AGN-229666 for the Treatment of Allergic Conjunctivitis: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for AGN-229666 for the Treatment of Allergic Conjunctivitis (NCT01754766), a randomized phase 2 study. The primary outcome is Ocular Itching Score at Day 1.

2. Clinical Question

In statistical terms, the central question is whether the average itching scores in the two AGN-229666 groups were distinguishable from the average in the vehicle group at the stated assessment time. The posted results report lower mean Day 1 scores for both dose groups than for vehicle, with unadjusted comparisons and intervals for each contrast. Those estimates describe this outcome and assessment; they do not by themselves establish a broader effect across symptoms, visits, or patients.

The record also includes ocular itching at Day 15 and conjunctival hyperemia as secondary outcomes. These can add context to the primary comparison, but they are not interchangeable with it: they represent a later itching assessment and a different clinical score. The registry record does not report a multiplicity procedure or detailed sponsor analyses for these outcomes, so the secondary comparisons should be read as exploratory evidence rather than as independent confirmation.

3. Trial Design

This was a phase 2, randomized, double-masked, parallel-group trial sponsored by Allergan. The registry record lists allergic conjunctivitis as the condition and an enrollment of 90. It lists three groups: AGN-229666 Dose A, AGN-229666 Dose B, and vehicle of AGN-229666. A parallel design assigns participants to a group and compares outcomes between groups; the record does not describe a crossover between treatments.

Each treatment description specifies one drop into each eye on Day 1 and Day 15. The primary outcome was ocular itching score on Day 1, and secondary outcomes were ocular itching score at Day 15 and conjunctival hyperemia score. The primary analysis population is described as the Modified Intent-to-treat population: randomized participants with ocular itching score data available for the relevant time point. The posted outcome counts are 31 for Dose A, 29 for Dose B, and 30 for vehicle on the primary outcome. These are outcome-specific counts; the registry record does not explain missing outcome data or how any missing values were handled.

Randomization is intended, in general, to reduce systematic differences between comparison groups, while masking is intended to limit influences from knowing the assigned group. The registry record identifies the trial as randomized and double-masked but does not report the randomization method, who was masked, how allocation was concealed, or whether masking was assessed. It identifies the study as completed, with enrollment and study timing recorded, but does not provide additional detail about recruitment, follow-up, or protocol implementation in the information available in the registry record.

The registry record does not report the original sample-size justification, a planned statistical analysis protocol, or interim analyses. The planning illustrations associated with the posted estimates are separate from the trial’s original design assumptions.

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: Modified Intent-to-treat (MITT) population included all randomized participants with ocular itching score data available for this time point

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 at Day 1, measured over Day 1.

The primary endpoint is the mean ocular itching score at Day 1. Participants evaluated itching in both eyes five minutes after conjunctival allergen challenge, which was eight hours after dosing. The score for each participant was the average of the scores from both eyes.

The scale has nine points in half-unit increments, ranging from 0, meaning no itching, to 4, meaning incapacitating itch with an irresistible urge to rub. This is a continuous score in the posted analysis, summarized with a mean and standard deviation. The outcome captures the reported intensity of itching at a defined assessment following the challenge; lower mean scores indicate less reported itching on this scale at that assessment. That description is about how to interpret the measure, not a claim about the clinical importance of any particular difference.

Using a defined scale and assessment time gives the groups a common outcome for comparison. Averaging both eyes produces one participant-level score for the analysis rather than treating each eye as a separate participant. The registry record identifies the relevant population as randomized participants with available ocular itching data at the time point. It does not report further detail about how the scale was validated, a threshold for a clinically meaningful change, or how the Day 1 assessment was selected as the primary endpoint.

7. Results Posted in the Registry

• AGN-229666 Dose A: mean 0.50 versus 1.87 on control; difference -1.37 (95% CI -1.75 to -0.98), standardized effect d = -1.80; z-test p = <0.001.
• AGN-229666 Dose B: mean 0.32 versus 1.87 on control; difference -1.55 (95% CI -1.92 to -1.18), standardized effect d = -2.12; 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.

