Dose Finding Study of Fluticasone Furoate Nasal Spray for Uncomplicated Acute Rhinosinusitis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Dose Finding Study of Fluticasone Furoate Nasal Spray for Uncomplicated Acute Rhinosinusitis (NCT01018030), a randomized phase 2 study. The primary outcome is Mean Change From Baseline in the Daily Major Symptom Score (MSS) Over the Entire Treatment Period (Weeks 1-2).

2. Clinical Question

The major symptom score (MSS) combines ratings for nasal congestion or stuffiness, sinus headache or pressure or facial pain or pressure, and postnasal drip. Daily MSS averages morning and evening scores. Each symptom is rated from 0 to 3, from none to severe, and the combined score ranges from 0 to 9. The endpoint therefore captures change in the overall burden of these symptoms rather than a single symptom or a clinical event.

The registry record describes a two-week treatment study and reports the primary outcome over the entire treatment period, up to two weeks. The comparison addresses whether average symptom-score changes differed between the randomized treatment groups. It does not, by itself, answer questions about outcomes beyond the treatment period or about individual symptoms in isolation.

3. Trial Design

This was a randomized, parallel-group, placebo-controlled phase 2 study of FFNS in uncomplicated acute rhinosinusitis. The official title describes a double-blind, multi-centre, two-week treatment study, and the registry classifies masking as quadruple. The intervention groups received FFNS 110 mcg QD, FFNS 110 mcg BD, or placebo nasal spray. The study summary states that treatment was assessed without antibiotic use.

The registry record reports enrollment of 741 and status as completed. The recorded study start was 2010-01-06, and primary completion was 2010-07-01. The sponsor was GlaxoSmithKline. These details establish the trial’s broad setting and scope, but do not describe every operational feature of its conduct.

The primary outcome was evaluated in an Intent-to-Treat population defined in the record as randomized participants who received at least one dose of double-blind study drug. Participants missing diary data at baseline or post-baseline were not included in this endpoint analysis. The group counts for the primary endpoint were 242 for placebo, 237 for FFNS 110 mcg QD, and 245 for FFNS 110 mcg BD. These analysis counts need not equal the enrollment figure because enrollment and endpoint analysis populations describe different stages of participation.

The registry record does not report the original sample-size justification, allocation ratio, detailed masking procedures, study sites, eligibility criteria beyond the condition and age description, or the specific covariates used in the primary ANCOVA. It also does not report the trial’s full statistical analysis plan. Those omissions limit how far the design can be reconstructed from the registry record alone.

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

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Intent-to-Treat (ITT) Population: all randomized participants who received at least one dose of double-blind study drug. Participants with missing diary data at baseline or post-baseline were not included in this 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 From Baseline in the Daily Major Symptom Score (MSS) Over the Entire Treatment Period (Weeks 1-2), measured over Baseline and entire treatment period (up to 2 weeks).

The primary endpoint is mean change from baseline in daily major symptom score over the entire treatment period, described as weeks 1-2 and up to two weeks. The baseline score was the average daily MSS over the last 3 days before randomization. The change score compares that baseline average with the daily MSS averaged over the treatment period.

The MSS combines three symptoms: nasal congestion or stuffiness, sinus headache or pressure or facial pain or pressure, and postnasal drip. Each symptom is scored from 0 to 3, with higher values indicating more severe symptoms; the total ranges from 0 to 9. Daily MSS is the average of the morning and evening MSS. A negative change indicates a lower average score during treatment than at baseline.

This composite endpoint is used to represent change across several major symptoms rather than focusing on one symptom alone. Averaging daily ratings over the treatment period also provides a measure of the overall symptom pattern during the study, rather than relying on a single assessment. As a continuous outcome, the endpoint can be summarized by group means and compared using a mean difference.

The endpoint is not a direct measure of time to recovery, recurrence, or outcomes after treatment. Those questions are distinct from the average symptom-score change reported for this primary analysis.

