A Study to Test a New Decongestant in Patients With Allergic Rhinitis Following a Nasal Allergen Challenge: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study to Test a New Decongestant in Patients With Allergic Rhinitis Following a Nasal Allergen Challenge (NCT00562120), a randomized phase 2 study. The primary outcome is Minimum Cross-Sectional Area (Amin) Proportion Measured Using Acoustic Rhinometry.

2. Clinical Question

3. Trial Design

The registry describes a Phase 2, randomized, double-blind, double-dummy, placebo-controlled, four-way crossover study. It enrolled 21 participants and is marked completed. The listed start and primary completion dates are 2007-12 and 2008-08. Seasonal allergic rhinitis is the stated condition.

The interventions listed are placebo, Allegra, Allegra-D, and PF-03654746. The primary-outcome results include placebo, Allegra-D, PF-03654746 1 mg, and PF-03654746 10 mg. Although Allegra is listed as an intervention, a separate Allegra primary-outcome result is not reported in the registry record.

In a crossover trial, participants receive different interventions during separate periods, so comparisons may use information from the same participant under more than one intervention. This is a general feature of crossover designs; the registry does not report the intervention sequence, period-specific allocation details, washout arrangements, or how the sponsor’s ANOVA handled period and within-participant effects. Those details matter because analyses that account for the paired structure can differ from comparisons treating groups as independent.

The primary-outcome population is described as all participants randomized at baseline who received at least 1 dose of double-blind treatment. Outcome-specific counts are reported by intervention, but the reasons for differences in those counts are not reported in the registry record. The sample-size justification, original design assumptions, and detailed statistical analysis plan are also not reported in the registry record.

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.

First Intervention Period

Reasons for not completing this period:

Washout Period 1 (At Least 14 Days)

Second Intervention Period

Washout Period 2 (At Least 14 Days)

Analysis population for the primary outcome, as defined in the registry: Full analysis set included all participants randomized at baseline and who received at least 1 dose of double-blind treatment.

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: Safety analysis set included all participants randomized at baseline and who received at least 1 dose of double-blind treatment.

6. Primary Endpoint

The registry lists the primary outcome as Minimum Cross-Sectional Area (Amin) Proportion Measured Using Acoustic Rhinometry, measured over 2 hrs 10 min, 2 hrs 25 min, 2 hrs 40 min post dose (Baseline); 2 hrs 55 min, 3 hrs 10 min, 3 hrs 25 min post dose on Day 1 of each intervention period.

The primary endpoint is the proportion of minimum cross-sectional area (Amin) after allergen challenge relative to baseline, measured using acoustic rhinometry. Acoustic rhinometry assesses the geometry of the nasal cavity and nasopharynx and is used to evaluate nasal obstruction. At each measurement time, measurements from both nostrils were averaged.

For each intervention period, baseline Amin was the mean of measurements taken after diluent and before allergen challenge. The post-challenge value was the mean of measurements taken after the allergen challenge. The endpoint is the ratio of that post-challenge mean to the baseline mean. As a general interpretation, a ratio nearer to baseline indicates less change in the measured area, while a lower ratio indicates a larger proportional decline. This is an objective measurement of nasal geometry, not a direct measure of how a participant feels.

The registry reports measurements at specified times from 2 hrs 10 min to 3 hrs 25 min after dose on Day 1 of each intervention period. The exact interpretation of a clinically meaningful change in the ratio is not reported in the registry record. Nor is a threshold defining a meaningful benefit. The endpoint therefore describes a physiologic response to a controlled allergen challenge; it does not, by itself, establish the importance of any difference to patients.

7. Results Posted in the Registry

• PF-03654746 10 mg: mean 0.76 versus 0.80 on control; difference -0.04 (95% CI -0.19 to 0.12), standardized effect d = -0.15; z-test p = 0.652.
• PF-03654746 1 mg: mean 0.74 versus 0.80 on control; difference -0.05 (95% CI -0.23 to 0.13), standardized effect d = -0.19; z-test p = 0.561.
• Allegra-D: mean 0.72 versus 0.80 on control; difference -0.08 (95% CI -0.24 to 0.08), standardized effect d = -0.31; z-test p = 0.346.

