To Evaluate the Effect of Moisturizing Creams on Skin Barrier Function: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for To Evaluate the Effect of Moisturizing Creams on Skin Barrier Function (NCT03804710), a randomized na study. The primary outcome is Change From Baseline in Trans-epidermal Water Loss (TEWL) Following Application of Test Regimen on Face (Area 1 Compared to Area 2) at Day 29.

2. Clinical Question

The registry describes the trial as randomized, double-masked, and parallel. The primary outcome compares change at Day 29, calculated as the Day 29 value minus the baseline value, for facial areas 1 and 2. The posted group means are reductions in all three groups. The unadjusted comparisons estimate the difference in mean change between each test product and standard cleanser soap. The primary estimates are negative, but their confidence intervals include zero, so the posted data do not precisely distinguish those mean changes from no between-group difference.

3. Trial Design

The registry describes a randomized, double-masked, parallel study with enrollment of 158. The phase is listed as not applicable. The study status is completed, with a start date of 2019-01-22 and primary completion on 2019-04-16. The sponsor is GlaxoSmithKline. The brief summary states that the aim was to evaluate twice-daily topical application of two moisturizing creams on skin barrier function over 4 weeks.

The intervention list names Developmental moisturizing cream 1, Developmental moisturizing cream 2, and standard cleanser soap. Arm descriptions explain that the test products were applied to assigned areas of the face and lower legs. The description for Test Product 1 specifies pumps of product, while Test Product 2 is described using pea-sized and walnut-sized amounts. The soap description instructs participants to cleanse the face and lower legs with wet soap and warm water twice daily. These descriptions do not fully establish how every outcome group maps to every regimen in the record, so the group labels should be read as recorded rather than used to infer additional protocol details.

For the primary outcome, the modified intent-to-treat population includes participants with available outcome data. The posted facial analysis includes 70 participants for Test Product 1, 66 for Test Product 2, and 137 for standard cleanser soap. These outcome-specific counts need not match total enrollment, because the primary outcome population is defined by data availability. The original sample-size justification, recruitment target rationale, detailed allocation procedures, and full analysis plan are not reported in the registry record. The registry record also does not report an interim-analysis plan or explain how masking was maintained.

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 174 participants were screened, out of which 158 participants were enrolled, 149 participants were randomized and 25 participants not randomized. Out of 149 randomized participants, 7 participants did not completed study because 3 participants experienced adverse event, 3 participants withdrew consent and 1 participant due to other reason.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Modified Intent-to-Treat (MITT) population. Here, number analyzed indicates participants with available data for this outcome measure.

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 comprised of all randomized participants who applied at least one dose of the study product.

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline in Trans-epidermal Water Loss (TEWL) Following Application of Test Regimen on Face (Area 1 Compared to Area 2) at Day 29, measured over Baseline and Day 29.

The primary endpoint is change from baseline in trans-epidermal water loss (TEWL) on the face at Day 29, measured in g/m^2/hr. Change is calculated as the Day 29 measurement minus the baseline measurement. A negative change therefore indicates a lower measured TEWL value at Day 29 than at baseline; the posted group means are negative.

TEWL is a non-invasive measure related to the integrity of the stratum corneum barrier. The registry describes use of a Tewameter TM 300. Its probe measures the density gradient of water evaporation indirectly using temperature and relative-humidity sensors. The probe was held on the skin for one measurement lasting 40 sec, with the values from the last 10 sec averaged as the measurement. This procedure is intended to obtain a stable reading, but the outcome remains a measurement of water evaporation rather than a direct measure of every aspect of skin health or comfort.

The primary outcome compares facial areas 1 and 2 at baseline and Day 29. Comparing change, rather than only the Day 29 value, makes the outcome explicitly account for each group’s baseline measurement. The outcome description does not report an adjusted model, a clinically important threshold, or a minimum change considered meaningful to participants. Therefore, the size and statistical uncertainty of the mean differences can be described, but their practical importance cannot be determined from the registry record alone.

