Dymista Allergen Chamber - Onset of Action Study: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Dymista Allergen Chamber - Onset of Action Study (NCT04652245), a randomized phase 4 study. The primary outcome is Change in Patient-assessed Instantaneous Total Nasal Symptom Score (TNSS) From Baseline Compared to Placebo.

2. Clinical Question

The trial assessed symptoms induced by an allergen challenge in an Environmental Exposure Unit. Its primary measure was change in the instantaneous Total Nasal Symptom Score (TNSS), with the posted outcome covering 0 to 4 hours post application. The registry describes the first significant difference to placebo in TNSS as occurring at 5 minutes, which it identifies as the onset of action under its stated definition.

The comparison is between a combined nasal spray and its placebo vehicle in a controlled allergen-exposure setting. It is not a comparison with another active treatment, and the posted record does not describe outcomes beyond the stated trial measures. The available summary gives treatment-period means and standard errors, plus a sponsor-reported ANCOVA superiority analysis. It does not give the adjusted effect estimate or its confidence interval. The recalculated unadjusted comparison and the sponsor’s analysis differ, so the sponsor’s own analysis takes precedence when describing the trial’s reported statistical conclusion.

3. Trial Design

This was a completed phase 4, randomized, double-masked crossover trial sponsored by MEDA Pharma GmbH & Co. KG. The registry records enrollment of 216 participants. The study began on 2020-12-14, and primary completion was recorded on 2021-12-04. Participants received both treatment conditions in different sequences: Dymista followed by placebo, or placebo followed by Dymista. The periods were separated by at least 14 days of wash-out.

The setting was an Environmental Exposure Unit, where seasonal allergic rhinitis symptoms were induced by allergen challenge. The study’s stated purpose was to assess onset of action for the fixed combination of azelastine hydrochloride and fluticasone propionate nasal spray compared with placebo. Double masking and randomization are recorded, but details of the masking procedures and sequence-generation methods are not reported in the registry record.

The primary outcome was change in patient-assessed instantaneous TNSS from baseline compared with placebo. The stated assessment timeframe was 0 to 4 hours post application. The primary result is for the 5-minute post-dose time point, which the registry identifies as the onset of action. The secondary outcome was change in patient-assessed instantaneous Total Ocular Symptom Score (TOSS) from baseline compared with placebo, with a posted result at 10 minutes.

Because each participant could receive both treatments, the crossover structure is important to interpreting the comparison: treatment responses may be paired within participants, and the analysis can account for that structure. The registry lists ANCOVA for the sponsor’s reported primary and secondary comparisons, but its model terms and handling of crossover-period features are not reported in the registry record. The record also does not report the trial’s original sample-size assumptions or a detailed statistical analysis plan.

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.

Treatment Administration Period 1

Wash-Out Period

Reasons for not completing this period:

Treatment Administration Period 2

Analysis population for the primary outcome, as defined in the registry: FAS (Full Analysis Set) population includes all randomized patients, including subjects who received incorrect treatment, did not complete the study or did not comply to the protocol, and who were randomized but did not take any study medication. Overall number of Participants Analyzed means the number of participants for whom the respective TNSS value at 5 min post-dose was available.

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

Population: FAS population includes all randomized patients, including subjects who received incorrect treatment, did not complete the study or did not comply to the protocol, and who were randomized but did not take any study medication

6. Primary Endpoint

The registry lists the primary outcome as Change in Patient-assessed Instantaneous Total Nasal Symptom Score (TNSS) From Baseline Compared to Placebo, measured over 0 to 4 hours post application.

The primary endpoint was change from baseline in patient-assessed instantaneous Total Nasal Symptom Score (TNSS), comparing Dymista with placebo. The score combines four nasal symptoms, each rated on a scale from 0 to 3, where 0 means none and 3 means severe. The total score ranges from 0 to 12. A change from baseline represents movement in this symptom score during the stated assessment timeframe of 0 to 4 hours post application.