7. Results Posted in the Registry

• FFNS 110 mcg QD: mean -3.36 versus -2.97 on control; difference -0.39 (95% CI -0.74 to -0.04), standardized effect d = -0.20; z-test p = 0.027.
• FFNS 110 mcg BD: mean -3.33 versus -2.97 on control; difference -0.36 (95% CI -0.71 to -0.01), standardized effect d = -0.18; z-test p = 0.042.

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.

Mean Change From Baseline Over the Entire Treatment Period in AM MSS

• 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:
  • FFNS 110 mcg QD: mean -3.40 versus -3.10 on control; difference -0.30 (95% CI -0.63 to 0.03), standardized effect d = -0.16; z-test p = 0.077.
  • FFNS 110 mcg BD: mean -3.30 versus -3.10 on control; difference -0.20 (95% CI -0.52 to 0.12), standardized effect d = -0.11; z-test p = 0.219.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between FFNS 110 mcg QD and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between FFNS 110 mcg BD and the control. The interval gives the range of effects that remain compatible with the data.

Mean Change From Baseline Over the Entire Treatment Period in PM MSS

• 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:
  • FFNS 110 mcg QD: mean -3.40 versus -3.00 on control; difference -0.40 (95% CI -0.73 to -0.07), standardized effect d = -0.22; z-test p = 0.018.
  • FFNS 110 mcg BD: mean -3.40 versus -3.00 on control; difference -0.40 (95% CI -0.73 to -0.07), standardized effect d = -0.21; z-test p = 0.018.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for FFNS 110 mcg QD than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for FFNS 110 mcg BD than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Mean Change From Baseline Over the Entire Treatment Period in the Daily Nasal Congestion/Stuffiness Score

• 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:
  • FFNS 110 mcg QD: mean -1.10 versus -1.00 on control; difference -0.10 (95% CI -0.21 to 0.01), standardized effect d = -0.16; z-test p = 0.077.
  • FFNS 110 mcg BD: mean -1.10 versus -1.00 on control; difference -0.10 (95% CI -0.21 to 0.01), standardized effect d = -0.16; z-test p = 0.077.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between FFNS 110 mcg QD and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between FFNS 110 mcg BD and the control. The interval gives the range of effects that remain compatible with the data.

The registry lists 13 secondary outcomes, including time to symptom improvement and changes in morning and evening MSS and symptom-specific scores. The posted numerical summaries represented in the registry record include morning MSS, evening MSS, and daily nasal congestion or stuffiness. Across these summaries, treatment-group mean changes are generally in the same negative direction as placebo changes, with the size and uncertainty of between-group contrasts varying by measure and dosing schedule.

This broad pattern is compatible with the primary endpoint’s direction, but secondary outcomes should not be treated as independent confirmation of the primary result. They examine related aspects of symptom change, and their results can be correlated because they use overlapping symptoms, time periods, and diary measurements. The registry record does not report a multiplicity adjustment for the secondary comparisons.

Unadjusted secondary results carry less weight when many outcomes or comparisons are examined. General explanation: as the number of statistical tests grows, the chance of obtaining at least one apparently notable result by chance can increase. Without a prespecified hierarchy or a reported adjustment, individual secondary p-values should be interpreted cautiously and as exploratory rather than as a set of definitive tests.

The registry record does not provide enough detail to establish which secondary outcomes were prespecified as key, whether an ordered testing strategy was planned, or how missing observations were handled for each secondary analysis. The secondary findings can add context to the primary symptom-score result, but they do not independently establish the broader pattern beyond the measures and analysis details posted in the record.

