Comparison of Seasonal Allergic Rhinitis Treatment With 2 Antihistamines Used in Combination With Intranasal Corticosteroid: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Comparison of Seasonal Allergic Rhinitis Treatment With 2 Antihistamines Used in Combination With Intranasal Corticosteroid (NCT00845195), a randomized phase 4 study. The primary outcome is Mean Change in Reflective Total Nasal Symptom Score (rTNSS) From Baseline.

2. Clinical Question

The clinical question is comparative rather than a comparison with no treatment: the two nasal antihistamine options are considered alongside intranasal fluticasone. The primary endpoint uses patient-completed diaries to record four symptoms: runny nose, itchy nose, stuffy nose, and sneezing. Their ratings are combined into a total score, and the primary outcome is the change in the mean score from baseline at the 14-day timeframe.

The registry reports group means and standard deviations for this endpoint, along with a mean difference and confidence interval. Those estimates describe the observed comparison in the per-protocol analysis population. They do not by themselves establish whether any difference is clinically important, and the registry record does not report a threshold for clinical importance.

3. Trial Design

The registry identifies this as a completed Phase 4 study with randomized allocation and a parallel design. It records triple masking, but does not specify which people involved in the trial were masked. Alcon Research is listed as the sponsor. The study start is recorded as 2009-03 and primary completion as 2009-05.

The enrollment was 150. One group received Olopatadine HCl Nasal Spray, 0.6%, and the other received Azelastine HCl Nasal Spray, 0.1%. The study purpose describes the treatments as used in conjunction with Fluticasone Nasal Spray. The registry record does not give further details about how fluticasone was administered or whether its use was identical across groups. The arm descriptions contain no additional treatment details.

The primary endpoint was assessed in a per-protocol population. The registry states that 15 patients were not included in that analysis. The posted primary outcome summaries include 67 participants in the olopatadine group and 68 in the azelastine group. The reasons for exclusion and the specific per-protocol criteria are not reported in the registry record.

The record lists four outcome measures, but no secondary outcome results are posted. It also lists no separate analysis records. The protocol's planned statistical methods, original sample-size rationale, allocation procedures, and details of masking are not reported in the registry record. The completion status indicates that the study is recorded as completed; it does not, on its own, provide further information about conduct or adherence to protocol.

4. Participant Flow and Accounting

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

Overall Study

Analysis population for the primary outcome, as defined in the registry: The analysis was per protocol. 15 patients were not included in the analysis.

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 in Reflective Total Nasal Symptom Score (rTNSS) From Baseline, measured over 14 days minus baseline.

The primary endpoint is the mean change in reflective Total Nasal Symptom Score (rTNSS) from baseline, assessed at 14 days minus baseline. Participants completed diaries recording four symptoms: runny nose, itchy nose, stuffy nose, and sneezing. Each symptom was rated on a whole-unit scale from 0 (none) to 3 (severe), and the four ratings were added to form a composite score with a maximum of 12.

The endpoint uses reflective ratings from the hour since the last dose of study medication. A change from baseline expresses how the group’s average score at the follow-up timeframe differs from its average starting score; the registry reports that change as a mean with a standard deviation. This format is suitable for a continuous measure, where each participant’s score can take values across a range rather than representing only a category such as yes or no.

In general, combining symptom ratings into a total score can provide a compact summary of several related symptoms. It can also conceal differences among the individual symptoms, because the same total may arise from different symptom patterns. The registry record does not report separate results for the four component symptoms or identify a threshold defining an important change. The posted endpoint therefore addresses the average composite score, not whether a particular symptom changed or whether an individual participant experienced a meaningful benefit.

7. Results Posted in the Registry

• Azelastine HCl Nasal Spray, 0.1%: mean 4.15 versus 4.28 on control; difference -0.13 (95% CI -1.02 to 0.76), standardized effect d = -0.05; z-test p = 0.774.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous: it is a numerical composite score, and the registry reports a mean and standard deviation for each group. A mean summarizes the group’s average score, while the standard deviation describes how spread out participant scores are around that average. In general, the mean is useful for comparing group averages, but it does not show the full distribution or reveal whether a small number of participants had unusually high or low scores.

The comparison is expressed as a mean difference. The posted estimate is -0.13 for azelastine relative to olopatadine. Under this ordering, a negative value means the azelastine group’s reported mean change is lower than the olopatadine group’s reported mean change. The sign depends on which treatment is subtracted from which; it does not by itself indicate clinical importance. The group means and standard deviations provide context for the size of the estimated difference.