Ocular Itching Score at Day 15

• 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 Dose A: mean 0.36 versus 1.26 on control; difference -0.90 (95% CI -1.26 to -0.54), standardized effect d = -1.26; z-test p = <0.001.
  • AGN-229666 Dose B: mean 0.21 versus 1.26 on control; difference -1.04 (95% CI -1.40 to -0.69), standardized effect d = -1.47; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for AGN-229666 Dose A 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 AGN-229666 Dose B than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

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 Dose A: mean 1.39 versus 1.63 on control; difference -0.25 (95% CI -0.55 to 0.06), standardized effect d = -0.41; z-test p = 0.112.
  • AGN-229666 Dose B: mean 1.34 versus 1.63 on control; difference -0.29 (95% CI -0.73 to 0.15), standardized effect d = -0.34; z-test p = 0.198.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between AGN-229666 Dose A 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 AGN-229666 Dose B and the control. The interval gives the range of effects that remain compatible with the data.

Across the secondary endpoints, the broad pattern is that the itching comparisons favor lower mean scores in the AGN-229666 groups relative to vehicle, while the conjunctival hyperemia comparisons are less conclusive. This pattern is directionally consistent with the primary itching result, particularly because the later itching outcome measures the same symptom at a different assessment. It is not a direct replication of the primary endpoint: Day 15 is a separate time point, and conjunctival hyperemia measures a different feature.

Secondary outcomes can help show whether a primary-outcome pattern is accompanied by related observations, but they generally carry less confirmatory weight when the testing plan and multiplicity handling are unknown. Testing several outcomes and group comparisons creates more opportunities for apparently notable results to occur by chance. In general, multiplicity procedures manage that issue by adjusting interpretation or testing thresholds across a family of comparisons. The registry record does not report whether such a procedure was used.

The record lists two secondary outcomes and no reported analyses. The displayed unadjusted comparisons therefore provide descriptive evidence, but the registry record does not establish whether these outcomes were prespecified in a hierarchy, how they were analyzed by the sponsor, or whether any broader set of outcomes was considered. In addition, the secondary outcomes have their own available-score counts and uncertainty. They should be interpreted in their own measurement context rather than pooled into a single judgment about treatment effect.

The relationship to the primary result is therefore supportive in direction for itching but not sufficient by itself to establish consistency across all measures. A difference on itching does not imply a corresponding difference on hyperemia, and a less conclusive hyperemia comparison does not negate the posted itching contrasts. The secondary evidence is best viewed as context for the primary finding, with uncertainty about multiplicity, missing data, and analysis planning limiting confirmatory claims.

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

• Ocular Itching Score at Day 15
• Conjunctival Hyperemia Score

9. Statistical Interpretation

10. Statistical Methods Explained

Comparing group means

The primary outcome is continuous: each participant contributes a numerical itching score, and the posted group summaries are means and standard deviations. A mean difference compares the average score in one dose group with the average in the vehicle group. The contrast is expressed as treatment group minus vehicle group, so a negative estimate means the treatment-group mean is lower. For Dose A, the estimate is -1.367; for Dose B, it is -1.548. These are unadjusted contrasts calculated from the posted summary statistics, rather than adjusted estimates from a model described in the registry record.

In general, a mean difference keeps the result in the original measurement scale, which makes it possible to relate the contrast to the score’s range and meaning. A standardized effect such as Cohen’s d instead expresses the contrast relative to a pooled standard deviation. It can help compare effects measured on different scales, but it is less directly interpretable in the original score units. The posted standardized estimates are -1.802 for Dose A and -2.118 for Dose B on the primary outcome. They do not replace the original-scale mean differences and do not independently show clinical importance.

Variation and standard errors

A standard deviation describes the spread of individual scores around a group mean. It is not the same as the standard error, which describes the sampling uncertainty of an estimated mean. In general, standard errors depend on both variability and the amount of information in the group; they are used in constructing intervals and test statistics. The registry record reports group standard deviations and comparison standard errors, but does not describe a sponsor analysis model. The recalculations use the posted summary statistics and should be interpreted as unadjusted.