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.

Minimum Cross-Sectional Area (Amin) Maximum Fall Measured Using Acoustic Rhinometry

• 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:
  • PF-03654746 10 mg: mean 0.15 versus 0.19 on control; difference -0.04 (95% CI -0.11 to 0.04), standardized effect d = -0.29; z-test p = 0.379.
  • PF-03654746 1 mg: mean 0.16 versus 0.19 on control; difference -0.03 (95% CI -0.12 to 0.05), standardized effect d = -0.25; z-test p = 0.450.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between PF-03654746 10 mg 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 PF-03654746 1 mg and the control. The interval gives the range of effects that remain compatible with the data.

Nasal Volume Maximum Fall Measured Using Acoustic Rhinometry

• 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:
  • PF-03654746 10 mg: mean 3.13 versus 3.27 on control; difference -0.14 (95% CI -1.75 to 1.47), standardized effect d = -0.06; z-test p = 0.862.
  • PF-03654746 1 mg: mean 3.24 versus 3.27 on control; difference -0.03 (95% CI -1.65 to 1.58), standardized effect d = -0.01; z-test p = 0.970.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between PF-03654746 10 mg 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 PF-03654746 1 mg and the control. The interval gives the range of effects that remain compatible with the data.

The registry lists secondary outcomes covering maximum fall in Amin, maximum fall in nasal volume, and nasal symptom scores for congestion, itching, rhinorrhea, and sneezing. The posted continuous results for maximum fall measures show variation among intervention means, without a consistent pattern that would strengthen the primary-outcome evidence. The reported analyses for those measures likewise do not provide a clear, precise basis for a broader conclusion about intervention differences.

The registry lists symptom-score outcome domains, but numerical results for those symptom measures are not reported in the registry record. It is therefore not possible to assess how closely the subjective symptom outcomes align with the acoustic rhinometry findings. The secondary outcomes should be understood as additional measurements rather than confirmation of the primary result.

Unadjusted secondary results carry less weight when many outcomes and comparisons are examined, because the chance of apparently notable findings can increase across multiple tests. The registry lists 48 analyses, while the multiplicity procedure and prespecified hierarchy are not reported in the registry record. Interpretation should therefore focus on the primary endpoint and treat secondary patterns as exploratory unless the analysis plan establishes otherwise. The secondary findings do not resolve the imprecision in the primary comparisons.

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

• Minimum Cross-Sectional Area (Amin) Maximum Fall Measured Using Acoustic Rhinometry
• Nasal Volume Maximum Fall Measured Using Acoustic Rhinometry
• Nasal Symptom Scores: Nasal Congestion, Nasal Itching, Rhinorrhea
• Nasal Symptom Scores: Sneezing

9. Statistical Interpretation

10. Statistical Methods Explained

What does a group mean describe?

The primary endpoint is continuous, and the registry reports its mean and standard deviation for each intervention. A mean summarizes the central value of the observed measurements; the standard deviation describes how spread out individual measurements are around that mean. The standard deviation is not the uncertainty in the mean itself. Uncertainty in a treatment comparison depends on the amount of information and the variability in the measurements, as well as on the analysis design.

For the primary outcome, the reported means are 0.76 for PF-03654746 10 mg, 0.742 for PF-03654746 1 mg, 0.717 for Allegra-D, and 0.795 for placebo. Group means do not show how each participant’s outcome changed across intervention periods. That participant-level information can be important in a crossover study.

What is the purpose of a confidence interval?

A confidence interval presents a range of estimates compatible with the data and the method used to calculate it. A narrow interval indicates greater precision than a broad interval, all else equal. It is not a guarantee that the true effect lies within the particular interval. Nor does an interval establish clinical importance: that requires an appropriate threshold, which is not reported in the registry record.

The recalculated 95% confidence intervals compare each intervention’s mean with placebo using posted summary statistics. Each interval includes zero. This means the range includes no mean difference under that calculation, while also including differences in either direction. These intervals are simple unadjusted recalculations, not the sponsor’s participant-level crossover intervals; sponsor confidence intervals for the ANOVA comparisons are not reported in the registry record.