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

• First Time to Symptom Improvement
• Mean Change From Baseline Over the Entire Treatment Period in AM MSS
• Mean Change From Baseline Over the Entire Treatment Period in PM MSS
• Mean Change From Baseline Over the Entire Treatment Period in the Daily Nasal Congestion/Stuffiness Score
• Mean Change From Baseline Over the Entire Treatment Period in the AM Nasal Congestion/Stuffiness Score
• Mean Change From Baseline Over the Entire Treatment Period in the PM Nasal Congestion/Stuffiness Score
• Mean Change From Baseline Over the Entire Treatment Period in the Daily Sinus Headache/Pressure or Facial Pain/Pressure Score
• Mean Change From Baseline Over the Entire Treatment Period in the AM Sinus Headache/Pressure or Facial Pain/Pressure Score

9. Statistical Interpretation

10. Statistical Methods Explained

Mean change and the treatment contrast. The endpoint is continuous: each participant has a symptom-score change, and the result is summarized as a group mean. A mean difference compares the average change in one treatment group with the average change in placebo. Because the score is a change from baseline, negative values indicate lower scores during the treatment period than at baseline. A negative treatment-minus-placebo contrast means the average reduction was greater in that treatment group, as coded by this contrast.

Least-squares means and ANCOVA. The registry identifies the sponsor’s primary comparisons as ANCOVA and reports least-squares mean differences. In general, analysis of covariance compares group outcomes while accounting for specified variables in a statistical model. A least-squares mean is a model-based group estimate, and its difference represents a model-based contrast. The model’s covariates and adjustment details are not reported in the registry record, so the exact adjustment cannot be reconstructed from the listed results.

ANCOVA is often used for continuous outcomes in randomized trials because baseline values or other prespecified variables can be incorporated into a model. That general rationale does not establish which variables were used in this trial. The description of the endpoint identifies a baseline score in the construction of change, but does not state the covariates in the sponsor’s ANCOVA. Those details are not reported in the registry record.

Standard errors and confidence intervals. The arm summaries report standard errors (SEs). In general, an SE describes the estimated uncertainty of a sample mean: smaller SEs indicate greater precision in estimating that mean, under the model and sampling assumptions. A confidence interval presents a range of values compatible with the data and specified statistical procedure. A 95% confidence interval is a procedure that, under its assumptions, would cover the target parameter in 95% of repeated samples. It is not a range containing 95% of individual outcomes, nor does it give the probability that a fixed parameter lies in this particular interval.

The sponsor’s primary comparisons report 95% confidence intervals. Both intervals are below zero, which aligns with the negative direction of the treatment-minus-placebo estimates. Interval width matters as well as direction: a narrower interval indicates more precise estimation, while a wider interval leaves more uncertainty about the size of the contrast. The registry reports the interval limits but does not provide the model’s full variance-covariance details.

p-values and statistical evidence. A p-value is calculated under a null hypothesis and model assumptions. It describes how unusual data at least as incompatible with that null would be if the null and assumptions held; it is not the probability that the null hypothesis is true. The sponsor reports p = 0.008 for QD versus placebo and p = 0.014 for BD versus placebo. These are the reported ANCOVA p-values. The simple recalculations report unadjusted p-values, which are separate estimates based on posted summaries and do not account for unknown model adjustments.

Why over-dispersion can matter. General explanation: for count outcomes, over-dispersion means the observed variability exceeds what a simple model assumes. If ignored, standard errors can be too small and confidence intervals or tests can be misleading. The primary endpoint is a continuous symptom score, not a count outcome. The registry record does not report an over-dispersion model, and such a model should not be inferred from these results.

Unadjusted recalculation. The recalculated comparisons are simple, unadjusted estimates derived from posted arm summaries. The calculation uses the mean changes and their reported standard errors to estimate a treatment contrast and uncertainty; where the record indicates an approximate standard deviation, that reconstruction is approximate. These calculations do not reproduce an ANCOVA with participant-level observations. The assumptions and information available to the recalculation are therefore more limited than those available to the sponsor’s full analysis, if conducted as described.

The record marks the primary comparisons as not having a discrepancy between the reported results and recalculation. That does not mean the methods are identical: the recalculated p-values and sponsor ANCOVA p-values differ, and the procedures answer their questions using different information and adjustment. The sponsor’s analysis remains the reported trial analysis; the recalculation is best treated as a check on the broad direction and scale of the posted summary statistics.

Planning calculations. The sample-size illustrations use a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. They consider effects set at the stated fraction of the observed effect. General explanation: a two-sided test allows for evidence in either direction, and power is the probability of detecting a specified effect under the planning assumptions if that effect is true. The illustrations are not the trial’s original design calculation; the original sample-size justification is not reported in the registry record.