7. Results Posted in the Registry

• Test Product 1: mean -5.08 versus -3.69 on control; difference -1.38 (95% CI -3.20 to 0.43), standardized effect d = -0.22; z-test p = 0.134.
• Test Product 2: mean -4.95 versus -3.69 on control; difference -1.25 (95% CI -3.07 to 0.57), standardized effect d = -0.20; z-test p = 0.177.

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 TEWL Following Application of Test Regimen on Legs (Area 5 Compared to Area 6) at Day 29

• 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 1: mean -3.58 versus -1.32 on control; difference -2.26 (95% CI -3.36 to -1.16), standardized effect d = -0.58; z-test p = <0.001.
  • Test Product 2: mean -3.15 versus -1.32 on control; difference -1.83 (95% CI -2.84 to -0.83), standardized effect d = -0.49; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Test Product 1 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 Test Product 2 than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline in TEWL Following Application of Test Regimen on Face (Area 1 Compared to Area 2) at Day 15

• 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 1: mean -4.47 versus -3.30 on control; difference -1.18 (95% CI -2.89 to 0.54), standardized effect d = -0.20; z-test p = 0.178.
  • Test Product 2: mean -5.96 versus -3.30 on control; difference -2.67 (95% CI -4.58 to -0.75), standardized effect d = -0.44; z-test p = 0.006.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Test Product 1 and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Test Product 2 than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline in TEWL Following Application of Test Regimen on Legs (Area 5 Compared to Area 6) at Day 15

• 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 1: mean -2.07 versus -0.71 on control; difference -1.36 (95% CI -2.24 to -0.49), standardized effect d = -0.43; z-test p = 0.002.
  • Test Product 2: mean -1.94 versus -0.71 on control; difference -1.24 (95% CI -2.19 to -0.28), standardized effect d = -0.38; z-test p = 0.011.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Test Product 1 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 Test Product 2 than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The registry lists 15 secondary outcomes, including TEWL changes on the face and legs at different visits and Corneometer measurements at specified time points. Available secondary summaries include TEWL comparisons on the legs at Day 29 and Day 15, and on the face at Day 15. Across those summaries, the reported mean differences are negative, but their statistical evidence is not uniform: some intervals include zero and some lie below zero. This mix is consistent with the primary facial result being uncertain rather than establishing one consistent pattern across every location and visit.

In broad terms, the available leg TEWL comparisons show more consistent evidence of differences from standard cleanser soap than the primary facial comparison. The facial Day 15 comparison varies between the two test products. These secondary results can add context about location and timing, but they do not answer the primary Day 29 facial question. They should not be substituted for it or treated as independent confirmation without considering the full set of outcomes.

Unadjusted secondary results carry less weight because many outcome measures, body sites, visits, and measurement types are listed. When many comparisons are made, some may appear statistically notable by chance even if there is no underlying difference. The registry record does not report a multiplicity adjustment, a testing hierarchy, or which secondary outcomes were designated as confirmatory. The secondary p-values therefore describe individual comparisons without controlling the overall chance of false-positive findings across the outcome set.

The record lists Corneometer outcomes, but the available secondary summaries do not include their result estimates. The number of outcome measures and the number of analyses reported in the registry are distinct: the record lists 16 outcome measures in total and zero reported analyses. The posted summaries allow statistical descriptions of selected outcomes, but not a full assessment of every registered secondary measure or the prespecified role of each one.

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

• Change From Baseline in TEWL Following Application of Test Regimen on Legs (Area 5 Compared to Area 6) at Day 29
• Change From Baseline in TEWL Following Application of Test Regimen on Face (Area 1 Compared to Area 2) at Day 15
• Change From Baseline in TEWL Following Application of Test Regimen on Legs (Area 5 Compared to Area 6) at Day 15
• Change From Baseline in Corneometer Values Following Application of Test Regimen on Face (Area 1 Compared to Area 2) at Two Different Time-points [30 Minutes (Mins) and 6 Hrs After First Application] at Day 1 and One Time-point at Day 2
• Change From Baseline in Corneometer Values Following Application of Test Regimen on Legs (Area 5 Compared to Area 6) at Two Different Time-points (30 Mins and 6 Hrs After First Application) at Day 1 and One Time-point at Day 2
• Change From Baseline in Corneometer Values Following Application of Test Regimen on Face (Area 1 Compared to Area 2) at Day 15 and 29
• Change From Baseline in Corneometer Values Following Application of Test Regimen on Legs (Area 5 Compared to Area 6) at Day 15 and 29
• Change From Baseline in TEWL Following Application of Test Regimen on Face (Area 1 Compared to Area 2) at Day 30, 31, 32, 33 and 34