A confidence interval describes a range of values that are reasonably compatible with the observed data under the method used to construct it. In repeated use of a method with its assumptions met, confidence intervals at a stated confidence level would cover the corresponding true parameter at that level of frequency. The registry record does not state the confidence level or the method used to construct the posted interval, so those details are not reported in the registry record. The interval for the mean difference includes zero, meaning the data are compatible with no difference as well as with values on either side of zero.

The p-value is reported as unadjusted. In general, a p-value measures how unusual data at least as incompatible with a specified null hypothesis would be if that hypothesis and the statistical model were correct. It is not the probability that the null hypothesis is true, nor does it measure the size or clinical importance of a difference. The unadjusted p-value of 0.774 should be read alongside the effect estimate and interval rather than as a stand-alone verdict.

The registry labels the primary analysis as per protocol. In general, a per-protocol analysis includes participants who meet specified criteria for following the study procedures. Those criteria can affect which participants contribute to the estimate and may differ from an analysis that retains all randomized participants in their assigned groups. The registry says that 15 patients were not included, but the reasons, criteria, and any other analysis populations are not reported in the registry record. It is therefore not possible to determine from the record how exclusions may have affected the result.

The endpoint is based on diary responses and is a sum of four symptom ratings. For continuous outcomes, summaries such as means and standard deviations are commonly used when they adequately describe the data and the analysis assumptions are suitable. The registry record does not describe the distribution of individual scores, any diagnostic checks, or whether alternative methods were used. No claim about those features can be made from the posted summary statistics alone.

Random allocation is intended, in general, to make treatment groups comparable with respect to both measured and unmeasured factors on average. It does not guarantee identical groups, particularly in a finite study, and the registry record does not provide baseline characteristics or details of the randomization procedure. The parallel design means the record identifies separate groups receiving the respective study treatments; it does not describe a crossover comparison in which participants receive both options in sequence.

Masking is recorded as triple, but the registry does not identify which roles were masked or how masking was maintained. Allocation concealment, the detailed statistical model, covariate adjustment, the approach to missing observations, and the original analysis plan are not reported in the registry record. The record also does not report interim analyses. These are important elements for judging the analysis, but their absence from the record should not be replaced with assumptions.

In general, over-dispersion refers to variability greater than a statistical model expects. It can make standard errors too small if the model does not allow for the extra variability, leading to intervals that are too narrow and tests that are too optimistic. This concept is relevant when data are analyzed with models that impose a particular variance structure. The posted primary outcome is summarized as a continuous measure with means and standard deviations, and the registry record does not report an over-dispersion assessment or model details. It is not possible to say that over-dispersion was present or that a correction was or was not applied.

The posted comparison is accompanied by an unadjusted p-value and confidence interval, but the registry does not report a multiplicity strategy. When several hypotheses are tested, the chance of at least one nominally unusual result can increase; adjustment methods or a prespecified hierarchy may address that issue. The number of outcome measures listed is four, but no secondary outcome results are posted, and the record does not say whether multiple testing was planned or addressed. Accordingly, the primary comparison can be interpreted on its own terms, while the broader family of analyses remains unclear.

10. Confidence Intervals and Precision

The mean difference is -0.13, and its confidence interval runs from -1.017 to 0.757. The interval includes zero, so the posted data do not isolate a single direction of difference between group means. The estimate is centered near zero, while the range of values compatible with the data extends to either side of zero. The unadjusted p-value is 0.774.

Precision concerns the uncertainty around an estimate, not whether the estimate is important. A narrower confidence interval would indicate a more precise estimate under the method’s assumptions; a wider one would indicate greater uncertainty. The interval allows a range of possible differences, and the registry record does not state a threshold that would distinguish a clinically important difference from a difference of little importance.

The observed group standard deviations are 2.63 in both arms, compared with a mean difference of -0.13. This context indicates that participant scores vary within groups, while the estimated separation between group averages is small in relation to that variation. The standard deviations describe the spread of individual scores; the confidence interval describes uncertainty about the group comparison. These are different quantities and should not be conflated.

The per-protocol analysis and exclusion of 15 patients are also relevant to precision and interpretation. The posted group counts are 67 and 68, but the record does not explain the exclusions or report how missing diary data were handled. The interval therefore pertains to the reported analysis and does not account, in any visible way, for uncertainty about those omissions. The confidence interval method and confidence level are not reported in the registry record, which limits assessment of how the interval was constructed.

11. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The planning figures are participants per arm, not total events. The planning illustration assumes a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. It uses a target effect set to the stated fraction of the observed effect. The registry record does not report the trial’s original sample-size justification or design assumptions.

The 80% power column gives the number of participants per arm that the planning calculation indicates would be needed to have an 80% chance of detecting the chosen effect under those assumptions, if that effect were the true one. The 90% power column gives the corresponding requirement for a 90% chance. These are planning concepts: higher target power generally requires more participants for the same assumed effect.

The planning rows consider 100%, 75%, and 50% of the observed effect. For 100% of the observed effect, the figures are 6,425 participants per arm for 80% power and 8,602 participants per arm for 90% power. For 75%, they are 11,422 and 15,291 participants per arm, respectively. For 50%, they are 25,700 and 34,405 participants per arm, respectively. Smaller effects need more participants to detect, all else being equal.

These are planning illustrations based on the observed effect, not a description of the study’s original design. They are not observed power: they do not tell how likely the completed trial was to detect an effect after its results were known. They also depend on the stated assumptions, including the normal approximation and equal allocation, and should not be treated as a substitute for a protocol-based sample-size justification.

12. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = -0.130; pooled standard deviation σ = 2.630.
2. n = 2 × (1.96 + 0.842)² × 2.630² / -0.130² = 6,424.8, rounded up to 6,425 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
delta <- -0.13                      # observed difference in means
sigma <- 2.63                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(845195)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 6,425 (80% power), 8,602 (90% power)
 75% of observed effect: n per arm = 11,422 (80% power), 15,291 (90% power)
 50% of observed effect: n per arm = 25,700 (80% power), 34,405 (90% power)
power.t.test: 6425.8 
Simulated power at n = 6,425 per arm: 0.797 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

13. Multiplicity, Missing Data and Analysis Populations

The registry record does not report a statistical plan describing how multiple outcomes or comparisons were handled. It lists four outcome measures, but no secondary outcome results are posted. The primary comparison has an unadjusted p-value of 0.774. No multiplicity adjustment, testing hierarchy, or prespecified primary analysis procedure is reported in the registry record. In general, when several hypotheses are tested, unadjusted p-values do not account for the possibility of chance findings across the full set of tests.

Interim analyses and stopping rules are also not reported in the registry record. It is not possible to determine whether planned interim looks were conducted or how any such looks might have been incorporated into the statistical approach. The record does not provide a protocol or analysis plan that could clarify these matters.

The primary endpoint analysis is described as per protocol, with 15 patients not included. The registry does not state why they were excluded, how the per-protocol population was defined, or whether another population was analyzed. The posted arm counts for the primary outcome are 67 and 68. The record does not report whether all diary observations were complete, how missing observations were handled, or whether any imputation or sensitivity analyses were used.

These gaps limit assessment of the impact of exclusions and missing data, as well as the degree to which the posted result reflects the prespecified analysis. They do not establish that the analysis was improper; they mean that these aspects cannot be evaluated from the registry record. The available inference is confined to the reported per-protocol summary and its unadjusted comparison.

14. 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.

The registry reports serious adverse events for 75 participants at risk in each group and lists zero participants affected in each group. No serious adverse event terms are listed. These figures describe the registry’s serious-event reporting for the groups and should be read with their denominators in mind.

The record also lists 75 participants at risk for other adverse events in each group and zero participants affected in each group. The death fields do not contain a reported value; deaths are therefore not reported in the registry record, rather than established as zero by the posted figures.

These summaries do not describe the type, timing, duration, or severity of events beyond the categories recorded. The registry record does not provide further safety-analysis details or explain the difference between the overall enrollment and the number at risk in these adverse-event summaries. The figures should not be interpreted as proof that no event could occur or as a complete characterization of safety outside the recorded groups and reporting period.

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

The posted primary comparison estimates a small difference in average change in reflective total nasal symptom score between the two treatment groups: -0.13 for azelastine relative to olopatadine. The confidence interval, from -1.017 to 0.757, includes zero, and the unadjusted p-value is 0.774. The results therefore do not provide strong evidence of a difference between group means in the reported per-protocol analysis.

This finding is not proof that the treatments are identical or equivalent. A failure to identify a difference is not the same as demonstrating that any difference is smaller than a prespecified acceptable margin. The registry record does not report an equivalence or noninferiority framework, nor does it provide a threshold for clinical importance. The data are also compatible with a range of differences on either side of zero.

