A Pivotal Subjective Sleep Study of a Nasal Dilator (Breathe Right Tan): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Pivotal Subjective Sleep Study of a Nasal Dilator (Breathe Right Tan) (NCT03549117), a randomized phase 2 study. The primary outcome is Change From Baseline in Mean Total Score of the Nocturnal Rhinoconjunctivitis Quality of Life Questionnaire (NRQLQ) for Each Domain (Sleep, Sleep Time, Symptoms on Waking in the Morning, and Practical Problems) at Day 7.

2. Clinical Question

3. Trial Design

This was a randomized, double-blind, parallel-group, placebo-controlled study of a nasal dilator strip. The registry record lists Phase 2 and an enrollment of 140. Participants were assigned to Breathe Right Tan small/medium nasal strips or placebo nasal strips for use at home. The active and placebo strips were both applied to the outside of the nose according to dispensing instructions. The record identifies GlaxoSmithKline as the sponsor and lists the study status as completed.

The population was selected for chronic nocturnal nasal congestion and sleep trouble. Qualification required congestion every night or almost every night, reported sleep trouble, and a bedtime nasal openness score at most 70 on a 100-point VAS on at least four of seven qualification nights. The NRQLQ was administered at study visits after 7 and 14 days of nightly strip use. The primary outcome specified in the record focuses on Day 7, while secondary outcomes include daily diary VAS changes at multiple study times and improvement on diary questions.

The record describes the primary analysis population as the ITT population, comprising randomized participants who had at least one post-baseline efficacy assessment. It gives this population as n=140. The adverse-event summaries list 70 participants at risk in each group. The registry record does not report details of the randomization sequence, allocation concealment, masking procedures, adherence, or the handling of deviations from assigned treatment. It also does not report the protocol or a detailed statistical analysis plan.

Although the study is labeled double-blind, the record does not specify which roles were masked or how masking was maintained. The design label alone does not establish whether participants, investigators, outcome assessors, or statisticians remained unaware of assignment throughout the study. These details 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.

Before assignment: A total of 200 participants were screened. Out of which 140 participant were randomized in the study. 60 participants were not randomized as 52 of which did not meet study criteria, 2 had adverse event, 3 were lost to follow up, 2 withdrew consent and 1 because of other (unspecified) reason.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The Intent to treat (ITT) (n=140) population included all the participants who were randomized into the study and had at least one post-baseline efficacy assessment.

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: The Intent to treat (ITT) (n=140) population included all the participants who were randomized into the study and had at least one post-baseline efficacy assessment.

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline in Mean Total Score of the Nocturnal Rhinoconjunctivitis Quality of Life Questionnaire (NRQLQ) for Each Domain (Sleep, Sleep Time, Symptoms on Waking in the Morning, and Practical Problems) at Day 7, measured over At Baseline and Day 7.

The primary endpoint is change from baseline in the mean total score for each NRQLQ domain at Day 7. The domains are Sleep, Sleep Time, Symptoms on Waking in the Morning, and Practical Problems. Participants rated their experience on a seven-point scale from 0, “Not troubled,” to 6, “extremely troubled.” The domain totals have different ranges: Sleep and Symptoms on Waking in the Morning range from 0 to 24, Sleep Time ranges from 0 to 30, and Practical Problems ranges from 0 to 18. Lower scores indicate improvement in rhinitis symptoms.

These domain scores represent different aspects of the reported burden of nasal symptoms and related sleep difficulties. Sleep captures problems such as difficulty getting to sleep, waking during the night, restless sleep, or having to get up because of a stuffy nose. Sleep Time includes nasal and related symptoms during sleep; the morning domain addresses symptoms and tiredness on waking; Practical Problems includes symptom avoidance, rubbing the nose or eyes, and medication use.

In general, a change-from-baseline endpoint compares a participant’s score after treatment with their own baseline score. It can describe whether scores moved in a more or less favorable direction over the study period, but a treatment comparison also requires an estimate of how changes differed between groups and the uncertainty around that estimate. The registry record does not report numerical Day 7 domain results or the corresponding between-group estimates and confidence intervals. The endpoint’s stated purpose and scoring are reported, but the observed treatment contrast cannot be interpreted from the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The record identifies the primary outcome as a continuous measure: mean NRQLQ domain score and change from baseline. In general, continuous outcomes retain information about the scale of participants’ responses rather than reducing each response to a category such as improved or not improved. A mean can provide a compact description of a group’s scores, but it does not show the full distribution. Participants may have similar averages despite differing degrees of variability or differing patterns of response.

