A Study to Evaluate the Safety and Effectiveness of a Nasal Spray to Treat Perennial Allergies: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study to Evaluate the Safety and Effectiveness of a Nasal Spray to Treat Perennial Allergies (NCT00712920), a randomized phase 3 study. The primary outcome is Change From Baseline in 12-hour Reflective Total Nasal Symptom Score (AM and PM Combined) at 28 Days..

2. Clinical Question

The registry describes the purpose as determining whether two allergy medications are more effective than placebo. The clinical question is framed around a patient-reported symptom score covering runny nose, itchy nose, nasal congestion, and sneezing. Each symptom was rated on a scale from 0 to 3, from none to severe, and the score was assessed twice daily.

The planned comparison structure includes two active-treatment groups and a placebo group. The registry record does not report the numerical primary endpoint results, so the direction and size of any difference between the groups cannot be described from this record. It also does not report confidence intervals or a primary-endpoint p-value. The stated question is therefore clear, but the posted information does not establish how the groups differed on the primary measure.

3. Trial Design

This was a randomized, double-blind, placebo-controlled, quadruple-masked, parallel-group phase 3 trial. The registry record lists an enrollment of 581 and identifies perennial allergic rhinitis as the condition under study. The sponsor is Meda Pharmaceuticals. The study began in 2007-01, reached primary completion in 2008-05, and is listed as completed.

Participants were assigned to placebo, 0.1% azelastine hydrochloride, or 0.15% azelastine hydrochloride. The two active regimens were described as nasal sprays administered 2 times a day for 4 weeks. The record gives the dose descriptions as 1096 mcg/2 sprays per nostril for the 0.1% group and 1644 mcg/2 sprays per nostril for the 0.15% group. The trial used a parallel model, meaning the listed treatment groups were separate groups rather than successive treatments within the same participant.

Randomization is intended to support a fair comparison by assigning treatment groups through chance. Masking is intended to limit the influence of treatment knowledge on participants, investigators, or other study personnel; the registry labels the trial double-blind and quadruple-masked but does not explain which roles were masked or how masking was implemented. Allocation concealment procedures are not reported in the registry record.

The primary endpoint was change from baseline in the 12-hour reflective total nasal symptom score, with morning and evening assessments combined, at 28 days. The primary population is identified as ITT. The registry record also lists secondary outcomes involving instantaneous nasal symptoms, a reflective secondary symptom complex, quality of life, and direct visual nasal examinations. It lists 5 outcome measures and 8 analyses, but does not provide enough detail to reconstruct every analysis or outcome comparison. The record does not report the planned sample-size justification, the allocation ratio, or further details about follow-up and analysis procedures.

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: Subjects participated in a 7 day screening period to Identify appropriate subjects based on symptom scores.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: ITT

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 12-hour Reflective Total Nasal Symptom Score (AM and PM Combined) at 28 Days., measured over baseline and 28 days.

The primary endpoint is the change from baseline in the 12-hour reflective total nasal symptom score at 28 days, combining morning and evening assessments. The score is built from four symptoms: runny nose, itchy nose, nasal congestion, and sneezing. Each symptom is rated from 0 for none to 3 for severe, and the total possible score is 24 per day. A higher score reflects more reported symptom severity on the component ratings.

Change from baseline describes how the score at the endpoint differs from the participant's starting score. Comparing such changes between randomized groups can help distinguish group-level symptom trajectories from the starting symptom level. The registry describes an analysis using least squares means and states that baseline was included as a covariate. It also says the model accounted for study day as a within-patient effect, treatment group and site as between-patient effects, and a treatment-by-study-day interaction.

This endpoint is used to summarize several nasal symptoms in one measure rather than treating each symptom as the sole primary outcome. Repeated daily assessment can characterize symptoms over the study period, while the 28-day endpoint sets a specific time for the primary comparison. The record does not report the endpoint values, the estimated between-group contrasts, or uncertainty intervals. Accordingly, the score's definition and intended role are available, but the magnitude and precision of the observed treatment differences are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary analysis is described as using least squares means, with several effects and a baseline covariate included. Those terms describe how the investigators intended to account for repeated symptom measurements and other study features. The registry gives some model components, but does not provide a complete statistical analysis plan or enough information to reproduce the analysis. General statistical explanations below describe the concepts rather than additional details of this trial.

What does a least squares mean represent?

In general, a least squares mean is a model-based group mean adjusted for other terms in the statistical model. It is not necessarily the same as a simple arithmetic average of the observed scores. Adjustment can be useful when the analysis accounts for baseline score, study site, or repeated measurements. In this trial, the record says that baseline was included as a covariate, with study day, treatment group, site, and a treatment-by-study-day interaction included in the model. It does not report the adjusted means or the contrasts between groups.

Why account for repeated measurements?

Participants were assessed twice daily, and the primary score combines morning and evening assessments. Repeated measurements from one participant are generally related to one another; they should not automatically be treated as independent observations. In general, a model for repeated measurements can represent that within-participant structure and estimate group patterns over time. The registry says study day was included as a within-patient effect and treatment-by-study-day interaction was included. It does not state the covariance structure or other technical choices used to model repeated observations, so the precise implementation cannot be inferred.

