Montelukast in Perennial Allergic Rhinitis - 2001-2002 Study (0476-246): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Montelukast in Perennial Allergic Rhinitis - 2001-2002 Study (0476-246) (NCT00974571), a randomized phase 3 study. The primary outcome is Mean Change From Baseline in Daytime Nasal Symptoms Score.

2. Clinical Question

The study asked whether montelukast changed daytime nasal symptom scores in patients with perennial allergic rhinitis, compared with placebo. Cetirizine was included as an active control. The registry record describes a multicenter, double-blind, randomized, placebo-controlled, parallel-group study. It does not report eligibility criteria or further details about the population beyond the condition being studied.

The primary outcome was a continuous symptom score: lower ratings represented fewer or less severe symptoms, and the analysis summarized average change from baseline. The posted results give an estimate and a 95% confidence interval for each group. They do not give a numerical treatment-versus-placebo estimate or a test of that comparison. Consequently, the arm-level results describe observed changes but do not, on their own, establish whether the groups differed statistically.

3. Trial Design

This was a phase 3, randomized, double-blind, parallel-group study with placebo control. The official title describes it as multicenter. The sponsor was Organon and Co. The recorded start was 2001-11, and primary completion was 2002-05. The study is recorded as completed, with enrollment of 1365.

Three groups are listed: montelukast 10 mg, cetirizine 10 mg, and placebo. Cetirizine was an active control, while placebo was the control specified for the primary comparison. The reported primary outcome population counts were 626 for montelukast, 120 for cetirizine, and 609 for placebo. These are the numbers associated with the posted primary outcome results; they should not be assumed to describe every analysis or every safety population.

Randomization and double masking describe important design features, but the registry record does not report the allocation ratio, sequence-generation method, concealment procedures, or which study roles were masked. It also does not report the number of centers, eligibility criteria, treatment adherence, or the reasons participants may have been excluded from the primary-outcome population. Such details matter when judging how well the design limits bias and how broadly the findings may apply.

The endpoint timeframe was baseline and the first 4 weeks of a 6-week treatment period. This distinction is important: the posted primary result concerns the specified early treatment interval, not a separate estimate for the full 6-week period. The registry record does not describe the visit schedule or how measurements within that interval were combined beyond defining the score and reporting a least-squares mean change.

Four secondary outcomes are listed: change from baseline in nighttime symptoms, change from baseline in composite symptoms, and patient and physician global evaluations. The registry record does not post analysis results for those outcomes. The study design therefore establishes the intended comparisons and measured outcome, while the available numerical interpretation must remain centered on the posted primary endpoint.

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: Patients who required excluded medication and those who did not meet a minimum predefined level of combined daytime rhinitis symptoms score during the run-in period were excluded from randomization.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: All patients who had a baseline and at least one posttreatment measurement were included.

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 Mean Change From Baseline in Daytime Nasal Symptoms Score, measured over Baseline and first 4 weeks of a 6-week treatment period.

The primary endpoint was mean change from baseline in the Daytime Nasal Symptoms Score, reported as a score on a scale. Patients rated congestion, rhinorrhea, itching, and sneezing daily on a 4-point scale from 0, the best score, to 3, the worst. The average of those four symptom ratings formed the Daytime Nasal Symptoms Score. The outcome therefore combines several daytime nasal symptoms into one continuous measure rather than presenting each symptom as a separate primary result.

Change from baseline expresses how the average score shifted during the assessment interval relative to the starting score. A negative change represents a lower score than baseline, which corresponds to movement toward the better end of this scale. This interpretation concerns the direction of the score; it does not by itself establish that a change is clinically important or caused by a particular treatment.

The registry reports least-squares mean changes and 95% confidence intervals for the first 4 weeks of a 6-week treatment period. In general, a least-squares mean is a model-based estimate of an average. The model specification and any adjustment variables are not reported in the registry record, so the estimates cannot be independently characterized as adjusted for particular factors. The stated primary-outcome population required a baseline and at least one posttreatment measurement.

