An Evaluation of the Reduction in Erythema in Adult Patients With Moderate to Severe Persistent Facial Erythema Associated With Rosacea: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for An Evaluation of the Reduction in Erythema in Adult Patients With Moderate to Severe Persistent Facial Erythema Associated With Rosacea (NCT03352323), a na phase 3 study. The primary outcome is Responder.

2. Clinical Question

This question concerns change from the participants’ own pre-dose assessment, rather than a contrast between treatment and a concurrent control group. A responder must meet the stated improvement threshold on both scales; improvement on only one scale does not satisfy the registry definition. The endpoint is expressed as a percentage of responders, so its intended summary is a proportion within the analysis population.

The record lists an enrollment of 50 and says the per-protocol population was used for the endpoint analysis. It also notes that one subject was not compliant with drug applications. The exact handling of that subject in the analysis is not reported in the registry record. Most importantly, the observed percentage of responders is not reported in the registry record. Therefore, the clinical question is identifiable from the endpoint definition, but the posted record does not supply an outcome estimate with which to answer it.

3. Trial Design

The registry classifies NCT03352323 as a Phase 3, single-group study. Enrollment is listed as 50. The study started on 2017-10-18, reached primary completion on 2017-12-06, and is recorded as completed. The intervention is oxymetazoline hydrochloride topical cream, 1%, identified in the intervention listing as oxymetazoline.

No separate control arm is listed, and allocation is marked NA. Masking is listed as none. These design features mean the record does not describe a randomized or blinded comparison between treatment groups. The arm description for oxymetazoline cream is empty, so additional administration details are not reported in the registry record.

The primary outcome is a binary responder measure expressed as a percentage. The assessment time is Day 15. A responder is defined by a 2-grade improvement from pre-dose on Day 1 on both the Clinician Erythema Assessment and Patient Self Assessment scales. The analysis population is described as per protocol, with one subject noted as not compliant with drug applications. The record does not give a fuller account of the analysis population or how compliance affected inclusion.

Because there is no listed comparator, the design can describe the observed response within the single group but cannot directly estimate a between-group treatment contrast. The record does not report a protocol rationale for choosing this design, a sample-size justification, or further details of how assessments were scheduled or conducted. Those items are not reported in the registry record.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Overall Study

Analysis population for the primary outcome, as defined in the registry: Per-protocol population used for analysis; one subject was not compliant with drug applications

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

6. Primary Endpoint

The registry lists the primary outcome as Responder, measured over Day 15.

The primary endpoint is the percentage of participants classified as responders at Day 15. The registry defines response as a 2-grade improvement from pre-dose on Day 1 on both the Clinician Erythema Assessment and Patient Self Assessment scales. Requiring improvement on both measures makes the classification depend on agreement across the clinician assessment and the participant’s self-assessment, according to the stated threshold.

A binary endpoint divides participants into those who meet the response definition and those who do not. Reporting the percentage is a way to express the share of the analysis population meeting that definition. It is not the same as reporting the average change in erythema scores, and the registry record does not provide score distributions or individual changes.

In general, a prespecified responder definition can make an endpoint easier to interpret than an unthresholded score change because it states what degree and pattern of change count as success for the endpoint. That does not establish that the threshold is clinically meaningful; the rationale for the 2-grade threshold is not reported in the registry record. Nor does the definition itself show how many participants responded. The observed responder percentage and its precision are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The endpoint is a binary outcome: each participant either meets the responder definition or does not. The registry expresses it as a percentage of responders and sets the assessment at Day 15. The responder criterion requires a 2-grade improvement from pre-dose on Day 1 on both named assessment scales. This combined rule defines the outcome; it does not report the number of participants who met it.

What does a responder percentage describe?

In general, a responder percentage is a proportion calculated within a defined analysis population. Its interpretation depends on both the event count and the denominator. The registry identifies the per-protocol population as the population used for analysis and gives enrollment as 50, but does not state the endpoint denominator or the number of responders. Enrollment and an analysis denominator are not interchangeable: participants enrolled in a study may not all contribute to a particular analysis. The specific accounting for this endpoint is not reported in the registry record.

A proportion is often accompanied by a confidence interval. In general, a confidence interval conveys uncertainty around an estimate under the assumptions of the method used; it is not a guarantee that the true value lies within the interval. The interval’s width reflects the information in the data and the chosen calculation method. No responder estimate or interval is reported in the registry record, so neither the estimated response rate nor its precision can be evaluated.

What does the single-group structure imply?