Intervals and p-values

In general, an interval estimate gives a range of values reasonably compatible with the data under the method used, and its width conveys precision. The reported primary intervals are -1.751 to -0.983 for Dose A and -1.917 to -1.179 for Dose B. Both are entirely negative. The confidence level and the interval-construction procedure are not reported in the registry record, so they should not be inferred from the values alone.

A p-value measures how unusual data at least as inconsistent with a specified null hypothesis would be if that null hypothesis and the test assumptions held. It is not the probability that the null hypothesis is true, nor a measure of the size or importance of a difference. The primary comparisons have unadjusted p-values below 0.001. The registry record does not describe a statistical testing plan, adjustment for multiple comparisons, or sponsor-reported analyses. The posted p-values therefore should not be read as accounting for all possible testing across endpoints and dose groups.

Why distribution and design matter

General statistical methods for comparing means often rely on assumptions about the data or the sampling distribution of the estimates. These can include independent observations and an adequate approximation for the distribution of the mean difference. The record identifies a randomized parallel design and a score averaged across both eyes for each participant, but does not describe diagnostics, transformations, model choices, or sensitivity analyses. The posted simple comparisons do not establish that any particular assumption was checked.

Because the score is bounded and uses half-unit steps, the possible values are not unrestricted continuous measurements. That does not make a mean comparison inherently invalid, but it makes it useful to consider whether the mean and standard deviation adequately summarize the distribution. The registry record does not provide participant-level distributions, medians, or other summaries that would permit a fuller assessment. Nor does it describe whether score distributions differed in shape between groups.

Analysis population and missing observations

The primary endpoint description names a Modified Intent-to-treat population, defined as all randomized participants with ocular itching score data available at that time point. This is not the same description as a complete intention-to-treat analysis that necessarily retains every randomized participant regardless of outcome availability. The outcome counts are 31, 29, and 30 across Dose A, Dose B, and vehicle. For Day 15, the posted counts are 30, 28, and 30. The registry record does not explain the differences in available counts, the amount or reasons for missingness, or any imputation or other missing-data approach.

In general, missing data can affect a comparison if the availability of scores is related to participants’ outcomes or treatment group. The direction and size of any such effect cannot be determined from group means and counts alone. Without reported missingness reasons and sensitivity analyses, the posted complete-score summaries are best interpreted as descriptions of the participants contributing data at the stated assessments.

Planning illustrations

The sample-size illustrations use a two-sided significance level of 0.05, equal allocation between the two compared arms, and a normal approximation. They consider effects set at a stated fraction of the observed effect. These are planning calculations based on the posted estimates, not the trial’s original design calculation. General planning logic is that a smaller target effect requires more participants to distinguish it from no difference with a chosen probability under the assumptions. These illustrations do not establish how the trial was planned or what probability of detecting an effect the completed trial had.

The registry record does not report the sponsor’s statistical analysis plan, the method used for any original trial planning, interim analyses, or adjusted analyses. Therefore, these explanations distinguish the posted numerical summaries and simple recalculations from analyses that cannot be attributed to the sponsor on the basis of the registry record.

11. Confidence Intervals and Precision

The primary comparison estimates are accompanied by reported intervals: -1.751 to -0.983 for Dose A versus vehicle, and -1.917 to -1.179 for Dose B versus vehicle. Each interval is entirely below zero, consistent with the negative mean differences and lower treatment-group means. The intervals also convey a range of uncertainty around each estimated contrast; their widths show that the point estimates should not be treated as exact values.

The confidence level and construction method for these intervals are not reported in the registry record. They should therefore be read as the reported comparison intervals, without assigning a confidence percentage or assuming a particular model. In general, an interval’s interpretation depends on its statistical method and assumptions, not only on its endpoints.