Combining symptoms can give a concise summary of daytime nasal burden, but an average can conceal different patterns among the component symptoms or among individual patients. The posted primary outcome does not report those individual-level patterns.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous because it is a numerical score that can take values across a scale. The registry reports least-squares mean change and a 95% confidence interval for each group. It does not report the detailed statistical analysis plan, the model used, adjustment variables, or the method used to construct the intervals. The explanations below distinguish general statistical interpretation from what can be confirmed about this study.

What does a least-squares mean represent?

General: A least-squares mean is an estimate of an average derived from a statistical model. Depending on the model, it may account for specified design features or covariates, unlike a simple arithmetic average. The label alone does not identify which factors were included or how they were handled. For this trial, the registry record names the estimate as a least-squares mean but does not report the model specification or adjustments. It is therefore appropriate to describe the posted values as model-based mean changes, without attributing adjustment to any particular variable.

How should a confidence interval be read?

General: A confidence interval conveys uncertainty in an estimated quantity. A narrower interval indicates greater precision for that estimate under the analysis assumptions; a wider interval indicates less precision. A 95% confidence interval is not a statement that 95% of individual observations fall within its limits. Here, the intervals apply to the group-specific mean changes. They do not directly provide the interval for a difference between montelukast and placebo or between any other pair of groups.

The posted group estimates and intervals allow readers to see the direction and precision of each mean change. They do not establish a treatment contrast. In a randomized trial, the treatment effect of interest is commonly expressed as a between-group contrast, with its own estimate and uncertainty. For a continuous outcome, that contrast may be based on a model that includes design or baseline information, but the registry record does not state which approach was used. No numerical contrast or p-value is posted for this endpoint.

Why does over-dispersion matter?

General: Over-dispersion is a concern for some statistical models when the observed variability is greater than the model assumes. If that extra variability is not accommodated, standard errors can be too small and confidence intervals can be too narrow. This concept is especially relevant to certain count or binary outcome models. The primary endpoint in this record is a continuous score, and the registry does not report a model diagnosis or an over-dispersion assessment. It would not be justified to claim that over-dispersion was present or that a particular correction was used.

What can the score scale tell us?

The score is the average of ratings for congestion, rhinorrhea, itching, and sneezing. Each symptom was rated daily on a 4-point scale from 0, best, to 3, worst. Accordingly, a negative mean change indicates a reduction in the average score from baseline. This direction describes the scale, not the cause of the change. Because the measure averages multiple symptoms, the same overall mean could arise from different combinations of symptom changes. The posted summary does not provide component-level or individual-level distributions.

What do planning calculations mean?

General: A sample-size planning calculation asks how many participants may be needed under specified assumptions to detect a chosen effect with a chosen statistical power and significance level. It is a design illustration, not an observed trial outcome and not a measure of the probability that the study result is correct. Calculations based on an effect observed in the completed trial are particularly assumption-dependent: a smaller effect target generally requires more participants than a larger target, all else equal. That is a general statistical relationship, not a new estimate for this study.

The planning assumptions associated with this record describe a two-sided significance level of 0.05, equal allocation between the two arms, a normal approximation, and effects expressed as stated fractions of the observed effect. These are planning assumptions, not evidence about the original trial's design. The record does not report the trial's own sample-size justification, target effect, or power calculation. Any planning figures should be read as illustrations under those stated assumptions, not as observed power and not as the sample-size method used by the sponsor.

The posted results do not supply a two-arm effect estimate for this continuous endpoint. Therefore, a planning illustration based on the observed effect should not be confused with a sponsor-reported comparison. The registry record states that values were missing or not estimable for a two-arm comparison. It also does not report interim analyses, stopping rules, or details of multiplicity control. These omissions limit how fully the statistical conduct can be reconstructed from the registry record.

