Can a Nasal Decongestant Test Predict Treatment Outcomes in Seasonal Allergic Rhinitis?: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Can a Nasal Decongestant Test Predict Treatment Outcomes in Seasonal Allergic Rhinitis? (NCT00618332), a randomized na study. The primary outcome is Global Assessment.

2. Clinical Question

The registry rationale proposes that people with purely seasonal allergic rhinitis may decongest better than people whose symptoms have another contributing cause, and that the latter group may respond less well to an intranasal steroid. It also refers to a 60% response rate in prior studies as context for that hypothesis. This rationale is not itself evidence that the test predicts treatment outcome. The posted primary comparison is between treatment groups, not a reported comparison of treatment effects across decongestant-response groups. The record does not report the test results, a predictive interaction estimate, or a conclusion about whether the test distinguishes treatment outcomes.

3. Trial Design

This was a randomized, double-masked, parallel-group trial sponsored by the University of Chicago. The registry record lists 40 participants as enrolled and identifies seasonal allergic rhinitis as the condition. Participants were assigned to mometasone furoate nasal spray or placebo, with 2 weeks of treatment in each arm. The trial is listed as completed. The registry record does not report further details of the randomization procedure, concealment, or how masking was maintained.

The primary outcome was a global assessment at week 2. The posted primary results include 19 participants in the mometasone furoate group and 18 in the placebo group; the record notes one missing primary value in the mometasone furoate group and two in the placebo group. The safety figures use 20 participants at risk in each group. These are different reported counts for different purposes and should not be treated as interchangeable. The registry record does not explain the analysis-population definitions or the handling of missing primary values.

The record lists eight secondary outcomes concerning changes in the overall Rhinoconjunctivitis Quality of Life Questionnaire (RQLQ) score and its activity, sleep, non-nasal/eye, practical, nasal, emotional, and eye domains. The numeric summaries in the posted results include the overall, activity, and sleep outcomes. The registry record does not report the original sample-size justification, the planned statistical analysis, or whether any interim analyses were planned or conducted. Those design details therefore cannot be inferred from the enrollment or the observed results.

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: There were one patient in the Mometasone Furoate group and two patients in the Placebo group with missing values.

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 Global Assessment, measured over at week 2.

The primary endpoint is the mean global assessment score at week 2, expressed in units on a scale. The scale runs from -3 to 3: -3 means significantly worse, -2 moderately worse, -1 mildly worse, 0 no change, 1 mildly improved, 2 moderately improved, and 3 significantly improved. A mean summarizes participants’ scores into a group-level measure of reported change. It can describe the average direction and degree of assessment, but it does not show how many individuals had each response or how scores were distributed within each group.

A global assessment is used to capture an overall judgment of change rather than a single symptom or questionnaire domain. That broad summary can be clinically interpretable, while also combining different experiences into one score. The registry record does not report a threshold defining a responder, nor does it report a separate analysis of the proportion of participants who improved by a specified amount.

The reported group means were 1.7 for mometasone furoate and 1.4 for placebo. The registry’s primary comparison is the mean difference between those groups. This endpoint addresses the treatment-group contrast at week 2; by itself, it does not answer whether nasal decongestant test response predicts which participants benefit more from treatment. That predictive question would require an analysis relating test response to the difference between treatment outcomes.

7. Results Posted in the Registry

• Mometasone Furoate: mean 1.70 versus 1.40 on control; difference 0.30 (95% CI -0.44 to 1.04), standardized effect d = 0.26; z-test p = 0.429.

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.

Changes in RQLQ: Overall

• 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 deviations.
• Result:
  • Mometasone Furoate: mean -1.35 versus -1.25 on control; difference -0.10 (95% CI -0.78 to 0.58), standardized effect d = -0.09; z-test p = 0.772.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Mometasone Furoate and the control. The interval gives the range of effects that remain compatible with the data.