The sample-size illustrations concern continuous outcomes and give participants per arm. They are not the realized power of the completed trial. General explanation: planning power depends on assumptions about the true effect, variability, allocation, and statistical test. Changing any of those assumptions can change the number of participants needed. The posted calculations are conditional illustrations, not a retrospective measure of whether the trial was adequately powered.

11. Confidence Intervals and Precision

Precision is reflected by the uncertainty around an estimate, not only by whether a p-value is below a threshold. For the sponsor’s QD comparison, the estimated least-squares mean difference is -0.386 and the 95% confidence interval runs from -0.67 to -0.10. For BD, the estimate is -0.357 and the interval runs from -0.64 to -0.07. Both reported intervals lie below zero, while their ranges still allow more than one plausible magnitude of difference.

These intervals are not so narrow that they identify a single exact treatment contrast. They support a negative average difference under the reported ANCOVA, but the possible values span a range. Precision is also tied to the endpoint and model: these intervals concern the mean change in daily MSS during the treatment period, not an individual participant’s outcome, another symptom measure, or longer-term effects.

The recalculated unadjusted estimates use different assumptions and are not interchangeable with the sponsor’s confidence intervals. The posted arm standard errors describe uncertainty around each group mean, while the sponsor’s intervals describe uncertainty around model-based between-group contrasts. A confidence interval for a contrast is the more direct measure for judging the precision of the treatment comparison.

The registry does not report a clinical-importance threshold for the MSS contrast. Statistical precision alone therefore cannot establish whether the estimated difference would be considered important in practice. Nor do the intervals account for limitations that are not represented in the model, such as uncertainty arising from missing diary data or unreported choices in analysis. The intervals quantify uncertainty under the reported procedure and its assumptions.

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 for participants per arm for 80% power and participants per arm for 90% power. They are not total event counts: the primary outcome is continuous, and the posted planning assumptions specify equal allocation between two arms. The illustrations use a two-sided significance level of 0.05 and a normal approximation.

Each planning scenario uses a fraction of the observed effect: 100%, 75%, or 50%. The 80% power column gives the number of participants per arm that the stated calculation estimates would be needed to detect that specified effect with 80% power under its assumptions. The 90% power column gives the corresponding number per arm for 90% power. Higher planned power generally requires more participants for the same effect and assumptions.

The figures illustrate how planning changes when the assumed effect changes. Smaller effects need more participants to distinguish them from chance variation at the same significance level and power target. Thus, planning for 75% or 50% of the observed effect gives larger per-arm requirements than planning for the full observed effect in the listed comparisons. These are conditional planning illustrations based on the observed estimates, not the trial’s own original sample-size justification; that justification is not reported in the registry record.

This is not observed power. The calculations do not measure the probability that the completed study detected an effect after its results were known. They show hypothetical sample-size requirements under the stated assumptions. The design assumptions used by the trial itself, beyond the planning illustration, are not reported in the registry record.

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 = -0.390; pooled standard deviation σ = 1.935.
2. n = 2 × (1.96 + 0.842)² × 1.935² / -0.390² = 386.2, rounded up to 387 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 <- -0.39                      # observed difference in means
sigma <- 1.93450820948856                     # 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(1018030)
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 = 387 (80% power), 518 (90% power)
 75% of observed effect: n per arm = 687 (80% power), 920 (90% power)
 50% of observed effect: n per arm = 1,545 (80% power), 2,069 (90% power)
power.t.test: 387.2 
Simulated power at n = 387 per arm: 0.805 (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 analysis as ANCOVA, with least-squares mean differences and 95% confidence intervals. For QD versus placebo, the reported difference is -0.386, with a 95% confidence interval from -0.67 to -0.10 and p = 0.008. For BD versus placebo, it is -0.357, with a 95% confidence interval from -0.64 to -0.07 and p = 0.014.