9. Statistical Interpretation

10. Statistical Methods Explained

The primary measure is continuous: each participant’s TEWL is recorded on a numerical scale, and the registry reports a mean and standard deviation for each group. The endpoint is change from baseline, so an individual’s Day 29 value is compared with that person’s baseline value before the group mean change is calculated. A negative mean represents a lower value at follow-up on average. The standard deviation describes how dispersed individual changes are around the group mean; it is not the uncertainty of the mean itself.

How should the group comparison be read?

The posted comparison is a difference in mean changes: the mean change for a test-product group minus the mean change for standard cleanser soap. The Test Product 1 estimate is -1.385, and the Test Product 2 estimate is -1.254. In this direction of subtraction, a negative estimate means the test-product group has a more negative average change than the soap group. It does not show that every participant’s measurement changed in that direction, and it does not by itself establish a cause-and-effect relationship.

Each estimate is accompanied by a confidence interval. A confidence interval gives a range of values compatible with the observed data under the method used; narrower intervals indicate greater precision, while wider intervals indicate greater uncertainty. For both primary comparisons, the interval extends across zero. Zero represents no difference between group mean changes. Thus, the data do not rule out zero difference at the interval’s stated level. The confidence level itself is not reported in the registry record.

What does a p-value add?

The primary unadjusted p-values are 0.134 and 0.177. A p-value describes how unusual data at least as discrepant as those observed would be under a specified null model of no difference, assuming the model and its assumptions are appropriate. It is not the probability that the null hypothesis is true, and it does not measure the size or practical importance of a difference. The record does not report an adjustment for multiple comparisons. Consequently, these p-values should be treated as unadjusted evidence for the individual comparisons, not as a family-wide assessment across all outcomes and time points.

The posted calculations are unadjusted comparisons based on the group summaries. The registry record lists no reported analyses and does not describe the sponsor’s full statistical model, covariate adjustment, or prespecified testing hierarchy. This matters because the exact analysis plan can affect estimates, standard errors, and interpretation. There is no indication in the registry record that the recalculated comparisons should replace a sponsor analysis; no discrepancy is flagged, but the sponsor’s detailed analysis method is not reported.

Why do outcome populations and variability matter?

The primary endpoint uses the modified intent-to-treat population, defined in the record as participants with available data for the outcome. The numbers analyzed therefore differ by group and do not have to equal total enrollment. The registry record does not explain how missing measurements were handled beyond defining the analyzed population by available data. If availability is related to participants’ measurements or experience, an available-data analysis can differ from the result that would have been observed with complete follow-up. The extent and handling of missingness are not reported in the registry record.

Standard deviations are substantial relative to the mean differences in the primary comparisons. General statistical context: when individual observations vary widely within groups, a given difference in group means is estimated less precisely, all else being equal. The uncertainty also depends on the amount of available data in each group. A standard deviation describes participant-to-participant spread; the confidence interval for a difference describes uncertainty about the group contrast. These are related but not interchangeable quantities.

What assumptions underlie the planning illustrations?

The sample-size planning illustrations use a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. They consider effects equal to 100%, 75%, or 50% of the observed effect. These are planning assumptions for illustrative sample sizes, not evidence about the original trial’s design. The original design assumptions and sample-size justification are not reported in the registry record.