Changes in RQLQ: Activity

• 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 deviations.
• Result:
  • Mometasone Furoate: mean -1.73 versus -1.55 on control; difference -0.18 (95% CI -1.24 to 0.88), standardized effect d = -0.11; z-test p = 0.739.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Mometasone Furoate and the control. The interval gives the range of effects that remain compatible with the data.

Changes in RQLQ: Sleep

• 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 deviations.
• Result:
  • Mometasone Furoate: mean -1.42 versus -0.85 on control; difference -0.57 (95% CI -1.26 to 0.12), standardized effect d = -0.51; z-test p = 0.107.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Mometasone Furoate and the control. The interval gives the range of effects that remain compatible with the data.

The registry identifies eight secondary outcomes across RQLQ overall score and activity, sleep, non-nasal/eye, practical, nasal, emotional, and eye domains. The posted numeric summaries include the overall, activity, and sleep domains. Across these outcomes, the available mean differences do not produce a consistent pattern of clear between-group separation: their recalculated confidence intervals include zero, and their reported two-sided p-values do not provide strong evidence of a difference. These findings are best read as uncertain secondary comparisons rather than confirmation of a broad effect across quality-of-life domains.

The secondary results do not change the interpretation of the primary global assessment. They measure related but distinct aspects of quality of life, whereas the primary endpoint is a global assessment at week 2. Their role is to add context about other reported outcomes, not to substitute for the primary comparison or answer the decongestant-test prediction question. No secondary analysis by test response is reported in the registry record.

Multiple secondary outcomes create a multiplicity concern: when many outcomes are tested, the chance of at least one apparently unusual result can increase. The registry record does not report a multiplicity adjustment or a hierarchy for interpreting these outcomes. Consequently, unadjusted secondary results carry less weight than a single prespecified primary comparison, particularly when interpreting isolated findings. The registry also does not report whether the listed secondary outcomes were all planned before the data were examined. These limitations mean the secondary findings should be treated cautiously and should not be used to make a definitive claim based on one domain.

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

• Changes in RQLQ: Overall
• Changes in RQLQ: Activity
• Changes in RQLQ: Sleep
• Changes in RQLQ: Non-Nasal/Eye
• Changes in RQLQ: Practical
• Changes in RQLQ: Nasal
• Changes in RQLQ: Emotional
• Changes in RQLQ: Eye

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous: each participant’s global assessment is represented by a numerical score, and the group results are reported as means with standard deviations. A mean describes the center of the scores; a standard deviation describes their spread around that center. The standard deviation is not the uncertainty around the mean difference. That uncertainty is represented by the confidence interval for the comparison.

What does the mean difference represent?

The posted comparison is mometasone furoate minus placebo. Its estimate of 0.3 means the average score was higher in the mometasone furoate group by 0.3 scale units in this sample. The sign of an estimate indicates its direction according to the comparison order; it does not, on its own, establish that the difference is reliable or important. The registry record does not report a threshold for a clinically important difference on this scale, so the observed estimate cannot be classified against such a threshold.

How should the t-test and p-value be read?

The registry reports a two-sided t-test for the primary comparison. In general, a two-sided test considers departures in either direction from a model of no group difference. Its p-value summarizes how compatible the observed data are with that model under the test assumptions; it does not measure the size of the effect. The registry reports p = 0.372. An unadjusted recalculation from the posted summary statistics gives p = 0.429. The reported result is the sponsor’s analysis; the recalculation is a separate, simple comparison based on the posted group summaries. The registry record does not report enough detail to determine the reason for the difference between these p-values.

Why does variability matter?

Participants’ scores vary within each group. Greater variability makes a group mean less precise when the number of observations is limited, because the average is less informative about the range of plausible group-level values. The confidence interval reflects both variability and the amount of information available for the comparison. In general, a wide interval signals less precision than a narrow interval. The standard deviations in the posted primary results describe observed spread; they are not a measure of clinical importance.

What does randomization contribute?

Random assignment is intended to make treatment groups comparable, on average, with respect to factors that could affect outcomes. It supports interpreting a between-group contrast as a treatment comparison, subject to the conduct and analysis of the trial. It does not guarantee that the groups are identical in a small trial. The registry record says the trial was randomized and double-masked but does not describe the allocation procedure, baseline balance, or analysis adjustments. No adjustment for baseline or other covariates is reported in the posted primary analysis.