What does a least-squares mean represent?

The primary outcome specifies a least-squares mean. In general, a least-squares mean is a model-based estimate of a group mean, often adjusted for terms included in the statistical model. It is not necessarily identical to the raw arithmetic average. Interpretation depends on the model specification, the variables included, the analysis population, and the method used for missing observations. Those model details are not reported in the registry record, so the adjustment represented by the listed least-squares mean cannot be described further.

The primary outcome also specifies a 95% confidence interval. In general, a confidence interval expresses the uncertainty around an estimated quantity under the assumptions of the method used. It is not a range that contains a fixed proportion of individual participant scores, and it does not on its own establish clinical importance. A narrow interval generally conveys more precision than a wide one, but judging either requires the actual interval and the scale on which it is reported. Numerical confidence intervals for the primary outcome are not reported in the registry record.

How should change from baseline be understood?

A change score represents the difference between a participant’s measurement at follow-up and their baseline measurement, using the analysis’s specified direction. Here, the registry states that lower NRQLQ scores indicate improvement, but does not give the numerical changes. A change score may account for where participants started, yet it can be affected by baseline variation, measurement error, and the statistical model. A between-group comparison of changes is needed to distinguish change observed under the active strip from change observed under placebo. The record does not provide that comparison for the primary domains.

In general, randomized parallel-group studies compare outcomes between groups assigned to different interventions, with each participant remaining in an assigned group. Randomization is intended to make groups comparable on average before treatment, including for factors that are measured or unmeasured. It does not ensure perfect balance in a particular trial, and it does not prevent bias from differential follow-up, adherence, outcome measurement, or analysis decisions. The registry record names the design as randomized and parallel group but does not report the sequence-generation or concealment methods.

Why does the placebo comparison matter?

A placebo group can help distinguish changes associated with the assigned active treatment from changes that might also occur with study participation, expectations, repeated measurement, or the passage of time. That interpretation depends on the groups receiving comparable study procedures and on the placebo being an appropriate comparator. The record identifies a placebo nasal strip but does not describe the evidence for how closely it matched the active strip in appearance, feel, or other features. It also does not provide masking checks. Therefore, the design description supports understanding the intended comparison but cannot establish how successful masking was.

In general, double masking means that more than one party involved in a study is intended to remain unaware of treatment assignment, but the exact parties vary by study. The registry record does not specify who was masked or how assignments were kept concealed. Because the endpoint is self-reported, participant awareness could matter to reported symptoms and sleep experience. This is a methodological consideration, not evidence that masking failed in this study.

What does statistical precision add?

An estimate’s confidence interval helps readers distinguish a result that is estimated precisely from one that remains uncertain. A result can have a favorable point estimate but substantial uncertainty, or a modest estimate with relatively limited uncertainty. The actual interval is needed to assess which description applies. The record’s endpoint definition names 95% confidence intervals, but numerical estimates are not reported in the registry record. No p-value or recalculated comparison can therefore be discussed.

The registry record also describes a sample-size planning illustration based on the observed effect, with a two-sided significance level of 0.05, equal allocation, and a normal approximation. It states that the effect to detect is a stated fraction of the observed effect. The numerical planning illustrations are not reported in the registry record. In general, such calculations are planning aids under assumptions, not observed power and not evidence that an effect exists. They should not be interpreted as the study’s original design justification; that justification is not reported in the registry record.

In general, over-dispersion matters when the variation in observed data is greater than a model assumes. If it is not handled appropriately, standard errors and confidence intervals may be inaccurate. This is a general statistical issue rather than a reported feature of this trial. The registry record does not describe an over-dispersion assessment or a specific model for the primary outcome.

