AGN-229666 Ophthalmic Solution in Japanese Patients With Allergic Conjunctivitis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for AGN-229666 Ophthalmic Solution in Japanese Patients With Allergic Conjunctivitis (NCT02161146), a randomized phase 3 study. The primary outcome is Ocular Itching Score.

2. Clinical Question

The score measures itching on a scale from 0 to 4, with higher values representing more severe itching. The recorded assessments were made 5 minutes after allergen challenge. Scores were assessed 8 hours after AGN-229666 and vehicle administration and 4 hours after olopatadine administration; data from Days 1 and 15 were pooled and averaged. These differing assessment times matter when interpreting the cross-treatment results: the comparisons describe the outcomes at the recorded schedules, not necessarily at a common time after dosing.

The registry record describes five treatment strategies, including two mixed-eye regimens, while posted primary endpoint results give means for AGN-229666, vehicle, and olopatadine. The posted comparisons therefore answer a focused question about those three groups; primary endpoint values for the mixed-eye regimens are not reported in the registry record.

3. Trial Design

This was a Phase 3, randomized, double-masked, parallel trial. The registry record lists the condition as allergic conjunctivitis, enrollment of 240, and study status as completed. The recorded start date was 2014-06-04, and the primary completion date was 2014-12-20. The sponsor is listed as Allergan.

The intervention descriptions specify one drop in each eye on Days 1 and 15 for AGN-229666, vehicle, and olopatadine. Two additional strategies used different treatments in the two eyes: AGN-229666 with olopatadine, and AGN-229666 with vehicle. Although the design is listed as parallel, details of sequence generation, allocation concealment, and how the mixed-eye regimens relate to the parallel assignment are not reported in the registry record.

The primary measure was ocular itching score, pooled and averaged across Days 1 and 15. The listed primary analysis population includes randomized participants with treated-eye data available. This description does not establish how missing observations were handled or how observations from eyes were incorporated into the statistical analysis. Those details are not reported in the registry record.

Conjunctival hyperemia score is the posted secondary endpoint. The registry record lists two outcome measures, and the posted results include arm summaries for the primary and secondary scores. It does not report the trial’s original sample-size justification, the planned statistical model, the intended testing hierarchy, or interim analyses. The observed summaries and recalculated comparisons should therefore be read separately from any unreported protocol-based analysis plan.

4. Participant Flow and Accounting

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

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Participants from the Intent-to-Treat Population, all randomized participants, with data of treated eyes available for 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 Ocular Itching Score, measured over Days 1 and 15.

The primary endpoint is ocular itching score, a continuous measure reported as a mean with a standard deviation. Participants rated itching on a 0 to 4 scale, using 0.5 grade increments. A score of 0 means no itching; 4.0 represents incapacitating itch with an irresistible urge to rub. Higher scores therefore correspond to more severe reported itching.

Itching is directly relevant to allergic conjunctivitis symptoms, and a numeric rating allows the average scores between treatment groups to be compared. The registry describes ratings 5 minutes after allergen challenge. Assessments were made 8 hours after AGN-229666 and vehicle administration and 4 hours after olopatadine administration. Results from Days 1 and 15 were pooled together and averaged.

Pooling the two days gives a combined summary across those recorded assessments, rather than separate day-specific results. The registry record does not report day-specific estimates or the method used to account for repeated observations from the same participant or eye. The available mean scores describe the posted outcome on its defined scale; they do not, by themselves, establish how participants valued the size of a score difference or whether it is clinically important.

7. Results Posted in the Registry

• AGN-229666: mean 0.33 versus 1.48 on control; difference -1.15 (95% CI -1.35 to -0.95), standardized effect d = -1.64; z-test p = <0.001.
• Olopatadine: mean 0.29 versus 1.48 on control; difference -1.19 (95% CI -1.39 to -0.99), standardized effect d = -1.70; z-test p = <0.001.

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.