Why is the predictive question different?

A treatment comparison averaged across participants asks whether the groups differ overall. A predictive question asks whether treatment differences vary according to a participant characteristic—in this case, response to a nasal decongestant test. A statistical analysis would need to compare treatment effects across test-response levels or estimate a treatment-by-test interaction. Reporting an association between test response and outcome in one treatment group alone would not establish prediction of treatment benefit. The registry record does not report an interaction analysis, test-performance measures, or outcome summaries by test response.

Why can extra variation affect an analysis?

As a general statistical point, over-dispersion occurs when observed variability exceeds what a chosen model assumes. If a model understates variability, its uncertainty estimates may be too small and its tests may appear more decisive than warranted. The registry record reports a continuous endpoint analyzed with a t-test and does not report an over-dispersion assessment. The concept is relevant as a general consideration, but there is no basis in the record for saying over-dispersion occurred in this trial.

Finally, statistical results depend on the analysis population, missing-data handling, and prespecified methods. These details are not reported in the registry record. The posted means, standard deviations, confidence interval, and p-values should therefore be read as the results that are available, without assuming unreported choices about exclusions, imputation, or covariate adjustment.

11. Confidence Intervals and Precision

The recalculated 95% confidence interval for the primary mean difference includes zero. In plain terms, the summary data are compatible with no average difference, as well as with a range of positive or negative differences. The interval is therefore not precise enough to isolate one direction of effect. Its interpretation depends on the comparison and assumptions used for the recalculation; it is not a statement that there is a 95% probability that the true value lies in the particular interval.

Precision is limited by the number of primary outcome values and the observed spread of scores. The posted primary groups contain 19 and 18 participants, with standard deviations of 1.1 and 1.2. The registry record notes missing primary values in each group, but does not report how they were handled. The displayed estimate should be considered alongside that missingness and the interval, rather than read as a stand-alone result.

The confidence interval is distinct from the standard deviations reported for each group. Standard deviations describe variation among participant scores; the interval describes uncertainty around the estimated between-group difference. A confidence interval can include zero without showing that the groups are equivalent. To support equivalence, the study would need a stated equivalence margin and an analysis designed to assess it; neither is reported in the registry record.

The reported p-value and recalculated interval answer related but not identical presentation needs: the p-value summarizes compatibility with a no-difference model, while the interval communicates a range of effect sizes compatible with the data under its assumptions. Neither establishes whether a difference matters clinically. The registry record does not report a threshold for meaningful change on the global assessment scale.

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 planning figures are participants per arm, not total events. They apply to a continuous outcome and use the observed effect as a starting point, with illustrations for detecting 100%, 75%, or 50% of that observed effect. The listed assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The trial’s own original sample-size assumptions and justification are not reported in the registry record.

The 80% power column describes the number of participants per arm that a planning calculation estimates would give an 80% chance of detecting the stated effect if that effect were the true one and the assumptions held. The 90% power column uses the same idea with a higher target chance of detecting the stated effect. These are design illustrations, not guarantees: actual power depends on the true effect, variability, analysis, and other features of the study.

Smaller effects are harder to distinguish from random variation, so the planning figures increase as the effect to detect becomes smaller. The figures are based on the observed effect in this trial, which is itself uncertain; treating it as a fixed planning input does not remove that uncertainty. These figures are not observed power. They do not tell whether the completed trial had a particular probability of finding its result, and they are not a retrospective measure of evidence strength. The registry record does not report that these calculations were used to design the trial.

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 = 0.300; pooled standard deviation σ = 1.150.
2. n = 2 × (1.96 + 0.842)² × 1.150² / 0.300² = 230.5, rounded up to 231 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 <- 0.3                      # observed difference in means
sigma <- 1.14965833433864                     # 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(618332)
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 = 231 (80% power), 309 (90% power)
 75% of observed effect: n per arm = 410 (80% power), 549 (90% power)
 50% of observed effect: n per arm = 923 (80% power), 1,235 (90% power)
power.t.test: 231.5 
Simulated power at n = 231 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.