What does baseline adjustment do?

In general, including a baseline measurement as a covariate can account for starting differences in the outcome and improve the precision of a comparison when the model is appropriate. The registry explicitly states that baseline was a covariate in the primary analysis. The score's change from baseline is the endpoint named in the record, but the model description also identifies baseline adjustment; those statements should be read as a description of the stated analysis rather than as a complete model specification. The record does not say how baseline values or post-baseline observations were handled when they were unavailable.

Why include site and treatment group?

In general, including study site can account for systematic differences among sites, while treatment group represents the groups whose outcomes are compared. The registry says both were modeled as between-patient effects. That description does not show whether sites differed in practice or whether adjustment changed any estimate. Such conclusions would require the results, which are not reported in the registry record.

What does a confidence interval communicate?

In general, a confidence interval describes the statistical uncertainty around an estimated effect under the assumptions of the analysis. A narrower interval indicates greater precision than a wider interval, while the interval's location helps show which effects are compatible with the data and model. Neither the primary endpoint estimates nor confidence intervals are reported in the registry record, so the precision of the treatment comparisons cannot be assessed.

Why can over-dispersion matter?

General explanation: over-dispersion occurs when observed variability is greater than a statistical model expects. If a model does not account for that excess variability, standard errors can be too small and inferential results can appear more precise than warranted. This is a general consideration for statistical modeling, not a feature reported for this trial. The registry does not identify an over-dispersion issue or describe a remedy.

What can be learned from the sample-size assumptions?

The sample-size assumptions describe a planning illustration based on the observed effect, using a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The illustration considers detecting a stated fraction of the observed effect. For non-time-to-event outcomes, such illustrations are expressed as participants per arm for 80% power or 90% power, where those values are calculated. Such planning illustrations are not observed power and do not describe the trial's actual enrollment by group. The record states that the illustration is not the trial's own design. The trial's sample-size justification is not reported in the registry record.

The record also indicates that the primary outcome involves several categories or time points and was not reduced to one comparison. As a result, no single comparison can be used to summarize every possible primary-outcome contrast from this information. The registry lists 5 outcome measures and 8 analyses, but does not report a full multiplicity strategy or complete analysis details. The statistical methods can therefore be described at a broad level, while their full specification and numerical results remain unavailable.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists 5 outcome measures and 8 analyses, with a primary symptom-score endpoint and several secondary outcomes. The primary outcome is described as having several categories or time points and is not reduced to one comparison. When investigators examine multiple outcomes, time points, or comparisons, the chance of observing at least one apparently unusual result can increase. General statistical practice may address this with a prespecified hierarchy, adjusted significance thresholds, or other procedures, but the registry record does not report which approach, if any, was used.

The record identifies ITT as the primary endpoint population. It does not define the population in operational detail or state how participants with incomplete follow-up, protocol deviations, or treatment discontinuation were handled. The method for handling missing symptom scores is not reported in the registry record. It also does not state whether any sensitivity analyses evaluated the effect of missing data assumptions.

The endpoint description specifies repeated assessments, but does not report whether every planned assessment was collected, how missing daily scores were summarized, or whether imputation was used. These details matter because different approaches to incomplete repeated measurements can affect estimates and their uncertainty. No conclusion about the direction or size of such an effect can be drawn without the analysis details and results.

The record does not report an interim-analysis plan, stopping rules, or a detailed prespecified statistical analysis plan. These should not be inferred from the phase, masking, or randomization labels. In the absence of the analysis plan and numerical results, multiplicity control, missing-data handling, and the exact analysis population cannot be independently assessed.

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 2% reporting threshold.

Most frequent non-serious adverse event terms

The registry reports serious adverse event counts of 0 among 192 participants at risk in the placebo group, 0 among 194 at risk in the Astepro 0.1% group, and 0 among 192 at risk in the Astepro 0.15% group. These are the serious adverse event figures recorded for the listed groups. The registry's serious-event terms list is empty.

The record also reports other adverse events affecting 21 of 192 participants in the placebo group, 27 of 194 in the Astepro 0.1% group, and 32 of 192 in the Astepro 0.15% group. These counts refer to participants affected, not necessarily the total number of individual events. The registry does not provide event descriptions in the information, so the types, severity, timing, and relationship to treatment cannot be assessed from these counts alone.

The deaths field is not populated for the listed groups; death counts are not reported in the registry record. The serious adverse event counts should be read as registry-recorded counts over the specified risk groups, not as proof that an event was impossible or that the treatments have equivalent safety. No comparative safety estimate or uncertainty interval is reported. The counts also do not replace consideration of the endpoint results or the full safety information, neither of which can be reconstructed from the listed totals.

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

The record gives a clear outline of a randomized comparison of two azelastine hydrochloride nasal sprays with placebo for perennial allergic rhinitis. It identifies a primary symptom outcome, an ITT population, and a model that accounts for repeated study-day measurements, treatment, site, a treatment-by-study-day interaction, and baseline. These features describe the intended basis for comparing groups.