The study is recorded as single group, with allocation marked NA and masking listed as none. There is no listed comparator. In general, an observed change from a participant’s pre-dose assessment can describe the course of that group across the assessment period. It does not produce a direct estimate of how the outcome would differ under a separate comparison condition. Without a concurrent comparator, other explanations for change cannot be separated from the intervention’s contribution using a between-group contrast. This is a design consideration, not a finding about the cause of any change in this study.

The before-and-after framing also makes the endpoint dependent on assessments at different times. General sources of variation in repeated assessments can include measurement variability and changes occurring over time. The registry description does not give details about assessor training, reliability procedures, or other methods intended to address measurement variation. These details are not reported in the registry record.

What can the analysis population tell us?

The registry says the endpoint analysis used the per-protocol population and notes that one subject was not compliant with drug applications. Per-protocol analyses generally focus on participants meeting specified protocol requirements, but the exact requirements and handling rules for this trial are not reported in the registry record. The note about compliance does not, on its own, establish the precise analysis denominator or whether any additional participants were excluded from the endpoint calculation.

In general, analysis-population choices can affect the interpretation of an estimate. A per-protocol result pertains to the population included under that analysis definition; it is not automatically equivalent to a result for every enrolled participant. The registry does not report a separate analysis using all enrolled participants, nor does it describe sensitivity analyses for alternative missing-data or compliance assumptions.

Are there reported tests or planning assumptions?

The record lists 1 outcome measure and 0 analyses. It does not report a primary-endpoint test statistic, p-value, adjusted estimate, or confidence interval. The registry record also does not report the statistical procedure used for the primary endpoint. Without the analysis output and method, there is no basis to characterize statistical significance or quantify precision.

The record describes planning illustrations based on the observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. It states that the effect to detect is a stated fraction of the observed effect. Such illustrations are planning scenarios, not observed power and not evidence that the study achieved a particular precision. They rely on an observed effect estimate, which is not reported in the registry record. Specific numeric planning estimates and their interpretation are not reported in the registry record.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Oxymetazoline Cream")
n      <- c(48)
events <- c(8)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Oxymetazoline Cream  48  8  16.7  7.5  30.2  8.7  29.6  8.8  29.7

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 1 outcome measure, with the responder endpoint identified as primary. The registry record does not report a multiplicity plan, such as rules for controlling the chance of false-positive findings when several outcomes or analyses are tested. The responder definition itself uses both the Clinician Erythema Assessment and Patient Self Assessment scales, but that combined criterion does not establish whether other outcomes or analyses were considered in the protocol.

The record lists 0 analyses. It therefore supplies no reported testing results to assess for multiplicity adjustment, and the statistical plan for any planned analyses is not reported in the registry record. The absence of reported analyses should not be interpreted as evidence about what may have been planned or conducted outside the posted record.

For missing data, the record identifies a per-protocol population and notes that one subject was not compliant with drug applications. It does not state whether endpoint assessments were missing, how missing values were handled, or whether any imputation or sensitivity analysis was used. The exact endpoint denominator and the handling of the noncompliant subject are not reported in the registry record.

In general, missing-data methods matter because the result can depend on which participants contribute an outcome and on assumptions made for unobserved measurements. A per-protocol label describes the stated analysis population but does not by itself specify these assumptions. The registry record does not report an all-enrolled analysis or enough detail to compare analysis populations. Consequently, the effect of missingness or compliance-related decisions on the responder estimate cannot be assessed from the posted record.

12. 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 5% reporting threshold.

Most frequent non-serious adverse event terms

The safety listing reports 0 serious adverse events among 50 at risk in the Oxymetazoline Cream group, and 0 deaths. It also reports 3 affected in the other adverse-event category among 50 at risk. No serious adverse event terms are listed. These figures describe the recorded counts; they are not a comparison with an untreated or alternative-treatment group.

In general, an at-risk count is the denominator associated with the safety listing, while the affected count is the number recorded with the event category. The registry does not provide event descriptions for the 3 affected in the other category, so their nature, timing, and severity beyond the category label are not reported in the registry record. It also does not explain further how safety events were collected.

A count of 0 serious adverse events is a statement about the events recorded in this group, not proof that such events are impossible. Without a comparator and additional detail about observation and reporting, the listing cannot estimate a comparative safety difference. The safety counts should also be kept separate from the primary responder endpoint: they answer a different question and do not indicate the responder percentage.

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

The record establishes what the investigators defined as a response: a 2-grade improvement from pre-dose on Day 1 on both the Clinician Erythema Assessment and Patient Self Assessment scales, assessed at Day 15. It also establishes that the study was recorded as a single-group Phase 3 evaluation of oxymetazoline hydrochloride topical cream, 1%, with an enrollment of 50. These design and endpoint details describe the question the study was set up to address.

