The Addition of Montelukast to Fluticasone in the Treatment of Perennial Allergic Rhinitis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for The Addition of Montelukast to Fluticasone in the Treatment of Perennial Allergic Rhinitis (NCT00119015), a randomized phase 4 study. The primary outcome is Change From Baseline in Total Nasal Symptom Score (TNSS) Over 2 Week Randomized Treatment Period.

2. Clinical Question

The clinical question is about an add-on treatment, not a comparison of fluticasone against no fluticasone. The recorded baseline was measured after a period of fluticasone therapy, before the randomized treatment period. This makes the outcome a change from symptoms during fluticasone treatment, rather than a change from an untreated state.

The registry lists sneezing, runny nose, stuffy nose, and other symptoms as secondary outcomes. The other-symptom category includes itchy nose or eyes and post-nasal drip. Whether participants had to meet a particular symptom threshold before randomization is not reported in the registry record, so the target population cannot be described more narrowly.

3. Trial Design

This was a Phase 4, randomized, double-blind, parallel-group trial sponsored by the University of Chicago. The registry lists enrollment of 102 and a status of terminated. The listed start was 2005-07, and primary completion was 2008-06. The reason for termination and its timing relative to these dates are not reported in the registry record.

The two arms were fluticasone propionate plus montelukast and fluticasone propionate plus placebo. Both used fluticasone nasal spray at 2 sprays in each nostril once a day for 2 weeks, described as 200 micrograms daily. The additional oral medication was montelukast or placebo, each described as 10 mg daily for 2 weeks. Randomization and double masking are stated in the registry, but details of sequence generation, allocation concealment, and who was masked are not reported in the registry record.

The primary outcome was change from baseline in total nasal symptom score over the 2-week randomized treatment period. Baseline was defined using symptom scores from the last 5 days of fluticasone therapy before randomization. The registry says that the daily changes during randomized treatment were averaged for each participant and that the group median and full range of these participant-level averages were reported.

The primary outcome lists 28 participants in the fluticasone-plus-montelukast arm and 26 in the fluticasone-plus-placebo arm. These outcome counts are not the same information as overall enrollment. The relationship between enrollment, randomization, and the numbers contributing to this endpoint is not explained in the registry record. Reasons for any differences in the counts, if applicable, are not reported in the registry record.

The registry lists four secondary symptom-score outcomes. The specific statistical analysis plan, including any planned interim analyses or sample-size justification, is 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: Those having residual symptoms (total nasal symptom score of 4+) after the open-label phase were randomized to montelukast or placebo for another two weeks in addition to fluticasone propionate. Of the 102 subjects in open-label phase, 54 with residual symptoms were randomized and are listed as "completed" in open-label period of participant flow.

Open-Label Phase (2 Weeks)

Reasons for not completing this period:

Double-Blind, Randomized Phase (2 Weeks)

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 Change From Baseline in Total Nasal Symptom Score (TNSS) Over 2 Week Randomized Treatment Period, measured over Baseline and 2 weeks.

The primary endpoint is the change from baseline in total nasal symptom score (TNSS) during the 2-week randomized treatment period. Participants recorded severity twice a day for sneezing, runny nose, stuffy nose, and other symptoms, including itchy nose or eyes and post-nasal drip. Each symptom was scored from 0 to 3, where 0 means no symptoms and 3 means severe symptoms. Morning and evening symptom scores were summed to form a TNSS with a range of 0 to 24.

The baseline used in the analysis was the average of symptom scores from the last 5 days of fluticasone propionate therapy before randomized treatment. For each participant, the change from baseline was calculated for each subsequent treatment day. Those daily changes were then averaged so that each participant contributed one summary measure. The registry reports the median and full range of these participant-level average changes within each arm.

A negative change indicates improvement in symptoms relative to baseline. The endpoint therefore expresses symptom change during add-on treatment against a recent period of fluticasone therapy. It combines several nasal and related symptoms into one measure, rather than focusing on a single symptom. The registry does not report a clinically important difference threshold for TNSS, so the clinical importance of a particular change cannot be determined from the score alone.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The reported primary comparison uses the Wilcoxon (Mann-Whitney) method. The outcome posted to the comparison is each participant’s average change in TNSS over the randomized treatment period. Although the trial collected repeated daily symptom scores, the registry describes summarizing them to one average change per participant before comparing the groups.