Conjunctival Hyperemia 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 deviations.
• Result:
  • AGN-229666: mean 1.15 versus 1.61 on control; difference -0.46 (95% CI -0.67 to -0.25), standardized effect d = -0.58; z-test p = <0.001.
  • Olopatadine: mean 1.34 versus 1.61 on control; difference -0.27 (95% CI -0.51 to -0.03), standardized effect d = -0.32; z-test p = 0.025.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for AGN-229666 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 Olopatadine than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The secondary endpoint is conjunctival hyperemia score, also summarized as a mean with a standard deviation across Days 1 and 15. Across the posted arm summaries, both AGN-229666 and olopatadine have lower average scores than vehicle. The direction is therefore broadly concordant with the primary endpoint pattern, where both active-treatment means are lower than vehicle. This parallel direction is descriptive; it does not establish that the two endpoints measure the same aspect of the condition or that their effects should be expected to match.

The recalculated unadjusted comparisons indicate stronger numerical separation from vehicle for AGN-229666 than for olopatadine on the secondary score. The posted unadjusted p-values differ between those comparisons. Because the registry record does not report an adjustment for the multiple endpoints and comparisons, these secondary calculations should be treated as exploratory evidence rather than as an independent confirmatory finding. The primary and secondary endpoints are related to the trial’s stated evaluation, but a favorable pattern across both does not remove the uncertainty associated with unreported analysis choices.

General statistical explanation: when several outcomes or treatment contrasts are examined, the chance of obtaining an apparently notable result by chance can increase if each result is considered separately. Multiplicity procedures can control or otherwise address that issue, but no such procedure is reported in the registry record. The number of outcome measures is listed as two, and the registry record does not report a hierarchy, a designated confirmatory role for the secondary outcome, or adjusted secondary analyses.

The secondary results can therefore be read as supportive descriptive context for the primary score, while keeping their evidential weight separate. They do not substitute for the primary endpoint, establish a prespecified hypothesis-testing sequence, or provide a basis for conclusions beyond the recorded score and assessment schedule.

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

• Conjunctival Hyperemia Score

9. Statistical Interpretation

10. Statistical Methods Explained

Ocular itching score is a continuous measure, so the posted arm summaries use means and standard deviations. A mean gives the average observed score in a group. A standard deviation describes how spread out individual scores are around that mean; it is not the uncertainty of the mean itself. The reported means and standard deviations are descriptive summaries of the available observations.

What does a mean difference represent?

A mean difference compares the average score in one group with the average score in another. The recalculated comparisons use vehicle as the reference. A negative difference means the active-treatment mean is lower than the vehicle mean for this outcome. Because higher itching scores indicate worse reported itching, the direction of these differences corresponds to lower average scores in the active-treatment group. This direction describes the measurement; it is not, on its own, a judgment about clinical importance.

The reported recalculated mean differences are unadjusted comparisons based on posted group summaries. They do not account for additional covariates or any trial-specific model unless that information is explicitly reported. The statistical model, any covariate adjustment, and the method for accounting for paired or repeated eye observations are not reported in the registry record. Consequently, these recalculations should be interpreted as simple comparisons of the posted summaries rather than as a reconstruction of the sponsor’s full analysis.

How should the intervals be read?

A confidence interval expresses uncertainty around an estimated effect under the assumptions of the method used to calculate it. A narrower interval indicates greater precision on that scale than a wider interval. If an interval includes zero for a mean difference, the data are compatible with no difference under the interval method; if it excludes zero, the interval is inconsistent with a zero difference under that method. The interval confidence level and the precise calculation method are not reported in the registry record, so the bounds should be read as posted without assigning an unreported level.

For the primary comparisons, the posted intervals lie below zero, in the direction of lower mean scores relative to vehicle. Their width conveys the uncertainty represented by those recalculations, but does not capture all possible sources of uncertainty, such as missing-data assumptions or a model that may have accounted for correlations between eyes or repeated days. Those elements are not reported in the registry record.

What does an unadjusted p-value say?

A p-value describes how unusual the observed data, or data more extreme, would be under a specified null hypothesis and statistical model. It is not the probability that the null hypothesis is true, and it does not measure the magnitude or importance of an effect. The primary comparisons have unadjusted p-values of < 0.001. The registry record does not report a multiplicity procedure for the several outcomes and treatment comparisons, so the p-values do not reflect a reported correction for examining multiple questions.

The trial’s statistical test and its assumptions are not reported in the registry record. The recalculated p-values should therefore be understood as unadjusted calculations associated with the posted summary-statistic comparisons, rather than as confirmation of the original analysis method. In particular, readers should not infer a sponsor-prespecified test from the presence of a p-value.