The record does not report the observed percentage meeting the responder definition. It therefore does not show how common response was in the analyzed group or how precisely that proportion was estimated. No primary analysis results are reported, and the endpoint denominator is not stated. The record cannot support a claim about the magnitude or statistical significance of a response.

Even if a response percentage were available, a single-group result would describe observed outcomes in that group rather than a direct comparison against another condition. In general, a within-group change does not by itself identify the cause of that change. The absence of a listed comparator is important when deciding what conclusions the design can support.

The safety listing gives counts for serious events, other events, and deaths, but those figures are not a substitute for a comparative safety analysis. The registry record does not give further descriptions of the other adverse events or a comparator group.

Thus, the most defensible interpretation is descriptive: the record specifies an endpoint and study design, and it records safety counts, but it does not provide the primary endpoint result. It does not establish that the intervention works or does not work. The clinical effect, its precision, and the possible influence of analysis-population decisions are not reported in the registry record.

14. Why This Trial Matters Statistically

This trial is statistically notable because its primary outcome is a defined binary response measured within a single group. The endpoint rule is explicit: response requires a 2-grade improvement from pre-dose on Day 1 on both named scales at Day 15. That gives readers a clear account of what would count as a responder, while leaving the observed proportion unknown because it is not reported in the registry record.

The single-group design is also central to interpretation. A percentage of responders can describe outcomes in the analyzed group, but without a comparator it cannot directly quantify a difference between treatment conditions. This distinction between describing an outcome and estimating a comparative effect is fundamental when interpreting clinical evidence. It applies regardless of whether the endpoint is a score, a time-to-event outcome, or a binary response.

The per-protocol population and the note about one subject not being compliant with drug applications highlight another important statistical issue: an estimate depends on who is included and how outcomes are handled. The registry record does not supply enough detail to determine the endpoint denominator or the consequences of the compliance note.

Finally, a result needs both an estimate and information about its precision to support quantitative interpretation. The primary responder estimate and its uncertainty are not reported in the registry record. Planning illustrations based on an observed effect cannot fill that gap when the observed effect is unavailable. The record therefore illustrates why design, endpoint definition, analysis population, and reported results must be read together, while avoiding conclusions that the posted data do not support.

15. 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 main limitation for statistical interpretation is that the registry record does not report the observed primary endpoint result. Although the responder definition and assessment time are stated, there is no reported responder percentage, responder count, confidence interval, or test result. The primary endpoint therefore cannot be quantified from this record.

The study is listed as single group, with no comparator, allocation marked NA, and masking listed as none. As a result, the design does not provide a concurrent between-group contrast. An observed within-group response, if reported, would not alone identify how outcomes would differ under another condition.

The analysis population is described as per protocol. One subject was not compliant with drug applications, but the exact handling of that subject and the endpoint denominator are not reported in the registry record. Further details about missing assessments, missing-data methods, protocol requirements, or sensitivity analyses are also not reported in the registry record.

The record lists 1 outcome measure and 0 analyses, but does not report a statistical analysis plan, multiplicity procedures, or a sample-size justification. The rationale for the responder threshold and details of measurement procedures are not reported in the registry record. These omissions limit assessment of the endpoint’s rationale, precision, and robustness.

Safety information is limited to the listed counts: 0 serious events among 50 at risk, 3 affected in the other adverse-event category among 50 at risk, and 0 deaths. The other events are not described, and there is no listed comparison group. These limitations prevent broader comparative interpretation of both efficacy and safety.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: An Evaluation of the Reduction in Erythema in Adult Patients With Moderate to Severe Persistent Facial Erythema Associated With Rosacea — NCT03352323.
• Registry record last updated 2021-11-08; status last verified 2021-11.
• Results first posted 2021-01-05.
• 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.

19. Record Summary

NCT03352323 is recorded as a completed Phase 3, single-group study of oxymetazoline hydrochloride topical cream, 1%, in adults with moderate to severe persistent facial erythema associated with rosacea. Enrollment is listed as 50. The study began on 2017-10-18 and reached primary completion on 2017-12-06. Masking is listed as none, and no comparator group is listed.

The primary outcome is the percentage of responders at Day 15. Response requires a 2-grade improvement from pre-dose on Day 1 on both the Clinician Erythema Assessment and Patient Self Assessment scales. The endpoint analysis population is described as per protocol, with one subject noted as not compliant with drug applications.

The registry record lists 1 outcome measure and 0 analyses. An observed primary endpoint result is not reported in the registry record. Safety counts include 0 serious adverse events among 50 at risk, 3 affected in the other adverse-event category among 50 at risk, and 0 deaths. No serious adverse event terms are listed.