Finally, statistical significance and practical importance are distinct. A p-value, if reported, would address compatibility with a null model, whereas the effect estimate and its uncertainty would describe the scale and precision of the observed contrast. A patient-reported score’s importance also depends on how the scale is interpreted in context. The registry record does not report a threshold for a clinically important change, nor the numerical outcome estimates needed for that assessment.

10. Multiplicity, Missing Data and Analysis Populations

The record lists 11 outcome measures and 32 analyses, including the primary NRQLQ outcome and secondary daily diary outcomes. Multiple outcomes, domains, times, and analyses create a multiplicity issue: the more comparisons considered, the greater the chance that at least one result may appear noteworthy by chance if all are tested without a suitable plan. In general, methods for addressing multiplicity include prioritizing outcomes, adjusting inference, or clearly separating confirmatory from exploratory analyses. The registry record does not report whether any such approach was prespecified or used.

The primary endpoint comprises four domains, and the record does not reduce them to a single comparison. It explicitly notes that the primary outcome has several categories or time points and is not reduced to one comparison. Without results for each domain and information about the inferential plan, the overall pattern and the role of any individual comparison cannot be assessed. The protocol, prespecified hierarchy, and adjustment method are not reported in the registry record.

The primary analysis population is described as ITT and includes randomized participants with at least one post-baseline efficacy assessment. The record gives n=140 for that population. In general, an analysis population should be understood from its operational definition; an ITT label alone does not guarantee that every randomized participant contributed outcome data or that every participant was analyzed exactly as randomized. The registry record does not describe missing outcome counts, reasons for missingness, imputation, sensitivity analyses, or exclusions from particular analyses.

Missing data can affect both precision and the validity of a comparison, especially if the likelihood of missingness is related to treatment or outcome. In general, complete-case analyses, imputation, and model-based approaches rely on different assumptions. No method should be attributed to this trial without a report. The handling of missing data and the analysis populations for the secondary outcomes are not reported in the registry record.

11. 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 adverse-event summary reports zero serious adverse events in the Active Nasal Strip Group among 70 participants at risk and zero in the Placebo Nasal Strip Group among 70 participants at risk. It also reports zero deaths in each group. For other adverse events, the summary lists 6 affected participants in the active group and 7 in the placebo group, with 70 at risk in each group.

These are participant counts, not a complete description of event types, timing, duration, severity, or whether events were considered related to treatment. The registry record does not provide those details in the adverse-event summary. The counts should not be converted into percentages or treated as a measure of comparative risk without a specified analysis and the relevant event definitions.

In general, an adverse-event count describes events reported under a study’s collection and classification procedures; it does not by itself establish causation. Serious and non-serious events are distinct categories, and an absence of reported serious events in a group does not establish that an intervention is free of risk. The record’s figures are limited to the reported summaries, and the detailed safety analysis is not reported in the registry record.

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

The registry record establishes the study question and the way the primary outcome was defined. The trial compared an active nasal strip with a placebo strip in a population selected for chronic nocturnal nasal congestion and sleep trouble. It focused on changes in four NRQLQ domains, with lower scores defined as improvement and Day 7 specified as the primary assessment.

What the record does not establish is the size or direction of the observed efficacy comparison. Numerical primary outcome estimates, confidence intervals, and p-values are not reported in the registry record. Without them, it is not possible to determine whether the group averages changed, how the groups compared, or how precise any difference was. The same limitation applies to the listed secondary outcomes, for which numerical findings are not reported in the registry record.

In general, an observed change within a group does not by itself show that the assigned intervention caused that change. The placebo comparison is intended to help interpret group differences, but the actual comparison and its uncertainty are necessary. A randomized design can strengthen causal interpretation when implemented and analyzed appropriately, but it does not replace outcome reporting or resolve possible issues with missing data, adherence, masking, or multiplicity.

The safety summary reports no serious adverse events and no deaths in either group, alongside counts of participants with other adverse events. These summaries describe reported counts; they do not provide enough detail to evaluate event characteristics or establish causation. The efficacy and safety information therefore answer different questions and should not be conflated.

Overall, the registry record supports a description of the population, interventions, endpoint, and study design, but it does not support a conclusion about the treatment effect. Such a conclusion would require the outcome estimates and appropriate uncertainty information. The absence of those results in the registry record is a reporting limitation, not evidence that the groups had identical outcomes.