Why does crossover structure matter?

In general, a crossover study can use within-participant contrasts: each participant’s outcomes under different interventions can be compared. This can account for stable differences between participants and may yield a different estimate and uncertainty from an analysis that treats intervention groups as independent. The posted summary statistics do not contain the individual paired observations needed to reconstruct such an analysis. The sponsor reports ANOVA, but the model specification and its handling of period, sequence, and within-participant correlation are not reported in the registry record.

The recalculated comparisons use the group means and standard deviations and are therefore not a reconstruction of the crossover analysis. Their role is to provide an unadjusted summary-based reference. They should not be interpreted as correcting or replacing the sponsor’s analysis.

What do the p-values say?

A p-value describes how compatible observed data are with a specified null model, under the assumptions of the test. It does not give the probability that the null hypothesis is true, the probability that a result is due to chance, or the size or clinical importance of an effect. The sponsor’s primary ANOVA p-values are 0.302, 0.229, and 0.134 for the three reported comparisons against placebo. Recalculated unadjusted p-values are 0.652, 0.561, and 0.346 for those same comparisons. These values come from different analyses and should not be conflated.

The registry lists 48 analyses across the outcome record. The multiplicity adjustment, if any, and the extent to which the analyses were prespecified are not reported in the registry record. When many outcomes or comparisons are assessed, selective emphasis on a small subset can overstate the strength of evidence. This is one reason to interpret individual secondary or pairwise results cautiously.

What do standard deviations and variability imply?

Greater variability makes a group mean less precise if other aspects of the design remain unchanged. In the primary results, the standard deviations are 0.150, 0.255, 0.194, and 0.304 for PF-03654746 10 mg, PF-03654746 1 mg, Allegra-D, and placebo, respectively. These summaries describe spread, but do not reveal whether variability was driven by particular participants, periods, or measurement conditions.

General statistical note: in some data, observations vary more than a simple model assumes, a property often called over-dispersion. Accounting for that extra variation can widen uncertainty and alter inference. The registry does not report over-dispersion as an issue or describe a model adjustment for it; there is no basis to infer that it occurred in this trial.

11. Confidence Intervals and Precision

The summary-based 95% confidence intervals for the primary mean differences are broad. For PF-03654746 10 mg versus placebo, the estimated difference is -0.035, with an interval from -0.187 to 0.117. For PF-03654746 1 mg versus placebo, the estimate is -0.053, with an interval from -0.232 to 0.126. For Allegra-D versus placebo, the estimate is -0.078, with an interval from -0.240 to 0.084.

All three intervals include zero and extend to differences on either side of it. Thus, the posted group summaries do not estimate the direction and magnitude of each difference precisely. The intervals also allow a range of effect sizes, so a small estimated difference should not be read as proof that the true difference is exactly small or absent.

These are unadjusted recalculated intervals based on summary statistics, not confidence intervals from the sponsor’s ANOVA. The registry reports sponsor p-values but does not report confidence intervals for the sponsor comparisons. Because the design is crossover, participant-level paired data and the details of the ANOVA would be needed to make a more directly aligned precision assessment. A clinical interpretation would also require a meaningful-change threshold, which is not reported in the registry record.

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. The trial’s primary outcome is continuous, so the relevant entries describe participants per arm for 80% power and participants per arm for 90% power. In plain terms, those columns indicate illustrative group sizes intended to give the stated probability of detecting the specified effect under the planning assumptions, if that effect and those assumptions were correct. A higher target power generally requires more participants.

The planning illustration assumes a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. It uses the observed effect as its reference and also considers planning for 75% and 50% of that observed effect. Smaller effects require more participants to detect, because they are harder to distinguish from the variability in the measurements. The entries are hypothetical planning illustrations based on the observed effect, not the original trial’s design calculation. The original sample-size assumptions and justification are not reported in the registry record.