General statistical context: the normal approximation treats the sampling distribution of a statistic as approximately normal for planning purposes. Its suitability depends on the outcome distribution and design; the registry record does not provide diagnostic information or a detailed justification. For continuous outcomes, these illustrations report participants per arm. The 80% and 90% power columns represent the planned chance of detecting the stated effect under the assumed model if the assumptions hold. They are not the probability that a result is true, nor are they a measure of the trial’s observed evidential strength.

General statistical context: power depends on the target effect, variability, allocation, significance threshold, and analysis method. Smaller effects are harder to distinguish from random variation and therefore require more participants under otherwise comparable assumptions. The illustrations use an observed effect as their starting point, so they are sensitive to uncertainty in that estimate. The original study’s own planning rationale is not reported in the registry record.

11. Confidence Intervals and Precision

The primary mean-difference estimates are -1.385 for Test Product 1 versus standard cleanser soap and -1.254 for Test Product 2 versus standard cleanser soap. Their confidence intervals extend from -3.197 to 0.427 and from -3.074 to 0.566, respectively. Each interval includes zero, the value corresponding to no difference in mean change. The intervals also include values on either side of zero, so the point estimates alone should not be read as a precise determination of the direction or magnitude of the between-group difference.

Precision is about how tightly the data constrain an estimate. A wide interval leaves more plausible values open; a narrow interval would provide stronger localization. The primary intervals span a range that includes both a negative difference and a positive difference. The registry does not report the confidence level attached to these intervals, so it cannot be named from the record. Their interpretation is conditional on the calculation method and assumptions used.

The standard deviations for the primary outcome are 6.408, 6.263, and 6.064 for Test Product 1, Test Product 2, and standard cleanser soap, respectively. These values describe variability in individual changes, rather than precision of the group comparison. The outcome-specific analyzed group counts are 70, 66, and 137. Unequal analyzed group sizes and variation in participant measurements contribute to the uncertainty around a contrast.

The p-values, 0.134 and 0.177, are consistent with the intervals crossing zero, but they do not resolve the uncertainty or establish that the groups are equivalent. A non-significant result can reflect a small difference, substantial variability, limited information, or some combination. The registry record does not report an equivalence margin, a non-inferiority margin, or a clinically meaningful threshold. The available results therefore support a description of uncertainty, not a claim that the groups are the same or that a particular difference matters to participants.

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 participants per arm, not total participants, because these are continuous-outcome planning illustrations. The assumptions listed for them are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set to the stated fraction of the observed effect: 100%, 75%, or 50%. These are planning assumptions for the illustrations; the original trial’s own sample-size assumptions and justification are not reported in the registry record.

The 80% power column gives the planned number of participants per arm for an 80% chance of detecting the specified effect under those assumptions. The 90% power column gives the corresponding number for a 90% chance. Power is a property of a design under an assumed effect and statistical model; it is not the probability that a finding is true. These planning figures are not observed power.

For each comparison, the figures rise as the target is reduced from the full observed effect to 75% or 50% of it. This reflects a general statistical principle: smaller effects are harder to distinguish from random variation, so more participants are needed when the other assumptions are held fixed. Because the observed effect is used as the planning starting point, these numbers are illustrative rather than a reconstruction of the trial’s original design. The registry record does not report the original sample-size rationale.

The curves associated with planning figures should be read as illustrating the same relationship between assumed effect size and required enrollment, rather than as observed trial results. Their values depend on the specified assumptions and should not be treated as a prediction of what a future study will find. No planning figures are total event counts; event-count planning applies to time-to-event outcomes, while this endpoint is continuous.

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 = -1.385; pooled standard deviation σ = 6.182.
2. n = 2 × (1.96 + 0.842)² × 6.182² / -1.385² = 312.7, rounded up to 313 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 <- -1.385                      # observed difference in means
sigma <- 6.18166733588214                     # 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(3804710)
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 = 313 (80% power), 419 (90% power)
 75% of observed effect: n per arm = 556 (80% power), 745 (90% power)
 50% of observed effect: n per arm = 1,251 (80% power), 1,675 (90% power)
power.t.test: 313.7 
Simulated power at n = 313 per arm: 0.797 (20000 replicates)

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

14. Multiplicity, Missing Data and Analysis Populations

The registry lists 16 outcome measures, including the primary TEWL endpoint and multiple secondary outcomes covering different sites, visits, and measurement types. The record lists zero reported analyses. No method for controlling multiplicity, no testing hierarchy, and no distinction between confirmatory and exploratory secondary tests are reported in the registry record. The comparison p-values are unadjusted. Their interpretation is therefore limited to the individual contrasts and does not account for the larger set of outcomes and comparisons.