13. Why This Trial Matters Statistically

This trial is statistically notable for combining a randomized, placebo-controlled design with patient-reported outcomes focused on sleep and nocturnal nasal symptoms. The NRQLQ separates several dimensions of experience rather than treating sleep-related burden as a single undifferentiated score. That structure can help describe which aspects of symptoms and daily experience are captured, although it also means that the primary outcome has multiple domains to interpret.

The primary endpoint is based on a scale where lower values indicate improvement, and each domain has a different score range. In general, results from scales with different ranges should be interpreted in their own measurement context rather than compared as if they were identical units. A complete statistical report would make clear how the domain estimates and uncertainty relate to the scale and whether a clinically meaningful threshold was defined. Such a threshold is not reported in the registry record.

The placebo-controlled comparison is also important because symptom reports and sleep experience can be influenced by expectations and repeated assessments. Randomization and masking are intended to limit some sources of bias, but the record does not detail how the randomization and masking procedures were implemented. Statistical interpretation depends not only on the named design but also on the actual results and the analysis choices.

The record’s listing of 11 outcome measures and 32 analyses makes multiplicity and transparent reporting relevant. In general, a clear distinction between primary and secondary analyses helps readers understand which results were intended to carry confirmatory weight. The registry record does not report a multiplicity strategy, and the numerical efficacy results are not reported. Consequently, this study illustrates why endpoint definitions and design labels alone are insufficient for judging evidence: estimates, intervals, analysis details, and transparent reporting are also needed.

14. Limitations

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

The principal limitation for interpreting this trial from the registry record is that numerical efficacy results are not reported. The endpoint definition is detailed, but the group-level changes, between-group contrasts, confidence intervals, and p-values needed to assess the primary comparison are absent. Numerical findings for the secondary outcomes are also not reported in the registry record.

The primary outcome includes four domains, and the record indicates that it is not reduced to one comparison. It lists 11 outcome measures and 32 analyses, but does not report how comparisons were prioritized or whether multiplicity was addressed. Without the prespecified analysis hierarchy or adjustment approach, the inferential role of any individual analysis cannot be determined.

The record names a least-squares mean and a 95% confidence interval but does not describe the model terms, covariance assumptions, or method used to obtain the estimates. The record also does not report how missing data were handled, the number of participants with available primary outcomes, or sensitivity analyses. The ITT population definition includes randomized participants with at least one post-baseline efficacy assessment, but that definition alone does not resolve the potential effect of missing assessments.

Details of random sequence generation, allocation concealment, who was masked, and whether masking was assessed are not reported in the registry record. Adherence and protocol deviations are also not described. These omissions do not show that the procedures were inadequate; they limit assessment of how the design was implemented.

Finally, the safety summary gives counts but not event descriptions, seriousness criteria beyond the reported category, timing, or attribution. The record does not report a clinically important change threshold for the NRQLQ domains. These limitations are specific to interpreting the reported record and should not be treated as proof that the underlying study lacked these procedures or analyses.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: A Pivotal Subjective Sleep Study of a Nasal Dilator (Breathe Right Tan) — NCT03549117.
• Registry record last updated 2018-09-25; status last verified 2018-09.
• Results first posted 2018-09-25.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

18. Record Summary

The registry record describes a completed Phase 2, randomized, double-blind, parallel-group, placebo-controlled study sponsored by GlaxoSmithKline. It lists enrollment of 140 and compares Breathe Right Tan small/medium nasal strips with placebo nasal strips in participants with chronic nocturnal nasal congestion and sleep trouble.

The primary outcome was change from baseline in mean NRQLQ scores across Sleep, Sleep Time, Symptoms on Waking in the Morning, and Practical Problems at Day 7. Lower scores indicate improvement. The stated ITT population included randomized participants with at least one post-baseline efficacy assessment.

Numerical efficacy estimates and their uncertainty are not reported in the registry record. The adverse-event summary reports zero serious adverse events and zero deaths in each group, and other adverse events in 6 participants in the active group and 7 in the placebo group. The record lists 11 outcome measures and 32 analyses, but does not report the multiplicity approach or detailed missing-data methods.