This endpoint is used to quantify nasal symptoms after the allergen challenge and to assess how quickly a difference from placebo is first observed. The registry states that onset of action is defined as the first time point after treatment initiation when the product shows a greater change from baseline than placebo and that difference proves durable. In this record, the first significant difference to placebo was reported at 5 minutes and designated the onset time.

Interpreting change scores requires attention to direction: a more negative change indicates a larger reduction from baseline on this scale. The posted least-squares means are treatment-period summaries, with standard errors, rather than participant-level data. The record does not provide the sponsor’s adjusted effect estimate or confidence interval for the primary endpoint, so the magnitude and precision of that adjusted contrast cannot be read from the posted analysis details alone.

7. Results Posted in the Registry

• Treatment A (Dymista), Cross-over Design, Time-point 5 Min Post-dose (Onset of Action): mean -1.37 versus -1.04 on control; difference -0.33 (95% CI -0.69 to 0.03), standardized effect d = -0.18; z-test p = 0.070.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Change in Patient-assessed Instantaneous Total Ocular Symptom Score (TOSS) From Baseline Compared to Placebo

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard errors.
• Result:
  • Treatment A (Dymista), Cross-over Design, Time-point 10 Min Post-dose (Onset of Action): mean -1.21 versus -0.87 on control; difference -0.34 (95% CI -0.63 to -0.05), standardized effect d = -0.23; z-test p = 0.020.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Treatment A (Dymista), Cross-over Design, Time-point 10 Min Post-dose (Onset of Action) than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The registry posts one secondary outcome: change in patient-assessed instantaneous Total Ocular Symptom Score (TOSS) from baseline compared with placebo. Its overall direction is consistent with the primary outcome in that the posted treatment summaries show a greater decrease from baseline with Dymista than with placebo. The registry also reports a sponsor ANCOVA superiority analysis for this secondary endpoint. The endpoint-specific figures and comparisons are displayed in the tables and are not repeated.

The ocular result adds context to the nasal-symptom finding because it concerns another symptom domain assessed in the same study setting. It does not independently establish the primary result, and it should not be treated as a substitute for the nasal endpoint. The measures capture different symptom scores, and the record does not report a combined endpoint or a shared model that would support treating them as one outcome.

Unadjusted secondary results generally carry less weight than the primary analysis because they may be among multiple comparisons, and their statistical interpretation depends on whether multiplicity was planned and addressed. The record does not report a multiplicity adjustment or a testing hierarchy. Without that information, secondary p-values are best read as nominal evidence rather than as definitive confirmatory tests. The number of posted secondary outcomes is limited in this record, but the absence of a reported adjustment plan means the possibility of multiple testing still matters.

The secondary result is supportive in direction, but its evidential role depends on the prespecified analysis plan and the handling of multiple outcomes. Those details are not reported in the registry record. The posted secondary analysis should therefore be interpreted alongside, not in place of, the primary analysis and its discrepancy between the sponsor result and the summary-based recalculation.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Change in Patient-assessed Instantaneous Total Ocular Symptom Score (TOSS) From Baseline Compared to Placebo

9. Statistical Interpretation

10. Statistical Methods Explained

The primary result is a continuous outcome: a symptom score that can take values across a defined numerical scale. The registry reports least-squares means and standard errors for the treatment conditions. A least-squares mean is a model-based average, typically adjusted for the terms included in the analysis model. The record does not list those terms for the sponsor’s ANCOVA, so it is not possible to tell from the registry entry which covariates or crossover factors were included.

What does the comparison estimate?

The posted summary compares change from baseline under Dymista with change from baseline under placebo. The displayed treatment means are -1.37 and -1.04 at the 5-minute point. The simple unadjusted recalculation summarizes their contrast as a mean difference of -0.33. Since lower changes are more negative, the estimate points toward a larger reduction from baseline with Dymista in the posted summaries. That direction is descriptive; the inferential conclusion should take account of the crossover design and the sponsor’s reported analysis.