These calculated figures are not observed power. They do not describe the probability that this completed trial detected an effect, and they do not change the uncertainty in the results already observed. The study used a crossover design, whereas the stated planning assumptions describe equal allocation between two arms; the illustration should therefore not be mistaken for a complete design-specific calculation for the original 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 = -0.035; pooled standard deviation σ = 0.238.
2. n = 2 × (1.96 + 0.842)² × 0.238² / -0.035² = 726.5, rounded up to 727 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 <- -0.035                      # observed difference in means
sigma <- 0.238103515984801                     # 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(562120)
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 = 727 (80% power), 973 (90% power)
 75% of observed effect: n per arm = 1,292 (80% power), 1,730 (90% power)
 50% of observed effect: n per arm = 2,906 (80% power), 3,891 (90% power)
power.t.test: 727.5 
Simulated power at n = 727 per arm: 0.801 (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 reports ANOVA comparisons for the primary endpoint. The p-values versus placebo are 0.302 for PF-03654746 10 mg, 0.229 for PF-03654746 1 mg, and 0.134 for Allegra-D. The registry does not report effect estimates or confidence intervals for these ANOVA comparisons, nor enough model detail to reproduce them.

The recalculated comparisons use the posted intervention means and standard deviations, and produce different unadjusted p-values. They are not a reanalysis of individual crossover data. They treat the posted summaries as independent-group information and do not recover within-participant contrasts. Accordingly, the two sets of p-values answer questions through different calculations and should be kept distinct.

The registry record does not mark a discrepancy between sponsor results and the recalculations. The sponsor’s ANOVA remains the reported trial analysis; the summary-based calculations are an additional, limited perspective on the group means. The registry does not report the complete statistical plan needed to determine whether the sponsor’s model included all relevant crossover features or how its comparisons were selected.

15. Multiplicity, Missing Data and Analysis Populations

The registry record lists 7 outcome measures and 48 analyses. It reports several pairwise comparisons for the primary endpoint and additional analyses for secondary outcomes. The multiplicity adjustment, if any, is not reported in the registry record. The registry also does not report which comparisons were designated as confirmatory, whether a hierarchy of outcomes was planned, or whether interim analyses were conducted.

Multiplicity matters because repeated testing across outcomes and comparisons can increase the chance of a result appearing noteworthy even when there is no underlying difference. A prespecified testing strategy can help distinguish primary confirmatory questions from exploratory analyses. Without that information, individual unadjusted p-values should be interpreted cautiously and in the context of the broader set of analyses.

The primary-outcome population is defined as randomized participants at baseline who received at least 1 dose of double-blind treatment. Group-specific outcome counts are reported, but reasons for missing measurements or differences in outcome availability are not reported in the registry record. The handling of missing values, whether participants were excluded from particular analyses, and any sensitivity analyses for missing data are also not reported in the registry record.

The crossover design makes the analysis population and missingness especially relevant: availability of measurements across intervention periods can affect which within-participant comparisons contribute information. The registry does not describe how incomplete periods or incomplete outcome records were handled. The original sample-size justification, full statistical analysis plan, and details of any interim monitoring are not reported in the registry record, so those aspects cannot be evaluated from the posted results.

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 non-serious adverse event terms

The serious adverse event figures report zero affected participants in each listed intervention group: PF-03654746 10 mg, PF-03654746 1 mg, Allegra-D, and placebo. The corresponding numbers at risk are 20, 19, 19, and 19. These figures describe the reported serious-event counts in this study; they do not establish that serious events cannot occur, particularly given the limited group sizes.

The registry also reports other adverse events affecting 5 participants in the PF-03654746 10 mg group, 2 in the PF-03654746 1 mg group, 0 in the Allegra-D group, and 2 in the placebo group. The adverse-event record does not provide event terms in the listed serious-event category, and deaths are not reported in the record. These counts are descriptive and do not establish whether an event was caused by an intervention. The registry does not report enough detail to characterize event severity, timing, or clinical course.

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

The posted results describe short-term measurements of nasal cross-sectional area after a controlled allergen challenge. The primary outcome compares the post-challenge measurement with baseline, and the group means differ numerically across placebo, PF-03654746 doses, and Allegra-D. The recalculated intervals are broad and include zero; the sponsor’s ANOVA p-values are also reported without confidence intervals or detailed model specifications.

These results do not establish that PF-03654746 improves symptoms, nor do they establish that it has no effect. A lack of precise evidence for a difference is not proof of equivalence. The registry does not report a margin for equivalence or non-inferiority, or a threshold for a clinically meaningful change in the primary endpoint.