14. Analyses Reported by the Sponsor

The registry reports the sponsor’s primary two-sided t-test as p = 0.372. The simple unadjusted recalculation from the posted group means and standard deviations gives a mean difference of 0.3 and p = 0.429. The recalculated confidence interval includes zero. These are not identical p-values, but the registry record marks no discrepancy requiring the recalculation to take precedence. The sponsor’s reported analysis remains the registry’s own inferential result.

The registry does not report the sponsor’s estimate of the mean difference, confidence interval, or additional test details in the analysis entry. It also does not explain why its p-value differs from the recalculation. A recalculation from summary statistics may not reproduce an analysis that used details not captured by the posted summaries, but the record does not establish that such details were used. No specific explanation should be inferred.

Both p-values are consistent with uncertainty about the group contrast rather than strong evidence of a difference. The recalculation is useful as a transparent check based on the posted means and standard deviations; it is not a replacement for the sponsor’s analysis. Neither result addresses the separate question of whether test response predicts variation in treatment effect.

15. Multiplicity, Missing Data and Analysis Populations

The registry record lists one primary endpoint and eight secondary outcomes. It reports two-sided tests for the primary comparison and the secondary results available in the posted record, but does not report a family-wise error strategy, multiplicity adjustment, or a sequence for testing outcomes. Without such information, the extent to which the analyses were intended to support confirmatory claims is not reported in the registry record. Unadjusted secondary p-values should therefore be interpreted cautiously, since examining multiple outcomes can increase the chance of an apparently notable result.

Missing primary endpoint values are noted for one participant in the mometasone furoate group and two in the placebo group. The registry record does not report the reasons for missingness, whether missingness was related to participants’ outcomes, or whether any imputation or sensitivity analysis was used. It also does not clearly state the analysis population or provide a detailed account of exclusions. The primary means and comparison should be understood in light of these unreported details.

The safety record lists 20 participants at risk in each group, whereas the primary endpoint summaries include 19 and 18 participants. These counts refer to the posted safety and primary outcome information respectively; the registry record does not explain all differences between the analysis counts. No assumption should be made that all randomized participants contributed to every outcome or that a particular missing-data method was applied.

The registry record also does not report the original statistical analysis plan, the sample-size justification, or whether interim analyses were planned or performed. These omissions matter because prespecified methods help distinguish planned tests from analyses chosen after results are known. The available record does not establish that any post hoc choices occurred; it simply does not report these design and analysis details.

16. 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 0% reporting threshold.

The posted safety figures list 20 participants at risk in each group. No serious adverse events are reported in either group, and no other adverse events are reported in either group in the posted figures. These counts describe what the registry records for the specified safety categories and denominators; they do not establish that no events of any kind occurred outside the categories or reporting period captured by the record.

The death fields are not populated with a numeric count. Deaths are therefore not reported in the registry record, rather than confirmed as zero. The record does not provide detailed event descriptions, severity classifications beyond the serious-adverse-event category, or additional information on how events were collected and reviewed. With the available safety data, comparisons between groups are limited, and absence of reported events should not be read as proof of absence of risk.

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

The posted primary results describe a mean global assessment score of 1.7 with mometasone furoate and 1.4 with placebo at week 2. The unadjusted recalculation estimates a mean difference of 0.3, but its confidence interval includes zero; the registry-reported test gives p = 0.372. The data therefore leave uncertainty about the size and direction of the average group difference. They do not establish equivalence, and the registry does not report a threshold for a clinically important difference.

The result also does not show whether response to a nasal decongestant test predicts treatment outcome. The record presents the predictive idea as a hypothesis, but does not report results stratified by test response or a formal test of whether the treatment contrast differs according to that response. A comparison of treatment groups overall cannot answer that distinct question.