What does the Wilcoxon (Mann-Whitney) test compare?

As a general statistical explanation, the Wilcoxon (Mann-Whitney) test ranks the observations from both groups together and assesses whether values from one group tend to be higher or lower than values from the other. It is often used when an analysis is based on ordered values or when a comparison of distributions is preferred to a comparison of means. Its interpretation is not automatically a test of the difference between the two medians. A median-focused interpretation requires assumptions about how the group distributions relate to one another.

In this trial, the posted summaries are medians and full ranges, while the test is rank-based. The p-value therefore does not supply an estimate of the magnitude of a between-group difference. A confidence interval for a treatment contrast would help show which contrast values are compatible with the observations and how precisely the contrast is estimated. Such an interval is not reported in the registry record.

Why summarize repeated scores by participant?

As a general statistical principle, repeated observations from one person are usually correlated: a participant’s symptom score on one day may be related to that same participant’s score on another day. Treating each daily score as independent could give too much weight to participants with repeated measurements and could understate uncertainty. The registry’s stated approach first calculates daily change and then averages those changes within each participant, leaving one summary value per person for the group comparison.

This summary approach gives a single measure of average change during treatment for each participant. It also compresses the time pattern: the reported median does not show whether a participant’s symptoms changed steadily, improved early and then returned, or varied from day to day. The registry does not report a separate analysis of the trajectory over time.

How should the median and range be read?

As a general explanation, the median is the middle value when observations are ordered. It is less affected by extreme values than the mean. The full range gives the lowest and highest observed values, but does not show the concentration of observations between those limits. A range can therefore describe the span of the data without conveying how variable a typical participant’s response was.

The endpoint is change from baseline, so its sign carries meaning: the registry defines negative values as improvement. A positive value indicates a higher symptom score than baseline. The reported ranges extend to values on both sides of zero in each arm. This shows that not all observed participant-level average changes had the same direction, though the range alone does not say how many participants had positive or negative values.

What does the p-value establish?

As a general statistical explanation, a p-value describes how compatible the observed data are with a specified null model, under the assumptions of the chosen test. It is not the probability that the null hypothesis is true, and it does not measure the probability that the result occurred by chance in a broad, assumption-free sense. A large p-value is not evidence of equivalence. Equivalence or non-inferiority requires a prespecified margin and an analysis designed to evaluate that question; those details are not reported in the registry record.

The reported p = 0.8 should be read alongside the group summaries, endpoint definition, and outcome counts. It does not provide a confidence interval or a measure of how large a difference remains compatible with the data. Nor does it establish that an effect is absent. The registry does not report the test’s detailed assumptions, an adjusted analysis, or an analysis plan that would clarify whether this comparison was the only primary inferential test.

The posted planning illustration is not observed power. As a general distinction, planning calculations describe the sample size that would be needed under stated assumptions for a future or planned comparison. They do not indicate the probability that this completed trial detected an effect. The registry describes its planning illustration as based on the observed effect, with a two-sided significance level of 0.05, equal allocation, and a normal approximation. The effect fractions and resulting planning values are not reported in the registry record used for this account, and the trial’s own design justification is not reported in the registry record.

10. Analyses Reported by the Sponsor

The registry reports the sponsor’s primary comparison as a Wilcoxon (Mann-Whitney) test with p = 0.8. The arm-level summaries accompanying that comparison are medians and full ranges for each participant’s average change in TNSS. These descriptive summaries and the rank-based test answer related but distinct questions: the summaries describe each group, while the test evaluates the relative ordering of observations between groups.

The registry does not report a confidence interval for the between-group contrast. The posted medians and ranges cannot by themselves reproduce the rank-based test or determine a confidence interval, because they do not contain the individual participant values. No separate recalculated contrast or interval is reported in the registry record. Consequently, the sponsor’s reported test is the available inferential result for the primary comparison, and the arm summaries provide context rather than an independent substitute for that test.

The registry record does not identify a discrepancy between the reported result and a recalculation. That does not add precision to the result: the reported p-value still does not quantify the size of a possible treatment difference, and the absent contrast interval leaves its uncertainty less directly characterized.