The outcome is a group-average composite of four self-reported symptoms over the specified timeframe. It does not show the separate pattern for each symptom, individual participant responses, results at other time points, or subgroup effects. The trial’s primary analysis excluded 15 patients, and the record does not explain why. This limits interpretation beyond the per-protocol participants whose results are posted.

The comparison concerns the two nasal antihistamine treatments in the setting described by the study purpose, which says they were used with Fluticasone Nasal Spray. It does not compare either option with placebo or with no treatment in the posted primary result. The record does not provide enough detail to assess other aspects of the treatment context, missing data, or the full analysis plan.

In short, the registry reports similar group averages on this endpoint, with uncertainty that includes no difference and values in either direction. It does not establish equivalence, clinical importance, individual response, or conclusions beyond the specific outcome, analysis population, and timeframe recorded.

16. Why This Trial Matters Statistically

This trial illustrates why a statistical comparison should be read through its estimate and uncertainty, rather than through a p-value alone. The estimated mean difference is -0.13, and the confidence interval spans zero. Together, these give both a central estimate and a sense of the range of differences compatible with the data under the interval’s method.

The endpoint also highlights a common feature of clinical research: a composite can combine several related symptoms into one continuous measure. This offers a single summary for the primary comparison, but it does not show whether the component symptoms behave alike. Without component results or a stated threshold for clinical importance, the composite’s numerical difference is not enough to determine the importance of a change.

The per-protocol population is another statistical consideration. The registry reports that 15 patients were omitted from the primary analysis, but does not explain why or report a complementary analysis. This makes the analysis population central to interpretation: the posted effect describes the analyzed participants, and the record does not show how the exclusions might affect generalizability or robustness.

Finally, the planning illustration demonstrates the dependence of sample-size requirements on the effect chosen for detection and the desired power. Its figures are not the original study’s design justification and are not observed power. Separating these planning calculations from the completed trial result prevents a common misreading of retrospective power calculations as evidence about what the trial did or did not detect.

17. 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 leaves several trial-specific details unreported. Although masking is recorded as triple, the roles that were masked and the procedures used to maintain masking are not described. Allocation concealment, randomization procedures, baseline characteristics, and the detailed protocol are also not reported in the registry record.

The primary analysis was per protocol, and 15 patients were not included. The reasons for their exclusion, the per-protocol criteria, and any results from other analysis populations are not reported. The posted result therefore cannot be compared with an all-randomized analysis using the information in the registry record. Missing diary observations and their handling are also not described.

The registry lists four outcome measures but posts no secondary outcome results. It does not report a multiplicity approach, interim analyses, or the statistical model and interval-construction method. The record also gives no threshold for clinical importance and no separate results for the four symptoms that make up the composite score.

The study purpose describes both nasal antihistamines as being used with fluticasone, but the arm descriptions provide no further details about the treatment regimen. The registry does not report the original sample-size rationale or planned assumptions. These omissions limit evaluation of protocol choices, analysis robustness, and the breadth of conclusions that can be drawn. They do not establish that the trial lacked these procedures; they indicate that the details are not reported in the registry record.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Comparison of Seasonal Allergic Rhinitis Treatment With 2 Antihistamines Used in Combination With Intranasal Corticosteroid — NCT00845195.
• Registry record last updated 2010-04-27; status last verified 2010-04.
• Results first posted 2010-04-21.
• 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.

21. Record Summary

This completed Phase 4 randomized, parallel-group study compared Olopatadine HCl Nasal Spray, 0.6%, with Azelastine HCl Nasal Spray, 0.1%, for seasonal allergic rhinitis. The study purpose describes both options as used with Fluticasone Nasal Spray. Enrollment was 150, and the record lists triple masking.

The primary outcome was mean change in reflective Total Nasal Symptom Score from baseline at 14 days. The per-protocol analysis excluded 15 patients. The posted group means were 4.28 and 4.15, and the estimated mean difference for azelastine relative to olopatadine was -0.13, with a confidence interval from -1.017 to 0.757 and an unadjusted p-value of 0.774.

No secondary outcome results are posted. The registry record does not report reasons for exclusions, missing-data handling, a multiplicity approach, or the original sample-size rationale. Serious adverse events and other adverse events were reported for 75 participants at risk in each group, with zero affected listed in each category; deaths are not reported in the registry record.