The secondary quality-of-life results add limited context. They involve multiple outcomes, and the registry record does not report a multiplicity plan. They should not be treated as independent confirmation of the primary result or as decisive evidence about particular domains. Similarly, the safety figures report no serious or other adverse events in the posted counts, while deaths are not reported; these entries should be interpreted within the limited detail available.

More broadly, registry results are a record of reported design features and outcome summaries, not a complete account of every analytic decision or participant experience. Details such as the original analysis plan, missing-data handling, and the basis for sample-size planning are not reported in the registry record. The appropriate reading is therefore bounded: the posted comparisons show an uncertain average treatment contrast in this small trial, and they do not resolve the proposed use of decongestant response as a predictor.

18. Why This Trial Matters Statistically

This trial is statistically notable because its title and rationale connect two questions that require different analyses. One is whether outcomes differ between randomized treatment groups overall. The other is whether a baseline test identifies participants for whom the treatment contrast differs. The posted primary endpoint addresses the first question. The predictive question requires evidence about variation in the treatment effect across test-response groups, and such evidence is not reported in the registry record.

The example also illustrates why an estimate should be read together with its uncertainty. A mean difference of 0.3 points in one direction is not a complete account of the evidence; the confidence interval includes zero, and the reported and recalculated p-values do not provide clear evidence of a group difference. Neither a point estimate nor a p-value alone establishes clinical importance or equivalence.

Finally, the record shows the limits of interpretation when analysis details are sparse. Missing primary values are noted, but the method for handling them is not. Multiple secondary outcomes are identified, but no multiplicity approach is reported. The original sample-size justification and the predictive analysis are also not reported. These are not merely administrative details: they affect what can be concluded from estimates and how much weight different results should carry. Statistical interpretation must distinguish the results actually reported from the hypotheses that motivated the trial.

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 main trial-specific limitation is that the registry record does not report the result needed to answer the title’s predictive question. There are no posted outcomes by nasal decongestant response, no treatment-by-test interaction estimate, and no reported measure of predictive performance. The primary overall treatment comparison cannot substitute for those analyses.

The primary endpoint summaries include fewer observations than the safety denominators, and the record notes missing values in both treatment groups. Reasons for missingness and the analysis used to address it are not reported in the registry record. The modest number of primary endpoint observations also leaves substantial uncertainty around the group contrast. The record does not report baseline characteristics or enough information to assess balance between the randomized groups.

The trial reports multiple secondary outcomes, but no multiplicity strategy or outcome hierarchy is reported. The available secondary results are therefore difficult to interpret as confirmatory evidence. In addition, the registry record does not report a clinically important difference for the global assessment or RQLQ outcomes, so statistical estimates cannot be compared with a stated importance threshold.

Important protocol and analysis details are also absent from the registry record, including the original sample-size justification, analysis-population definitions, missing-data methods, and whether interim analyses were planned or performed. These absences limit reconstruction of the intended analysis and the reasons behind the posted results. They do not demonstrate that the trial was conducted improperly; they restrict what can be concluded from the record.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Can a Nasal Decongestant Test Predict Treatment Outcomes in Seasonal Allergic Rhinitis? — NCT00618332.
• Registry record last updated 2014-02-14; status last verified 2014-01.
• Results first posted 2014-01-10.
• 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

The registry record describes a completed, randomized, double-masked, parallel-group trial sponsored by the University of Chicago, with 40 participants enrolled. Mometasone furoate nasal spray and placebo were each given for 2 weeks. The primary endpoint was mean global assessment at week 2. The posted means were 1.7 and 1.4 respectively; the sponsor-reported two-sided test gave p = 0.372, and the unadjusted recalculation gave a mean difference of 0.3 with p = 0.429.

The confidence interval from the recalculation includes zero. The record notes missing primary endpoint values, lists eight secondary outcomes, and reports no serious or other adverse events in the posted safety counts; deaths are not reported. Most importantly, the registry record does not report an analysis establishing whether nasal decongestant test response predicts treatment outcome. The primary results describe an uncertain overall group comparison, not a test of that predictive hypothesis.