11. Multiplicity, Missing Data and Analysis Populations

The registry lists one primary TNSS outcome and four secondary symptom-score outcomes: sneezing, runny nose, stuffy nose, and other symptoms. It reports five outcome measures and five analyses overall, but the multiplicity strategy is not reported in the registry record. In particular, it is not clear whether the primary outcome was treated as the sole confirmatory test, whether secondary outcomes were exploratory, or whether any adjustment was planned for multiple comparisons.

When several outcomes are tested, the chance of at least one apparently unusual result can increase. As a general statistical explanation, multiplicity procedures can control that risk, while an explicitly exploratory approach can frame secondary findings as hypothesis-generating. Without a stated plan, the secondary tests cannot be interpreted as either adjusted or unadjusted confirmatory evidence. Numerical results for the four secondary outcomes are not reported in the registry record. The registry also notes missing or non-estimable values for a two-arm comparison on another endpoint, but the endpoint and reason are not specified in the record available for this account.

Information about missing primary outcome data, the number of participants assessed at each stage, and reasons for missingness is not reported in the registry record. The record does not describe imputation, a complete-case approach, sensitivity analyses, or how participants were included in the primary analysis. Those details matter because missing outcomes can affect both the representativeness of the analyzed groups and the uncertainty of the estimated comparison.

The record also does not describe a prespecified analysis population, such as whether the primary analysis followed all randomized participants or only those with an observed endpoint. The primary endpoint counts are 28 and 26, while overall enrollment is 102; the relationship between these counts is not explained. No interim analyses or stopping rules are reported in the registry record. The trial status is listed as terminated, but the reason and any relationship to the analyses are not reported.

12. Safety Results

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

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 5% reporting threshold.

For fluticasone propionate plus montelukast, the registry lists 0 serious adverse events among 28 participants at risk and 0 other adverse events among 28 participants at risk. For fluticasone propionate plus placebo, it lists 0 serious adverse events among 26 participants at risk and 0 other adverse events among 26 participants at risk. No serious adverse event terms are listed.

These are the recorded adverse-event counts for the populations shown in the registry. Zero recorded events does not establish that no event could occur, and the counts do not describe event severity beyond the registry’s serious versus other classification. The record does not provide further definitions, surveillance details, or information about whether all participants completed safety follow-up.

Deaths are listed as null for both groups, which means a death count is not reported in the registry record. It should not be read as a reported count of zero. The short randomized treatment period was 2 weeks; the registry does not describe additional safety follow-up in the record used for this account. These figures therefore describe the reported counts, not a comprehensive assessment of all possible safety outcomes.

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

The primary result is a comparison of average symptom-score changes over a 2-week randomized treatment period among the participants included in the endpoint summaries. Both group medians were negative, which the registry defines as improvement from baseline. The reported Wilcoxon (Mann-Whitney) p-value is 0.8. Taken together, these figures do not provide strong evidence of a difference between the groups under the reported test, but they do not establish that the treatments have identical effects.

The absence of a reported confidence interval for the treatment contrast is important. A p-value alone does not show the range of effect sizes that may be compatible with the data. The medians and full ranges provide descriptive information for each group, but they do not determine the size or precision of a between-group contrast. The full ranges also show that participant-level average changes varied and included values in both directions.

The comparison concerns adding montelukast versus adding placebo to fluticasone, not using montelukast alone or comparing fluticasone with no treatment. The endpoint reflects a composite symptom score relative to a baseline period after fluticasone therapy. It does not, by itself, establish effects on each individual symptom, outcomes beyond the randomized period, or populations whose eligibility characteristics are not described in the registry.

The registry reports overall enrollment of 102 and endpoint counts of 28 and 26. Without an account of the analysis population, participant flow, and missing-data handling, the coverage of the primary result cannot be fully assessed. Secondary outcome values and a multiplicity plan are also not reported in the registry record.

Accordingly, the posted result is best read as an imprecise summary of one short-term primary comparison, with no reported contrast interval and limited reporting about analysis populations. It does not establish equivalence, rule out differences of potential importance, or answer questions beyond the outcome and period described.