The recalculated comparisons are simple, unadjusted estimates from posted summary statistics. They point in the same negative direction, but their p-values are 0.027 for QD and 0.042 for BD. The estimates and tests need not match because a summary-statistic recalculation is not the same as the sponsor’s ANCOVA. The registry record does not identify the covariates or other model details needed to reproduce the ANCOVA.

The recalculation is therefore supplementary: it checks whether the broad direction and scale are consistent with the posted arm summaries, but it does not replace the sponsor’s reported analysis. The record does not flag a discrepancy. This means the recalculation is not identified as contradicting the posted sponsor result; it does not make the two methods equivalent or remove uncertainty about unreported model details.

15. Multiplicity, Missing Data and Analysis Populations

The registry record reports two sponsor ANCOVA comparisons for the primary endpoint, each comparing an FFNS schedule with placebo. It does not report whether the two primary comparisons were adjusted for multiplicity, whether one was designated as the primary contrast, or whether a testing hierarchy was prespecified. The record also lists 13 secondary outcomes and does not report a multiplicity adjustment for their analyses.

Multiplicity matters when several hypotheses are tested. General explanation: if each test is evaluated separately at a chosen threshold, conducting many tests can increase the chance of at least one chance-positive result across the family of tests. An adjustment or prespecified testing sequence can address that issue, but no such procedure should be assumed when it is not described in the registry record. The posted p-values should therefore be read as reported for their individual comparisons, without claiming family-wise error control.

The primary population is described as randomized participants who received at least one dose of double-blind study drug. Participants with missing diary data at baseline or post-baseline were excluded from the primary endpoint analysis. This is the population definition reported for the endpoint, rather than an analysis including every randomized participant regardless of diary availability.

The registry record does not report how many participants were excluded for missing diary data, whether missingness differed by treatment group, or the method used to handle missing daily entries among participants retained in the analysis. It also does not report sensitivity analyses for missing data. The effect of these missing-data decisions on the estimated comparisons therefore cannot be assessed from the registry record.

Interim analyses, stopping rules, and the full statistical analysis plan are not reported in the registry record. Their absence from the record does not establish that they were not conducted or specified; it means the posted information is insufficient to describe them. Likewise, the covariates in the sponsor’s ANCOVA and the handling of deviations from the planned analysis are not reported.

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.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: rib fracture (0.4%).

The serious adverse event counts are reported for groups at risk of 245 for placebo, 240 for FFNS 110 mcg QD, and 252 for FFNS 110 mcg BD. The corresponding counts affected are 0, 0, and 1. The registry also lists Rib fracture at 0.4% among the top serious terms. These figures describe reported serious adverse events in the recorded groups; they do not establish whether an event was caused by study treatment.

For other, non-serious adverse events, the record reports 41 affected participants in placebo, 41 with QD, and 46 with BD, using the same respective group-at-risk counts stated for those summaries. The serious and other adverse-event figures should be read separately from the primary efficacy analysis, whose endpoint-specific participant counts differ.

Deaths are listed as null, so deaths are not reported in the registry record; null should not be read as a count of zero. The registry record does not give event-level context, causal assessments, or enough detail to compare the nature and duration of all reported events. These counts are descriptive safety information for the study and do not support conclusions beyond the recorded observations.

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

The posted primary results show lower average daily MSS during treatment than at baseline in all three groups. The sponsor’s ANCOVA estimates a negative mean difference for each FFNS schedule relative to placebo, and both reported 95% confidence intervals lie below zero. This describes the direction and statistical uncertainty of the average symptom-score contrasts in the analyzed population.

The result does not establish the size of benefit for any particular participant. A group mean is not a prediction of an individual’s experience, and the registry does not report a responder analysis or a threshold for a clinically important MSS change. The estimates also concern a composite score, so they cannot be read as separate effects on each symptom.

The result is limited to the study’s treatment period, described as up to two weeks. It does not establish what happens after treatment, how symptoms change over a longer period, or how the treatments compare on outcomes not reported in the primary analysis. The secondary outcomes provide related symptom information, but their unadjusted interpretation is limited by the number of outcomes and by missing details on multiplicity.