10. Multiplicity, Missing Data and Analysis Populations

The record lists one primary outcome and four secondary outcomes. The secondary outcomes concern nighttime symptoms, composite symptoms, and patient and physician global evaluations. Numerical results for those secondary outcomes are not reported in the registry record. It also does not report a multiplicity procedure, such as a prespecified sequence of tests or an adjustment for testing several outcomes. Without that information, the family of planned hypotheses and the interpretation of any unreported secondary tests cannot be reconstructed.

For the primary outcome, group-specific least-squares mean changes and confidence intervals are posted, but no two-arm comparison is reported. A group-specific interval does not replace the estimate and uncertainty for the treatment contrast. The registry record indicates that values were missing or not estimable for a two-arm comparison and lists no posted analyses. There is no reported p-value for the primary contrast.

The primary-outcome population included patients with a baseline and at least one posttreatment measurement. This criterion identifies who contributed to the reported primary summaries, but it does not explain how missing measurements were treated, whether any imputation was used, or how many people lacked measurements. The registry record does not report a full analysis-population definition, an intention-to-treat analysis, a per-protocol analysis, or sensitivity analyses for missing data.

Missing outcome information can affect both the precision and interpretation of a result, particularly if the availability of measurements is related to symptoms or treatment experience. That is a general concern; the record does not establish whether such a pattern occurred in this study. The safety denominators differ from the primary-outcome group counts, so the populations used for the two types of summaries should not be treated as interchangeable.

11. 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.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: pregnancy (0.3%), unstable angina (0.2%), laceration (0.2%).

The safety results list participants at risk and counts of serious adverse events and other adverse events for each group. For serious adverse events, the posted counts are 2 among 630 for montelukast 10 mg, 0 among 122 for cetirizine 10 mg, and 3 among 613 for placebo. These are counts, not comparative estimates. The registry record does not provide a statistical comparison, confidence intervals, or a causal assessment for these figures.

The listed top serious adverse event terms are Pregnancy at 0.3%, Unstable Angina at 0.2%, and Laceration at 0.2%. The record does not specify in this summary how those terms were distributed across study groups, so they should not be assigned to a particular treatment. The other adverse event counts are 85 among 630 for montelukast, 16 among 122 for cetirizine, and 65 among 613 for placebo. These summaries do not provide event severity, timing, relatedness, or participant-level detail.

Deaths are not reported in the registry record. Differences in the numbers at risk across the safety groups and the small number of serious events make unadjusted count comparisons particularly limited. These figures describe events recorded in the posted safety summaries; they do not establish whether treatment caused an event or whether event rates differed statistically.

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

The posted primary results show negative mean changes in the Daytime Nasal Symptoms Score in all three groups during the first 4 weeks of the 6-week treatment period. Because lower scores represent better symptom ratings, the direction of each estimate is toward a lower average score than baseline. The 95% confidence intervals convey uncertainty around each group mean change. This describes the posted data without treating within-group changes as proof of a treatment effect.

The central inferential question is whether the change differed between randomized groups. The registry record does not report a numerical treatment-versus-placebo contrast, its confidence interval, or a p-value. Separate group estimates cannot answer that question by themselves. Their intervals describe uncertainty about the separate means, not directly about the difference between means. The absence of a posted comparison does not show that groups were equivalent, nor does it establish that they differed.

The score combines four daytime nasal symptoms and does not reveal how each symptom changed or how responses varied between participants. The primary results also do not provide findings for nighttime symptoms, the composite symptoms score, or patient and physician global evaluations. Those outcomes are listed as secondary outcomes, but their results are not reported in the registry record. The timeframe is limited to the first 4 weeks, rather than a separately reported estimate for the entire treatment period.

The safety summaries give counts of serious and other adverse events in the listed safety populations. They do not provide comparative statistical analyses or establish causation. Deaths are not reported in the registry record. These limits matter because efficacy and safety interpretation both depend on clearly defined populations, complete outcomes, and appropriate between-group analyses.