Multiplicity matters because each additional statistical test creates another opportunity for an apparently unusual result to arise by chance. General statistical context: when a study examines many outcomes or time points, interpreting each p-value as if it were the only test can overstate the strength of evidence across the study as a whole. Adjustment methods or a prespecified hierarchy can help address this issue, but the record does not identify such an approach. The secondary results should consequently be treated as supportive or exploratory descriptions rather than as a confirmed set of separate findings.

The primary outcome population is described as modified intent-to-treat, with participants included when data are available for that outcome. The primary analyzed counts are 70 for Test Product 1, 66 for Test Product 2, and 137 for standard cleanser soap. The registry record does not report how many measurements were missing, why data were unavailable, whether missingness differed by group, or whether imputation or sensitivity analyses were used. Defining the analyzed population by data availability does not by itself show whether missing data could affect the comparison.

The registry record also does not report the full statistical analysis plan, model specification, covariate adjustment, confidence level, or a formal strategy for handling deviations from the planned analysis. The absence of these details limits independent evaluation of whether the posted unadjusted comparisons match the intended primary analysis. The record’s results can still be read descriptively, but they do not provide enough information to resolve these methodological questions.

15. 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 0% reporting threshold.

Most frequent non-serious adverse event terms

The safety record lists five groups, with the numbers at risk recorded separately for each. For Treatment Regimen 1, 75 participants were at risk for serious adverse events; for Treatment Regimen 2, 74 were at risk. The Test Product 1 and Test Product 2 groups list 75 and 74 at risk, respectively, and the Standard Soap group lists 149. Each listed group has 0 serious adverse events and 0 deaths. No serious-event terms are listed.

These are counts as recorded for each safety group. The group labels include regimens combining a test product with standard soap as well as product and soap groups; the record does not explain the relationship among all safety group counts. They should not be added to create a unique participant total, because the record does not establish that the groups are mutually exclusive.

A zero count in the posted record means no serious adverse event was recorded in that group for the reported safety summary. It does not establish that the products have no risks, and it does not describe every possible adverse outcome or longer-term experience. The registry record does not report further detail about event collection, follow-up completeness, or definitions for the safety summary. These figures are therefore a bounded description of the recorded serious events and deaths, not a comprehensive safety conclusion.

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

The posted primary data show negative mean changes in facial TEWL from baseline to Day 29 in the two test-product groups and in the standard cleanser soap group. The estimated differences versus soap are also negative, meaning the test-product group means had larger reductions on average. But the confidence intervals for both comparisons include zero, and the unadjusted p-values are 0.134 and 0.177. The data therefore leave meaningful uncertainty about the between-group differences.

These estimates describe averages. They do not imply that every participant experienced a decrease, and they do not show how individual responses were distributed beyond the reported standard deviations. The measurement is TEWL, a non-invasive indicator related to skin barrier function, not a complete measure of symptoms, satisfaction, quality of life, or every dimension of skin health. The registry does not report a threshold for a meaningful difference in this measurement.

The results do not establish equivalence between either cream and standard cleanser soap. Demonstrating equivalence would require an explicitly defined margin and a method designed to assess whether the uncertainty lies within that margin; neither is reported. Likewise, failure to obtain an unadjusted p-value below 0.05 does not establish that there is no difference. The estimates and intervals provide the appropriate description of what these data can and cannot distinguish.