However, the registry record does not report the numerical primary endpoint results. It therefore cannot show the observed change in each group, the estimated difference between an active-treatment group and placebo, or the uncertainty around any such difference. It is not possible to conclude from the record whether a difference was present, how large it was, or whether the estimates were precise. The study's stated purpose is not itself evidence about the outcome.

The safety information provides counts of serious and other adverse events among the listed risk groups, but no detailed event descriptions or comparative estimates. The serious adverse event count is 0 for each group as recorded. That observation should not be generalized beyond the participants and reporting captured by the registry. The record does not report deaths for the groups, so no death comparison can be made from the information available.

The statistical interpretation is also constrained by unreported details. The registry does not give the complete analysis plan, missing-data procedures, multiplicity strategy, primary endpoint estimates, or confidence intervals. Those omissions limit the ability to judge both the robustness of an analysis and the precision of any group comparison. The trial design supports a planned randomized comparison, but conclusions about the results require numerical outcome data and adequate methodological detail.

Accordingly, the responsible reading is descriptive: this completed phase 3 trial enrolled 581 participants and compared the listed sprays with placebo, using a specified symptom-score endpoint. The posted registry information does not establish an effect on that endpoint. It also does not support a conclusion that the treatments are equivalent or that one is superior. Those claims would require results and statistical evidence not reported in the registry record.

13. Why This Trial Matters Statistically

This trial is statistically informative as an example of how a clinical question can be tied to a repeated, patient-reported symptom endpoint. The primary score combines four nasal symptoms assessed twice daily, and the endpoint focuses on change from baseline at 28 days. That structure illustrates the choices researchers make when converting repeated symptom reports into a group-level comparison at a specified time.

The analysis description also highlights why endpoint definitions and model structure matter. Repeated measurements from the same participant are related, while starting scores and study sites may also be relevant to a comparison. The registry describes a least squares mean analysis that accounts for study day, treatment group, site, a treatment-by-study-day interaction, and baseline. This gives readers a broad sense of the intended model, while also showing why a brief description is not equivalent to a complete statistical analysis plan.

It matters just as much that the results and analysis details are not reported in the registry record. A sophisticated design cannot replace estimates, uncertainty intervals, and a transparent account of how outcomes were analyzed. Without these, readers cannot assess the magnitude or precision of treatment differences, evaluate missing-data assumptions, or understand how multiple outcomes and time points were handled.

The safety counts also illustrate the distinction between a descriptive tally and a comparative inference. Group counts provide a record of reported events, but by themselves do not describe event types or quantify uncertainty in differences between groups. Overall, this trial record demonstrates the importance of reading design features alongside what is and is not reported about results. Statistical conclusions depend on both the planned comparison and the evidence available to evaluate it.

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 main limitation for interpreting this trial record is the absence of numerical results for the primary endpoint. The registry defines the symptom score and describes the analysis, but does not report group changes, between-group estimates, confidence intervals, or a primary-endpoint p-value. The primary question therefore cannot be answered from the posted information.

The analysis description is incomplete for independent evaluation. It gives several model components, but does not state the covariance structure, the method for estimating uncertainty, or the full specification of the analysis. The approach to missing repeated symptom measurements and any sensitivity analyses are not reported in the registry record. Although ITT is named as the primary population, its detailed definition and the number of participants contributing to the analysis are not provided.

The record does not describe multiplicity control despite listing multiple outcome measures and analyses and noting that the primary outcome has several categories or time points. It also does not report the trial's sample-size justification, allocation ratio, interim-analysis plan, or stopping rules. These omissions prevent readers from assessing those aspects of the design or the prespecification of the reported analyses.

For safety, the registry provides group counts for serious and other adverse events, but does not give detailed event descriptions in the information. Death counts are not reported in the registry record. No comparative safety estimates or uncertainty measures are available. These limitations are specific to the information reported and do not establish that additional trial records or analyses do not exist; they mean that these details cannot be evaluated from the registry record.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: A Study to Evaluate the Safety and Effectiveness of a Nasal Spray to Treat Perennial Allergies — NCT00712920.
• Registry record last updated 2011-06-08; status last verified 2011-06.
• Results first posted 2010-01-15.
• 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

NCT00712920 is a completed, randomized, double-blind, quadruple-masked, parallel-group phase 3 trial of nasal sprays for perennial allergic rhinitis. The registry lists an enrollment of 581 and three groups: placebo, 0.1% azelastine hydrochloride, and 0.15% azelastine hydrochloride. The active regimens were described as 2 times a day for 4 weeks.

The primary outcome was change from baseline in the 12-hour reflective total nasal symptom score at 28 days, with morning and evening assessments combined. The registry identifies the primary population as ITT and describes a least squares mean analysis with study day, treatment group, site, a treatment-by-study-day interaction, and baseline included.

Numerical primary endpoint results, confidence intervals, and a primary-endpoint p-value are not reported in the registry record. Serious adverse event counts were 0 in each group; other adverse events affected 21, 27, and 32 participants in the placebo, Astepro 0.1%, and Astepro 0.15% groups, respectively. Death counts are not reported in the registry record.