Why can over-dispersion matter?

General statistical explanation: over-dispersion occurs when observations vary more than a model assumes. It is especially relevant in count or binary data models, where an underestimated amount of variation can make standard errors too small and apparent evidence too strong. The primary itching outcome is summarized as a continuous score with a standard deviation, not as a count outcome. The registry record does not report a model-based dispersion assessment. More broadly, any analysis of scores must represent their variability and the dependence structure appropriately; details of that structure are not reported.

General statistical explanation: when the same participant contributes observations at more than one time, or from more than one eye, those measurements may be correlated. Treating correlated measurements as independent can affect estimated uncertainty. The primary endpoint pools observations from Days 1 and 15 and refers to treated eyes, but the analysis method for repeated days and eyes is not reported in the registry record. No particular correction or model should be assumed.

What is and is not reported?

The registry record provides arm means and standard deviations for the primary endpoint and a secondary endpoint, along with the displayed sample counts and recalculated comparisons. It does not report the original analysis plan, the test used for the sponsor’s primary analysis, missing-data procedures, covariate adjustment, or interim analyses. The registry also does not report the original sample-size justification. These omissions limit how fully the posted results can be linked to a prespecified statistical plan.

General statistical explanation: an analysis population defines which observations enter an analysis. The stated primary population is the Intent-to-Treat Population, described as all randomized participants with treated-eye data available for analysis. That wording does not mean that every randomized participant necessarily contributed data to every summary. The registry record does not say how unavailable data were handled, nor does it detail any exclusions beyond the stated availability condition.

11. Confidence Intervals and Precision

The recalculated primary mean difference for AGN-229666 versus vehicle is -1.15, with interval bounds of -1.35 and -0.95. For olopatadine versus vehicle, the recalculated mean difference is -1.19; its posted interval bounds are -1.388 and -0.992. Both intervals lie below zero, corresponding to lower mean itching scores in the active-treatment groups under the stated comparison direction.

An interval gives a range of effect values compatible with the data and the calculation method, rather than a guarantee that the true effect lies within the range. General statistical explanation: greater precision is associated with a narrower interval, while a wider interval reflects more uncertainty in the estimated contrast. The interval confidence level and exact calculation method are not reported in the registry record, so the bounds should not be interpreted as a particular confidence level.

The arm standard deviations indicate that individual scores varied within each group. They are not substitutes for confidence intervals, and they do not show how much uncertainty remains in a between-group contrast. The reported counts differ across the three primary endpoint arms, and the registry describes treated-eye data in the analysis population. It does not fully report whether or how the comparison calculations account for dependence between eyes or repeated days. Thus, the displayed interval precision describes the recalculated comparisons under their calculation assumptions and should not be taken to resolve uncertainty about unreported design and analysis details.

The intervals and small unadjusted p-values speak to statistical compatibility with a zero mean difference under the calculations, not to clinical importance. Clinical interpretation would require context about meaningful score changes, which is not reported in the registry record. Nor do these intervals quantify uncertainty from multiple comparisons or from any missing-data assumptions that are not described.

12. Planning a Similar Trial: Sample Size

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

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

For these continuous outcomes, the figures mean participants per arm, not total events. The 80% power column gives the number of participants per arm estimated to yield an 80% chance of detecting the specified effect under the planning assumptions, if that effect and those assumptions hold. The 90% power column has the same interpretation at a 90% chance. These are prospective planning quantities, not a measure of the probability that the trial’s observed result is correct.

Rows that plan for a smaller fraction of the observed effect require more participants per arm. This is expected: a smaller difference is harder to distinguish from ordinary variation, so a larger sample is generally needed to attain the same planned power. The displayed numbers are illustrations tied to the observed effect sizes and simplified assumptions; they should not be read as estimates of the actual design used for this trial. This is not observed power.

General statistical explanation: power is the probability that a specified statistical procedure will reject its null hypothesis when a particular effect is present, under the model and assumptions used for planning. It depends on the effect size, variability, allocation, test, and significance threshold. If those planning inputs differ from the realized study or the original protocol, the planning figure may not describe the trial’s actual operating characteristics. The registry record does not report the trial’s original sample-size calculation.