A confidence interval describes a range of values compatible with the data and the assumptions of the analysis. It communicates precision as well as direction. In the recalculated comparison, the interval includes no difference, which is consistent with the unadjusted p-value of 0.07. This does not erase the sponsor-reported ANCOVA result, which has p = 0.028. The discrepancy signals that the two analyses do not produce the same statistical conclusion. The registry does not report enough model detail or an adjusted interval to reconcile them independently.

Why does the crossover structure matter?

In a crossover study, treatment comparisons can use the fact that an individual receives both conditions. Responses from the same participant may be correlated. That correlation can affect the standard error of a within-participant contrast, so a calculation based only on group summaries may not reproduce a crossover-model result. The posted recalculation is explicitly a simple, unadjusted re-calculation from summary statistics. It uses an approximate pooled standard deviation, as indicated in the posted calculation details, and it cannot incorporate participant-level pairing or model adjustments that are absent from the summaries.

The sponsor’s reported method is ANCOVA. In general, analysis of covariance models an outcome while accounting for selected explanatory variables. For a change-from-baseline outcome, a model may also account for baseline or design features, but the exact model used is not reported in the registry record. The label ANCOVA alone does not reveal which terms were included, how the crossover sequence was represented, or how repeated measures were handled.

What do the p-values say?

A p-value measures how surprising data at least as incompatible with a specified null hypothesis would be, under the model assumptions, if the null hypothesis were true. It is not the probability that the treatment has no effect, and it does not quantify the size or clinical importance of a difference. The unadjusted recalculation reports p = 0.07. The sponsor’s ANCOVA superiority analysis reports p = 0.028. Because the record flags a discrepancy, the sponsor’s analysis takes precedence for the trial’s reported result. The two p-values should not be averaged or treated as interchangeable: they come from different analyses and assumptions.

ANCOVA is a model-based method, while the recalculation is based on posted treatment summaries. Different methods can produce different standard errors and p-values, particularly when they use different information about baseline values, participant pairing, or design structure. The registry record does not provide the model specification or adjusted effect estimate, preventing a full independent reconstruction of the sponsor’s result.

What does standard error indicate?

A standard error describes the sampling uncertainty of an estimated mean under the analysis assumptions. It is not the same as the spread of individual participant scores. The posted standard errors for the two treatment summaries are 0.13 and 0.128. They help describe uncertainty around the reported least-squares means, but they do not, by themselves, provide the standard error of a paired treatment contrast. In a crossover design, the covariance between each participant’s treatment responses can be relevant to that contrast.

The score itself combines four symptom ratings, each on a scale from 0 to 3, and has a total range from 0 to 12. The registry reports a change score rather than the full distribution of individual responses. The summary therefore does not show how many participants improved, stayed unchanged, or had an increase in symptoms. Nor does it provide distributional plots or other diagnostics in this discussion record.

What can be concluded from the reported method?

The registry identifies the primary sponsor analysis as an ANCOVA superiority comparison and reports its p-value. That supports describing the sponsor’s reported statistical finding without inventing an adjusted effect size. The posted means and recalculated contrast offer a separate, unadjusted view of the summarized data, but they do not supersede the sponsor model. The exact onset assessment also depends on the record’s definition, including durability; detailed evidence across the assessment timeframe is not reported in the registry record.

More generally, statistical significance is a statement about evidence relative to a model and null hypothesis. It does not establish a particular magnitude of benefit, clinical importance, or generalizability. Those interpretations require information beyond a p-value, including an effect estimate, precision, study context, and the analysis plan. Here, the registry does not report the adjusted primary effect estimate and confidence interval, the trial’s original sample-size justification, or detailed missing-data procedures.

11. Confidence Intervals and Precision

Precision concerns how much uncertainty surrounds an estimated treatment contrast. The posted summaries give standard errors for the least-squares means: 0.13 for Dymista and 0.128 for placebo. Those values describe uncertainty around the separate model-based means, not necessarily the uncertainty around their within-participant difference in a crossover study.