14. Why This Trial Matters Statistically

This trial illustrates why the endpoint definition matters as much as the name of the outcome. TNSS combines several symptoms, uses repeated morning and evening ratings, and is then reduced to one average change per participant. Understanding those steps clarifies what the reported median represents and what information is lost when daily scores are condensed.

It also illustrates the difference between descriptive and inferential statistics. The arm medians and ranges describe the observed participant-level summaries. The Wilcoxon (Mann-Whitney) test compares the groups using ranks. Neither a pair of medians nor a p-value alone supplies a precise estimate of the between-group effect. A confidence interval for that contrast would make its uncertainty more directly interpretable, but none is reported in the registry record.

For biostatistical reading, enrollment and endpoint counts should be distinguished. The registry lists enrollment of 102, while the primary outcome summaries list 28 and 26 participants in the two groups. Without participant flow and analysis-population details, it is not possible to determine from the record why those counts differ or how the analyzed participants relate to enrollment.

The record also shows the limits of interpreting a nonsmall p-value as evidence of no effect. A failure to obtain a small p-value is not a formal demonstration of equivalence, especially when the treatment contrast’s confidence interval and a prespecified equivalence margin are not reported. The result needs to be read as an uncertain comparison, not as proof that any possible difference is negligible.

Finally, the registry lists multiple symptom outcomes but does not report a multiplicity plan or secondary outcome values. This makes it difficult to assess how the secondary results were intended to contribute to conclusions. These reporting features are relevant beyond this trial: clear endpoint definitions, analysis populations, missing-data methods, and treatment-contrast intervals make a result easier to evaluate without over-interpreting a single test statistic.

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 registry record gives limited detail about eligibility criteria. Its summary describes people with continuing symptoms despite a nasal steroid spray, but it does not state how those symptoms were defined, how participants were selected, or which characteristics shaped the intended population. Generalizability beyond the described condition and treatment setting is therefore difficult to assess.

The randomized period lasted 2 weeks, and the primary outcome was based on symptom scores during that period. The record does not report longer-term symptom outcomes or follow-up. The result consequently addresses only the short-term score change as defined, rather than persistence of any change over time.

The primary result is presented as group medians and full ranges, with a rank-based p-value. A confidence interval for the between-group contrast is not reported. The record does not give individual observations, distribution summaries beyond the median and range, or an estimate of the treatment contrast that would allow its precision to be directly assessed.

Overall enrollment is listed as 102, but the primary outcome summaries contain 28 and 26 participants. The record does not describe participant flow or explain these counts. Missing-data methods and the primary analysis population are also not reported, limiting assessment of potential selection or attrition effects.

The registry does not report the protocol’s sample-size justification, detailed statistical analysis plan, multiplicity strategy, or any interim analysis. It lists the trial as terminated but does not report the reason for termination. The results of the four secondary outcomes are not reported in the registry record, and the record notes missing or non-estimable values for a two-arm comparison on another endpoint without identifying it. These reporting gaps constrain interpretation without establishing that any particular analysis was mishandled.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: The Addition of Montelukast to Fluticasone in the Treatment of Perennial Allergic Rhinitis — NCT00119015.
• Registry record last updated 2014-02-28; status last verified 2014-01.
• Results first posted 2013-05-22.
• 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

NCT00119015 is a Phase 4, randomized, double-blind, parallel-group trial sponsored by the University of Chicago. It compared fluticasone propionate plus montelukast with fluticasone propionate plus placebo for perennial allergic rhinitis. The registry lists enrollment of 102, status terminated, a start of 2005-07, and primary completion of 2008-06.

The primary endpoint was change from baseline in TNSS over the 2-week randomized treatment period. The registry reports medians and full ranges for 28 participants in the montelukast arm and 26 in the placebo arm, with a Wilcoxon (Mann-Whitney) p-value of 0.8. Secondary outcomes cover four symptom categories, but their numerical results are not reported in the registry record. The record also lists zero serious and zero other adverse events in both groups; death counts are not reported.

Participant flow, missing-data procedures, the primary analysis population, multiplicity handling, and a confidence interval for the treatment contrast are not reported in the registry record. These omissions limit assessment of precision and completeness.