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 = -1.150; pooled standard deviation σ = 0.700.
2. n = 2 × (1.96 + 0.842)² × 0.700² / -1.150² = 5.8, rounded up to 6 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 <- -1.15                      # observed difference in means
sigma <- 0.700390548314344                     # 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(2161146)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 6 (80% power), 8 (90% power)
 75% of observed effect: n per arm = 11 (80% power), 14 (90% power)
 50% of observed effect: n per arm = 24 (80% power), 32 (90% power)
power.t.test: 6.9 
Simulated power at n = 6 per arm: 0.731 (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. Multiplicity, Missing Data and Analysis Populations

The registry record lists a primary endpoint and a secondary endpoint, and posted comparisons include two treatment groups contrasted with vehicle for each. It does not report a multiplicity adjustment, testing hierarchy, or familywise error-control strategy. The registry also does not report interim analyses or the intended significance threshold for the trial’s original analysis. These aspects of the statistical plan are not reported in the registry record.

General statistical explanation: testing multiple outcomes or contrasts without adjustment can increase the chance that at least one result appears statistically notable even when the corresponding underlying effects are absent. An adjustment or prespecified hierarchy can help manage that issue. Since no such plan is reported, the recalculated p-values should be interpreted as unadjusted and should not be treated as if they had been corrected for the full set of possible comparisons.

The primary population is described as all randomized participants with treated-eye data available for analysis. The registry record does not report how many randomized participants lacked usable endpoint data, why data may have been unavailable, or how missing observations were handled. It does not describe imputation, sensitivity analyses, or whether the analysis used all available observations in another way. The arm counts in the posted endpoint summaries should not be assumed to resolve these questions.

The registry record does not report the sponsor’s analysis records for the posted comparisons. It also does not describe an analysis model, covariate adjustment, or the statistical handling of observations from two eyes and two study days. As a result, the available recalculations cannot establish whether the original analysis accounted for correlations within a participant or followed a prespecified model.

These reporting gaps do not erase the observed arm summaries, but they limit the ability to assess the confirmatory status and robustness of the comparisons. The registry record does not report a protocol-based explanation for the analysis population, missing-data approach, multiplicity strategy, or sample-size justification.

15. Safety Results

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

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 5% reporting threshold.

Most frequent non-serious adverse event terms

The registry record lists serious adverse events for five treatment groups. No serious adverse events were reported among 47 participants at risk in the AGN-229666 group, 47 in the vehicle group, 49 in the olopatadine group, 48 in the AGN-229666/Olopatadine group, and 49 in the AGN-229666/Vehicle group. Death counts are not reported in the registry record. The serious adverse event terms list is empty.

These figures describe the recorded serious adverse event counts and their listed at-risk groups. They do not show that the groups had identical safety profiles or that an event could not occur. The registry record does not provide a comparative statistical analysis of serious adverse events, and the listed at-risk counts are not the same as the overall enrollment figure.

Other adverse events are listed separately: 4 in the AGN-229666 group, 10 in the vehicle group, 6 in the olopatadine group, 3 in the AGN-229666/Olopatadine group, and 5 in the AGN-229666/Vehicle group. Those counts are not serious adverse event counts. The registry record does not provide further detail about event severity, attribution, or statistical comparisons.

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

The posted primary endpoint data show lower mean ocular itching scores for AGN-229666 and olopatadine than for vehicle at the recorded allergen-challenge assessments pooled across Days 1 and 15. The recalculated unadjusted mean differences are negative, and the reported intervals lie below zero. The unadjusted p-values are < 0.001 for both comparisons. These statements describe the posted numerical results and their uncertainty under the recalculation assumptions.

They do not establish that either treatment is clinically important for every participant, that the effect applies beyond the study population, or that outcomes would be the same under a different assessment schedule. A score difference is a group-level average; it does not describe every individual participant’s experience. The registry record does not report a threshold for a clinically meaningful change in ocular itching score.

The comparisons also do not establish superiority between AGN-229666 and olopatadine. The posted estimates compare each with vehicle; a direct comparison between those two treatments is not reported in the registry record. Likewise, primary endpoint values for the two mixed-eye regimens are not reported in the posted results.