The registry record does not report enough information to reconstruct the ANCOVA covariates, all missing-data procedures, or the original sample-size justification. The reported statistical comparisons should be interpreted within those limits. The findings describe the posted results; they do not by themselves resolve questions about clinical importance, generalizability to populations not described in the record, or effects outside the measured outcomes and timeframe.

18. Why This Trial Matters Statistically

This trial illustrates why a treatment comparison should be read through both its estimate and its uncertainty. A negative mean difference describes direction relative to placebo, while the confidence interval gives a range of values compatible with the reported analysis. The p-value alone cannot convey the magnitude or practical importance of the contrast.

It also shows the distinction between the sponsor’s adjusted analysis and a simple recalculation from summary statistics. The two approaches have the same broad direction but do not produce identical p-values. Summary-based recalculations can provide a useful check, but they cannot recover unreported model adjustments or replace a participant-level analysis.

The primary endpoint is a composite continuous score built from daily symptom ratings. Understanding its construction matters: a change in the composite reflects the combined symptom measure, not necessarily a uniform change in each component. The analysis population definition matters as well, because participants missing diary data at baseline or after baseline were excluded from the primary endpoint analysis.

Finally, the record lists multiple secondary outcomes but does not report multiplicity procedures. This is a practical reminder that a collection of unadjusted tests should not be read as a set of equally strong confirmations. The study is statistically informative about its specified symptom-score comparison, while unanswered questions about model details, missing data, and clinical importance remain relevant to interpretation.

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.

Several trial-specific details needed to fully evaluate the estimates are not reported in the registry record. These include the original sample-size justification, the covariates used in the primary ANCOVA, the allocation ratio, and the full statistical analysis plan. The planning figures associated with the posted estimates are illustrations and should not be mistaken for the trial’s design assumptions.

The primary endpoint analysis excludes participants with missing diary data at baseline or post-baseline. The record does not report the number excluded, the pattern of missingness by group, the handling of intermittent missing diary entries, or sensitivity analyses. These omissions limit assessment of how missing data may have influenced the reported group estimates.

The registry reports multiple secondary outcomes but does not describe a multiplicity strategy. Consequently, secondary p-values should be interpreted cautiously, especially when considered collectively. The record also does not state whether an important secondary endpoint hierarchy or other confirmatory plan was used.

The treatment period was up to two weeks, and the main measure is a symptom diary composite. The posted primary result therefore does not characterize longer-term outcomes or establish the importance of a given score difference to participants. No minimum clinically important difference or responder threshold is reported in the registry record.

The primary analysis counts are endpoint-specific, while safety summaries use their own at-risk group counts. Those populations should not be conflated. The registry record does not provide sufficient detail to reconcile all analysis denominators or to describe event-level safety context. Finally, the study’s age and condition description does not provide a complete account of eligibility or the enrolled population’s characteristics, limiting assessment of generalizability.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Dose Finding Study of Fluticasone Furoate Nasal Spray for Uncomplicated Acute Rhinosinusitis — NCT01018030.
• Registry record last updated 2017-05-17; status last verified 2017-04.
• Results first posted 2011-04-12.
• 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

NCT01018030 is a completed phase 2 randomized, quadruple-masked, parallel-group study of FFNS nasal spray for uncomplicated acute rhinosinusitis. The official title describes a placebo-controlled, multi-centre, two-week treatment study in adults and adolescents 12 years and older. Enrollment was 741. The sponsor was GlaxoSmithKline.

The primary endpoint was mean change from baseline in daily MSS over the entire treatment period. The sponsor reported ANCOVA least-squares mean differences versus placebo of -0.386 for QD and -0.357 for BD, with 95% confidence intervals below zero. The recalculated unadjusted comparisons point in the same direction but are not a substitute for the sponsor’s analysis.

The registry record does not report the original sample-size justification, full statistical plan, multiplicity procedures, or detailed missing-data methods. The findings should be understood as average symptom-score comparisons over the recorded treatment period, with those limits in mind.