The calculated comparison table displays a recalculated confidence interval for the unadjusted mean difference. That interval includes no difference, which matches the recalculated p-value of 0.07. It is based on posted summary statistics and an approximate pooled standard deviation; it does not incorporate participant-level paired responses or reproduce the sponsor’s ANCOVA. The recalculated interval should therefore be treated as a separate, approximate summary rather than as the sponsor’s interval.

The sponsor’s adjusted confidence interval and effect estimate are not reported in the registry record. Consequently, readers cannot use the posted record to judge the precision of the sponsor’s adjusted treatment effect directly. The sponsor’s p-value indicates the result of its reported hypothesis test, but a p-value alone does not give the range of effect sizes compatible with the data.

In general, a wider confidence interval signals less precision, while a narrower one signals greater precision, conditional on the analysis assumptions. Precision is not the same as clinical importance: an estimate can be precise without being important, or imprecise even when its point estimate is notable. Here, the reported score summaries provide context for the size of change, but the adjusted interval needed to assess uncertainty around the sponsor’s primary contrast is unavailable.

12. 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 sample-size table and curve are planning illustrations based on the observed effect, not the trial’s original design calculation. The listed assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each planning row uses a stated fraction of the observed effect as the effect to detect. The calculations are not the trial’s own sample-size justification; the original design assumptions are not reported in the registry record.

For the continuous outcomes, the table gives participants per arm, not total events. The 80% power column describes the number of participants per arm that the planning calculation would require to have an 80% chance of detecting the assumed effect under the stated assumptions. The 90% power column gives the corresponding number per arm for a 90% chance. These are planning probabilities under the calculation’s model, not guarantees about the result of a future study.

The rows consider planning for 100%, 75%, and 50% of the observed effect. The table shows that smaller effects require more participants per arm to meet the stated power targets. For example, the primary-outcome table lists 513 participants per arm for 80% power when planning for 100% of the observed effect, and 2,049 participants per arm when planning for 50% of the observed effect. For 90% power, the corresponding listed figures are 686 and 2,742 participants per arm. The intermediate row is planning for 75% of the observed effect.

These figures are not observed power for the completed trial. They are hypothetical sample-size requirements generated from the observed effect and the stated planning assumptions. The crossover design and the sponsor’s model may involve information not represented by the equal-allocation, normal-approximation illustration, so the table should not be read as a reconstruction of the original design process.

13. 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 = -0.330; pooled standard deviation σ = 1.885.
2. n = 2 × (1.96 + 0.842)² × 1.885² / -0.330² = 512.1, rounded up to 513 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 <- -0.33                      # observed difference in means
sigma <- 1.88474492579079                     # 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(4652245)
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 = 513 (80% power), 686 (90% power)
 75% of observed effect: n per arm = 911 (80% power), 1,219 (90% power)
 50% of observed effect: n per arm = 2,049 (80% power), 2,742 (90% power)
power.t.test: 513 
Simulated power at n = 513 per arm: 0.806 (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.

14. Analyses Reported by the Sponsor

The sponsor’s primary analysis is reported as an ANCOVA superiority comparison with p = 0.028. The registry also contains a simple unadjusted recalculation from posted summary statistics, with an estimated mean difference of -0.33 and p = 0.07. The recalculated confidence interval includes no difference. These analyses do not agree on the statistical conclusion.

Because the record flags this discrepancy, the sponsor’s own analysis takes precedence when describing the trial’s reported inferential result. The recalculation is useful as a transparent comparison based on the posted means and standard errors, but it is not a substitute for the sponsor’s crossover analysis. In particular, the recalculation cannot make use of participant-level pairing or adjustments that may be included in the sponsor’s model.

The registry identifies ANCOVA as the method but does not report the adjusted effect estimate, its confidence interval, or the model terms. The record therefore supports reporting the sponsor’s p-value and method, while leaving important details of the adjusted magnitude and precision unavailable. Readers should keep the sponsor analysis and the unadjusted recalculation distinct rather than combining their results.