The outcome is an acoustic rhinometry measure after an experimental nasal challenge, rather than a direct measure of everyday symptoms or longer-term disease control. Although symptom scores are listed as secondary outcomes, their numerical results are not reported in the registry record. The trial’s reported findings therefore cannot answer whether participants experienced a meaningful difference in congestion or other symptoms in routine settings.

The study is described as a Phase 2 randomized crossover trial and enrolled 21 participants. Its results are informative as a small experimental assessment, but uncertainty remains about effect size, analysis details, missing data, and the multiplicity strategy. The posted results should be interpreted as evidence about the measured challenge response in this study, not as a complete account of clinical benefit, longer-term outcomes, or safety.

18. Why This Trial Matters Statistically

This trial illustrates the distinction between an observed group difference and a well-estimated treatment effect. The primary means are not identical, but the summary-based intervals are wide and include zero. A point estimate alone can invite an overly certain interpretation; considering its precision gives a more balanced account of what the data support.

The crossover design is also statistically important. It can allow comparisons within the same participant, but the value of that approach depends on an analysis that properly uses the paired measurements and accounts for relevant period features. The registry reports an ANOVA but not its model details. Simple comparisons based only on group summaries cannot recreate that analysis, which explains why recalculated and sponsor-reported p-values are different types of evidence.

The study also highlights why planning illustrations must be separated from observed findings. Sample-size figures based on the observed effect are hypothetical planning tools, not evidence that the completed study had a particular probability of detecting an effect. Their assumptions differ from the details that would be needed for a design-specific crossover calculation, and the original design rationale is not reported.

Finally, multiple outcomes and comparisons create interpretive challenges when the testing strategy is unavailable. Without the prespecified hierarchy and multiplicity approach, secondary results are best treated cautiously. Together, these issues show why a careful reading considers the endpoint, design, analysis, uncertainty, and reporting completeness rather than relying on a single p-value.

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 primary outcome measures a ratio after nasal allergen challenge, so its interpretation is specific to the measurement setting and timing reported. The registry does not report a threshold for clinical importance. The outcome is an objective nasal geometry measure, while the listed symptom-score outcomes do not have numerical results in the registry record.

The study is a crossover design, but the intervention sequence, washout details, and full ANOVA specification are not reported in the registry record. The posted group summaries do not permit reconstruction of paired participant-level comparisons. The recalculated intervals and p-values are therefore not a replacement for the sponsor’s crossover analysis.

The registry reports enrollment of 21, while the outcome-specific group counts vary. Reasons for the differences in available counts, missing-data handling, and sensitivity analyses are not reported in the registry record. The multiplicity adjustment and analysis hierarchy are also not reported despite the listed 48 analyses. These omissions limit assessment of how robust the reported comparisons are to missingness or multiple testing.

The original sample-size assumptions and justification are not reported in the registry record. The planning illustrations based on observed effects should not be treated as the study’s own design calculation. Finally, the posted results concern a short-term challenge response; longer-term outcomes and numerical symptom-score findings are not reported in the registry record.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: A Study to Test a New Decongestant in Patients With Allergic Rhinitis Following a Nasal Allergen Challenge — NCT00562120.
• Registry record last updated 2014-04-16; status last verified 2014-03.
• Results first posted 2014-04-16.
• 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

NCT00562120 is a completed Phase 2 randomized, double-blind, double-dummy, placebo-controlled, four-way crossover study in seasonal allergic rhinitis, with enrollment of 21. Its primary endpoint was the post-allergen-challenge to baseline ratio of minimum cross-sectional area measured by acoustic rhinometry.

The primary means were 0.76 for PF-03654746 10 mg, 0.742 for PF-03654746 1 mg, 0.717 for Allegra-D, and 0.795 for placebo. Sponsor-reported ANOVA p-values versus placebo were 0.302, 0.229, and 0.134, respectively. Summary-based recalculated confidence intervals are broad and include zero. The posted evidence is imprecise, and important details about the crossover model, multiplicity, and missing-data handling are not reported in the registry record.