Overall, the registry record supports a descriptive reading of group-specific mean changes and event counts. It does not provide enough inferential detail to reach a conclusion about the relative effect of the study treatments from the primary outcome. The result should be understood in the context of the stated score, assessment interval, and available analysis information.

13. Why This Trial Matters Statistically

This trial illustrates why randomized design and posted outcome summaries answer different statistical questions. Randomization and double masking are design features intended to support fair comparisons, but interpretation of an effect still depends on the reported between-group estimate and its uncertainty. The registry lists group-specific least-squares mean changes and confidence intervals, but does not post the primary treatment contrast. Readers therefore have descriptive estimates without the central inferential quantity needed to quantify the comparison.

The endpoint also highlights the distinction between a symptom scale and a clinical interpretation. A score can be defined consistently, combined across symptoms, and summarized as a mean change. The direction of that change is interpretable from the scale anchors. However, a mean change alone does not indicate the distribution of individual responses, and the registry record does not report a threshold for meaningful change. No conclusion about clinical importance can be drawn from the posted summaries alone.

Including cetirizine as an active control makes the design broader than a simple treatment-versus-placebo setup, but its presence does not resolve the missing contrast information. The record does not report whether the active-control result met a prespecified criterion or how its role was handled in the analysis plan. This is a reminder that study arms and analysis objectives are not interchangeable: the interpretation depends on the planned comparisons and their results.

Finally, the record identifies some key endpoint details and safety counts while leaving other statistical details unreported. The population definition for the primary outcome is stated, but missing-data handling, model specification, multiplicity procedures, and the sponsor's sample-size justification are not. These gaps limit reproducibility and make it especially important to distinguish posted descriptive findings from conclusions that require analyses not reported in the registry record.

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 primary results are limited to a mean change in a composite daytime symptom score over the first 4 weeks of a 6-week treatment period. The posted summaries do not show the four symptoms separately, the distribution of participant-level changes, or a threshold for interpreting clinical importance. The registry record does not report a separate primary result for the remaining treatment period.

Although the trial is described as randomized and double-blind, the record does not report the allocation ratio, randomization procedures, masking details, or the number of centers. It also does not report eligibility criteria or other baseline characteristics. Those omissions constrain assessment of how participants were selected, how well groups were balanced, and the populations to which findings might apply.

For the primary outcome, the record posts group-specific estimates but no formal two-arm comparison, p-value, or interval for a treatment contrast. Model details and covariate adjustments are not reported. The record states that the reported population included participants with a baseline and at least one posttreatment measurement, but does not explain missing-data handling, report the number with missing outcomes, or describe sensitivity analyses. Results for the listed secondary outcomes are also not reported.

The safety summaries provide event counts but not statistical comparisons, causal assessments, or detailed participant-level information. Deaths are not reported in the registry record. The record also does not report the trial's own sample-size justification, interim analyses, stopping rules, or multiplicity plan. These are specific reporting gaps; they should not be filled by assumptions about common trial practice.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Montelukast in Perennial Allergic Rhinitis - 2001-2002 Study (0476-246) — NCT00974571.
• Registry record last updated 2022-02-03; status last verified 2022-02.
• Results first posted 2010-06-07.
• 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 3, multicenter, randomized, double-blind, parallel-group study sponsored by Organon and Co. It lists 1365 enrolled participants with perennial allergic rhinitis and three groups: montelukast 10 mg, cetirizine 10 mg, and placebo. The recorded study start was 2001-11, with primary completion in 2002-05.

The primary outcome was mean change from baseline in the Daytime Nasal Symptoms Score during the first 4 weeks of a 6-week treatment period. Group-specific least-squares mean changes and 95% confidence intervals are posted. A numerical two-arm comparison is not reported in the registry record. Four secondary outcomes are listed without posted numerical results. Safety summaries report serious and other adverse event counts; deaths are not reported.

The record does not report the primary analysis model, missing-data methods, multiplicity procedures, or the trial's sample-size justification. The posted numerical results therefore support description of group-level scores and safety counts, but not a full reconstruction of the planned inferential analysis.