15. Multiplicity, Missing Data and Analysis Populations

The record describes a primary nasal symptom endpoint and one posted secondary ocular symptom endpoint. It does not report a multiplicity-control strategy, a testing hierarchy, or whether secondary analyses were intended to be confirmatory. Without those details, readers cannot determine whether the reported p-values were adjusted for the number of outcomes or comparisons. Unadjusted secondary results should therefore be interpreted cautiously, since testing multiple hypotheses can increase the chance of at least one apparently notable result.

The full analysis set is described as including all randomized participants, including people who received incorrect treatment, did not complete the study, did not comply with the protocol, or were randomized but did not take study medication. That definition describes who could be included in the analysis population. It does not explain how missing outcome measurements were handled, how incomplete crossover periods were treated, or whether any imputation was used. Those procedures are not reported in the registry record.

The treatment summaries list different participant counts for Dymista and placebo at the primary time point, and the secondary summaries also list treatment-specific counts. The record does not explain why these analysis counts differ or whether the same participants contributed measurements under both conditions. It also does not describe how participants with unavailable measurements were handled in the sponsor’s ANCOVA.

In a crossover study, period, sequence, and possible carryover effects can be relevant to analysis. The record reports a wash-out period of at least 14 days but does not provide the sponsor model terms or any assessment of period or carryover effects. This does not establish that such effects occurred; it means the registry entry does not give enough detail to assess how they were addressed.

16. Safety Results

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

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

Most frequent non-serious adverse event terms

The posted safety figures record zero serious adverse events and zero deaths in each listed group: Dymista, placebo, and the group not dedicated to a treatment group. The listed numbers at risk for serious adverse events were 212 for Dymista and 216 for placebo, with 216 in the group not dedicated to a treatment group. No serious adverse event terms are listed in the record.

These figures are a description of what the registry posts for the trial’s safety groups. The record also lists other adverse events separately, but those are not serious adverse events and should not be conflated with the serious-event figures. The trial’s crossover structure and the separate group not dedicated to a treatment group also mean the safety rows should be read according to their listed categories rather than combined into a single treatment comparison.

Zero recorded serious adverse events in these groups does not establish that an event is impossible or that the study can characterize uncommon harms. The registry summary does not provide detailed event narratives, exposure-adjusted analyses, or a fuller safety analysis. These figures describe the posted record only and do not support conclusions beyond it.

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

The result addresses a narrow statistical question: how patient-assessed nasal symptom scores changed after Dymista and placebo in an allergen challenge setting, and when the registry identified a first significant difference. The registry reports the first significant difference to placebo in TNSS at 5 minutes and labels that time point as onset of action. The sponsor’s ANCOVA superiority analysis has p = 0.028. The posted summary-based recalculation differs, so the sponsor’s analysis takes precedence for the trial’s reported conclusion.

This does not provide the adjusted size of the sponsor’s treatment effect or its confidence interval, because those are not reported in the registry record. The posted mean changes and their standard errors offer descriptive context, while the recalculated contrast is unadjusted and approximate. The record also does not report a threshold for a clinically meaningful change in TNSS. Statistical significance therefore should not be equated with a particular level of clinical importance.

The study was conducted in an Environmental Exposure Unit using allergen-induced seasonal allergic rhinitis symptoms. Its results should be understood in that trial context. The record does not establish how the findings translate to other exposure conditions, settings, patient groups, or patterns of use. Such broader claims are outside what the posted data show.

The reported onset definition includes a difference from placebo that proves durable. The registry names 5 minutes as the first significant time point, but the detailed results across the full 0 to 4 hours post application and the analysis used to establish durability are not reported in the registry record. The statement can be reported as the trial’s registry conclusion without implying that every detail behind it is available for independent review.

Finally, the primary analysis discrepancy matters: a simple recalculation from summary statistics does not agree with the sponsor’s ANCOVA result. The sponsor analysis is the appropriate reference for the trial’s reported inferential conclusion, while the recalculation illustrates how results can depend on analysis method and available information. Neither a p-value nor a symptom-score change alone answers questions beyond the measured outcomes and study setting.