The secondary summaries add observations across other sites and visits, but the registry lists many outcomes and does not report a multiplicity strategy. Those comparisons have a more exploratory interpretation and do not resolve the uncertainty in the primary facial Day 29 result. No medical advice follows from these registry statistics. The findings should be understood as results for the recorded measurements, groups, and follow-up period, not as a general claim about all people, products, or uses.

17. Why This Trial Matters Statistically

This study illustrates why a group mean difference should be read together with its uncertainty. The primary point estimates are negative, but both confidence intervals cross zero. The direction of the estimated contrast is therefore not enough to establish a clear difference between the test-product groups and standard cleanser soap. Reporting the interval makes the range of uncertainty visible rather than reducing interpretation to a single point estimate or p-value.

It also shows the distinction between within-group change and between-group comparison. Each group had a negative mean change in facial TEWL. The primary question, however, is not whether values changed within each group, but whether the mean change differed between a test product and soap. A change in every group can coexist with uncertain evidence for a difference between groups.

The record also provides an example of why statistical significance and practical importance are separate questions. A p-value does not tell readers whether a difference is large enough to matter, and the registry does not give a threshold for a meaningful TEWL change. The secondary outcomes add further complexity because multiple locations, visits, and measures are listed without a reported multiplicity plan. Their results should not be treated as a collection of equally strong confirmations.

Finally, the trial’s posted comparisons and the planning illustrations answer different questions. The comparisons describe estimated effects and uncertainty in the observed data. The sample-size figures illustrate how enrollment requirements change under stated assumptions and target effects; they do not reconstruct the original design or quantify observed power. Keeping those roles separate helps prevent planning calculations from being mistaken for evidence about the trial’s results.

18. Limitations

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

The primary facial outcome is based on available data in a modified intent-to-treat population. The registry record does not report the amount or pattern of missing data, reasons for unavailable measurements, or sensitivity analyses. If data availability was related to measurements or participant characteristics, the analyzed group summaries might not fully represent everyone enrolled.

The registry record does not describe the complete statistical analysis plan, model specification, or any covariate adjustment. It lists zero reported analyses, while the available comparisons are unadjusted calculations from posted summaries. The confidence level for the reported intervals is not stated. These omissions limit the ability to assess whether the posted calculations correspond to the intended analysis and how robust they are to alternative methods.

The primary result concerns facial TEWL at Day 29, while the study also lists outcomes across other body sites, visits, and measurement types. No multiplicity adjustment or testing hierarchy is reported. This makes secondary findings more vulnerable to selective emphasis and chance findings across a large set of comparisons. Some listed secondary outcome results are not included among the available summaries.

The posted outcome is a physiological measurement, and no clinically meaningful threshold is reported. The record does not provide participant-reported outcomes or longer-term follow-up in the registry record described. The original sample-size justification and design assumptions are also not reported, so the planning illustrations cannot establish whether the study was designed around a particular clinically important effect. Finally, the group descriptions do not fully explain how all regimen and safety groups relate to the outcome groups, limiting interpretation of the study structure beyond the randomized, double-masked, parallel description.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: To Evaluate the Effect of Moisturizing Creams on Skin Barrier Function — NCT03804710.
• Registry record last updated 2020-06-04; status last verified 2020-06.
• Results first posted 2020-06-04.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

22. Record Summary

NCT03804710 is a completed randomized, double-masked, parallel study sponsored by GlaxoSmithKline. It enrolled 158 participants and evaluated two developmental moisturizing creams in relation to skin barrier measurements, with standard cleanser soap as the primary comparison group. The brief summary describes twice-daily topical application over 4 weeks.

The primary outcome was change from baseline in facial TEWL at Day 29, measured in g/m^2/hr. Mean changes were -5.077 for Test Product 1, -4.946 for Test Product 2, and -3.692 for standard cleanser soap. The unadjusted mean differences versus soap were -1.385 and -1.254; both confidence intervals included zero.

The record also lists secondary TEWL and Corneometer outcomes and safety groups. It does not report the original sample-size justification, full analysis plan, missing-data methods, or multiplicity strategy. Safety summaries list 0 serious adverse events and 0 deaths in each recorded group.