intended use or every population. A mean score change also does not show how each individual responded, and the registry does not report a threshold for clinically important change.

The secondary outcomes offer related measures, but they are not substitutes for the primary endpoint and include unadjusted comparisons. Some listed outcomes do not have numerical results reported in the registry record. The safety summary reports no serious adverse events, but the limited scope and duration of the study do not establish the absence of risk in other settings.

In short, the record supports a description of the measured group averages and the sponsor's stated analyses under this study's conditions. It does not justify extending those findings beyond the studied procedure or making treatment recommendations.

18. Why This Trial Matters Statistically

This trial is statistically interesting because it combines several controls that answer different comparison questions. The soap-bar positive control provides a contrast with an active cleansing condition, sterile water serves as a reference product, and the untreated forearm area offers a reference for treated sites. Those conditions help frame what a score change means, but they do not make every contrast equivalent. The intended comparison and direction of the estimate matter.

The primary endpoint is a graded examiner score, summarized as a mean change. That approach makes the scale's ordering important: lower values indicate less dryness. Readers need to distinguish the direction of the scale from the direction used in a reported difference. In this record, the sponsor's net mean difference and the summary-based recalculation differ, making it particularly important not to treat a sign as self-explanatory.

The record also illustrates why estimates, uncertainty, and analysis plans should be read together. The sponsor reports ANOVA comparisons and classifications, while a simple recalculation from group summaries produces a different presentation. The discrepancy flag signals that the sponsor's result takes precedence; incomplete details about the model and non-inferiority margin limit independent verification. A p-value alone cannot resolve those questions or show whether a difference is important.

Finally, multiple secondary outcomes and comparisons raise questions about multiplicity, while incomplete reporting of analysis populations and missing-data handling constrains interpretation. These are not reasons to discard the observed results. They are reasons to describe the evidence at the level it supports: a controlled, short-term assessment of specified forearm measures, with limitations in the detail available for reconstructing analysis choices and extending conclusions beyond the recorded setting.

19. Limitations

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

This study's scope is specific: healthy participants, forearm sites, repeated topical applications, and a Day 5 assessment three hours after the last wash procedure. The registry record does not establish whether the findings generalize to other body areas, longer periods, or different use patterns. The primary endpoint is examiner-rated dryness, and no clinically important difference threshold is reported. The mean score cannot describe the range of individual responses.

The record contains a discrepancy between the sponsor's reported primary comparison and the simple recalculation from posted summaries. The sponsor analysis takes precedence, but the registry does not report enough detail about the ANOVA specification, comparison direction, covariates, or non-inferiority margin to reproduce or fully evaluate its conclusions. The distinction between the formal sponsor analysis and the unadjusted recalculation is essential.

Population reporting also leaves uncertainty. Enrollment is 50, the primary ITT population is N=48, and the endpoint arm summaries list 44 participants per arm. The reason for these different counts and the endpoint-specific handling of missing assessments are not reported in the registry record. The wording about the number analyzed is incomplete, and no missing-data strategy or sensitivity analysis is described.

The record does not report the original sample-size justification, the multiplicity plan, interim analyses, or a complete statistical analysis plan. The sample-size illustrations are based on observed effects and stated planning assumptions, not the original design. Safety reporting gives aggregate counts without event descriptions or detailed follow-up. These limits restrict assessment of reproducibility, broader relevance, and the robustness of conclusions beyond the comparisons and outcomes explicitly recorded.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: To Assess the Mildness of a Cosmetic Cleanser in Healthy Participants Using the Forearm-Controlled Application Technique (FCAT) — NCT03119688.
• Registry record last updated 2019-05-02; status last verified 2019-01.
• Results first posted 2019-05-02.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

23. Record Summary

NCT03119688 is a completed randomized, double-masked, parallel study of a cosmetic cleanser using repeated forearm application with the FCAT wash procedure. It enrolled 50 healthy participants and lists Test, Positive Control, Negative Control, and No Treatment conditions. The primary endpoint was change from baseline in examiner-rated dryness at Day 5, three hours after the last wash.

The posted means place the Test dryness score below the Positive Control mean; the simple recalculation and sponsor's reported ANOVA differ, and the discrepancy flag means the sponsor's own analysis takes precedence. The record also lists secondary skin measures and an aggregate safety summary with no serious adverse events or deaths reported. Details on the original sample-size justification, multiplicity, missing-data handling, and parts of the statistical analysis plan are not reported in the registry record.