18. Why This Trial Matters Statistically

This trial illustrates why a study’s design and analysis method matter when interpreting a treatment comparison. In a crossover study, participants receive both conditions, so the relationship between a person’s responses under the two treatments can inform the comparison. A summary-based recalculation that lacks participant-level pairing may not reproduce the result from a model that uses the crossover data.

The primary comparison makes that issue visible: the unadjusted recalculation and sponsor-reported ANCOVA produce different statistical conclusions. The record flags the discrepancy, and the sponsor’s own analysis takes precedence. At the same time, the adjusted estimate and confidence interval are unavailable, limiting assessment of the sponsor result’s magnitude and precision. Reporting a p-value without the corresponding adjusted effect estimate is not enough to describe the full statistical result.

The study also makes clear that onset is an analysis question, not merely a label attached to one time point. The registry defines onset using the first significant difference that proves durable and identifies 5 minutes as the first such point. Without detailed time-point results and model specifications, readers can report this conclusion but cannot independently evaluate every element of its definition from the registry summary.

Finally, planning calculations based on observed effects should not be confused with the trial’s original design rationale or with observed power. The planning table shows how required participants per arm rise when planning for smaller effects, under its listed assumptions. The original sample-size assumptions are not reported. Keeping those distinct statistical quantities separate helps prevent overinterpretation of a completed study’s result.

19. 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 does not provide the sponsor’s adjusted primary effect estimate or confidence interval, and its ANCOVA model terms are not described. The unadjusted recalculation uses posted summary statistics and an approximate pooled standard deviation; it cannot reproduce participant-level pairing or any adjustments in the sponsor’s crossover analysis. The discrepancy between the recalculation and sponsor analysis therefore limits independent assessment of the reported result.

Although the record defines onset in terms of a first difference that proves durable, detailed outcome results across the 0 to 4 hours post application are not included in the posted summary. The model and criteria used to determine durability are also not reported in the registry record. Thus, the onset statement is available as the registry’s reported conclusion, but the supporting time-course analysis cannot be fully inspected.

The record does not report the original sample-size justification, a detailed statistical analysis plan, a multiplicity strategy, missing-data procedures, or the handling of incomplete treatment periods. It also does not specify whether period, sequence, or carryover features were included in the sponsor model. The reported treatment-specific analysis counts differ, but the reason is not stated.

The trial used an allergen challenge in an Environmental Exposure Unit, so the reported setting is specific. The record does not provide a threshold for clinically meaningful TNSS change or enough information to assess how the results apply beyond the measured setting. These limitations concern what can be assessed from the registry entry; they do not establish that the omitted analyses were not performed.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Dymista Allergen Chamber - Onset of Action Study — NCT04652245.
• Registry record last updated 2023-03-23; status last verified 2023-02.
• Results first posted 2023-03-23.
• 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.

23. Record Summary

This completed phase 4 randomized, double-masked crossover trial enrolled 216 participants with seasonal allergic rhinitis. It compared Dymista, a fixed combination of azelastine hydrochloride and fluticasone propionate nasal spray, with placebo in an Environmental Exposure Unit using allergen-induced symptoms. Treatment periods were separated by at least 14 days of wash-out.

The primary endpoint was change from baseline in patient-assessed instantaneous TNSS, with a stated timeframe of 0 to 4 hours post application. The registry identifies 5 minutes as the first significant difference to placebo and reports a sponsor ANCOVA superiority analysis with p = 0.028. A summary-based unadjusted recalculation differs; the sponsor analysis takes precedence.

One secondary ocular symptom outcome is posted. The registry does not report the adjusted primary effect estimate or confidence interval, detailed ANCOVA model terms, multiplicity procedures, missing-data methods, or the original sample-size assumptions. Safety records list zero serious adverse events and zero deaths in each listed group.