General statistical explanation: a small p-value and an interval excluding zero can indicate that the observed group difference is difficult to reconcile with a zero-difference hypothesis under the calculation method. They do not measure the probability that a treatment is effective, establish causality without sound design and analysis, or determine clinical relevance. Unreported features of the trial’s analysis, including multiplicity and missing-data handling, remain relevant to interpretation.

The study was conducted in Japanese patients with allergic conjunctivitis and assessed a defined score after allergen challenge. The registry record does not establish whether these findings generalize to other populations, settings, or outcomes. The appropriate interpretation stays within the measured score, listed groups, recorded timing, and posted data.

17. Why This Trial Matters Statistically

This trial illustrates why an arm mean alone is not enough to interpret a continuous clinical outcome. The mean score describes the average, while the standard deviation describes variability among observations. The between-group mean difference puts the comparison on the original score scale, and an interval conveys uncertainty around that contrast. These pieces answer different statistical questions and should be read together.

The study also highlights the importance of separating observed summaries from the original analysis plan. The registry record contains randomized and masking details, treatment schedules, endpoint definitions, and group summaries, but does not report the sponsor’s analysis records, the trial’s original sample-size justification, or a multiplicity strategy. Recalculated unadjusted comparisons can provide a transparent description of the posted summaries, but they cannot recover unreported protocol choices.

Assessment timing and pooling are important features of this endpoint. Ratings were made at different post-administration times for AGN-229666 and vehicle versus olopatadine, then pooled across Days 1 and 15. Those features define what the posted averages represent and caution against treating the scores as interchangeable measurements at one common time point.

Finally, the intervention descriptions include mixed-eye regimens, and the endpoint population refers to treated-eye data. This makes it particularly important to know how observations within participants were handled. Because that analysis detail is not reported in the registry record, readers should distinguish the arm-level summaries from assumptions about independent observations. The example underscores the value of complete reporting of populations, analysis units, missing data, and testing plans alongside numerical results.

18. 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 features limit interpretation of the posted estimates. The study concerns Japanese patients with allergic conjunctivitis, and the primary outcome was measured after allergen challenge. The registry record does not establish that the results apply to populations or settings beyond those recorded.

The primary score was assessed at different times after administration for AGN-229666 and vehicle compared with olopatadine. The results pool Days 1 and 15 and provide no day-specific estimates. This means the posted group averages summarize the specified assessment schedule; they do not reveal whether effects differed by day or assessment time.

The registry describes mixed-eye regimens as well as standalone treatment arms, but the posted primary endpoint summaries cover AGN-229666, vehicle, and olopatadine. Primary endpoint values for the mixed-eye regimens are not reported in the registry record. The stated population includes randomized participants with treated-eye data available, while the arm sample counts differ and can exceed the overall enrollment when considered across treatment summaries. The registry does not fully report the analysis unit or how within-participant eye and day correlations were addressed.

The recalculated comparisons are unadjusted. The registry record does not report the original statistical model, multiplicity handling, missing-data procedures, or the original sample-size rationale. The interval confidence level is also not reported. There is no registry-reported direct comparison between AGN-229666 and olopatadine. These limitations constrain interpretation of precision, confirmatory status, and comparisons beyond each treatment versus vehicle.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: AGN-229666 Ophthalmic Solution in Japanese Patients With Allergic Conjunctivitis — NCT02161146.
• Registry record last updated 2019-04-17; status last verified 2019-04.
• Results first posted 2016-03-07.
• 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.

22. Record Summary

NCT02161146 is a completed Phase 3, randomized, double-masked, parallel trial sponsored by Allergan. The registry record lists enrollment of 240 Japanese patients with allergic conjunctivitis. AGN-229666, vehicle, and olopatadine were administered on Days 1 and 15; two mixed-eye regimens are also described.

The primary endpoint was ocular itching score, pooled across Days 1 and 15. The posted group means were lower for AGN-229666 and olopatadine than for vehicle. Recalculated unadjusted comparisons show negative mean differences with intervals below zero and p < 0.001 for both active-treatment comparisons with vehicle. The secondary endpoint was conjunctival hyperemia score, with a broadly similar direction in the posted arm summaries.

The registry record does not report the original analysis plan, multiplicity strategy, missing-data procedures, or sample-size justification. The recalculated results describe the posted summaries and should be interpreted within those reporting limits.