The posted primary group means and standard deviations add context about the data’s spread, but they are not substitutes for intervals on the treatment contrasts. The vehicle group’s standard deviation is 0.949, compared with 0.512 for Dose A and 0.395 for Dose B. Group variability and the available number of scores both contribute to the precision of estimates; neither the mean nor the p-value alone communicates all of that uncertainty.

For the secondary outcomes, the Day 15 itching comparison intervals are also wholly negative, while the conjunctival hyperemia intervals extend across zero. An interval crossing zero is compatible with values on either side of no mean difference under the interval method. It does not establish equivalence or show that all meaningful differences have been excluded. The record does not report a prespecified equivalence margin or a clinically meaningful threshold for these scales.

Thus, precision should be judged from the estimates and their intervals together, while keeping in mind the unreported interval procedure, the available-case population, and the lack of reported adjustment for multiple comparisons.

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 for 80% power and participants per arm for 90% power. They are not total events: the registry record’s planning assumptions specify participants per arm for these continuous outcomes. The illustrations assume a two-sided significance level of 0.05, equal allocation between the two compared arms, and a normal approximation. Each row considers detecting a stated fraction of the observed effect: the full observed effect, 75% of the observed effect, or 50% of the observed effect.

In plain language, the 80% power column gives the planning number per arm under which the calculation would have an 80% chance of detecting the target difference if the assumptions and target effect were correct. The 90% column describes a higher target chance of detection under the same type of assumptions. These are planning probabilities, not guarantees for a future study. The registry record does not report the original trial’s sample-size justification or its own design assumptions.

For both primary comparisons, the figures rise as the target effect is reduced from the full observed effect to 75% and then 50%. This reflects general planning logic: smaller effects are harder to distinguish from no difference, so more participants are needed to achieve the same target power. The illustrations use the observed estimates as their starting point, so their values depend on estimates from this trial and should not be treated as universal requirements.

This is not observed power. The figures are planning illustrations based on the posted effects and stated assumptions, not a retrospective measure of whether the completed trial had adequate power.

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 = -1.367; pooled standard deviation σ = 0.759.
2. n = 2 × (1.96 + 0.842)² × 0.759² / -1.367² = 4.8, rounded up to 5 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 <- -1.367                      # observed difference in means
sigma <- 0.758717181737969                     # 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(1754766)
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 = 5 (80% power), 7 (90% power)
 75% of observed effect: n per arm = 9 (80% power), 12 (90% power)
 50% of observed effect: n per arm = 20 (80% power), 26 (90% power)
power.t.test: 6 
Simulated power at n = 5 per arm: 0.707 (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 three outcome measures, including the primary Day 1 ocular itching score and two secondary outcomes. It reports no sponsor analyses and does not describe a statistical analysis plan, a testing hierarchy, or an adjustment for multiple comparisons. The posted comparisons include two dose-versus-vehicle contrasts for each outcome. Because several comparisons are present, interpreting each unadjusted p-value as though it were the only test could overstate the strength of evidence. In general, multiplicity methods address the increased chance of false-positive findings when multiple hypotheses are tested. Whether any such method was used is not reported in the registry record.

The primary endpoint population is described as randomized participants with available itching data for the time point. This definition makes outcome availability part of inclusion in the primary analysis. The posted counts differ by outcome: the primary assessment has 31, 29, and 30; Day 15 has 30, 28, and 30; the hyperemia outcome has 31, 29, and 30. The registry record does not report why scores were unavailable, whether missingness was related to treatment or outcome, or how missing data were handled.

In general, complete-case summaries can be biased if the participants with observed outcomes differ systematically from those without them. That possibility cannot be evaluated from the posted group summaries alone. The registry record does not report imputation, sensitivity analyses, or an analysis retaining all randomized participants regardless of outcome availability. It also does not report protocol deviations or the details of any per-protocol analysis.

The posted results should consequently be understood as comparisons among participants with score data available for each stated outcome, with the precise missing-data process and multiplicity strategy unknown. These omissions do not change the arithmetic of the posted contrasts, but they limit how confidently the comparisons can be treated as planned, confirmatory tests.

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 serious adverse event figures report zero affected participants in each group: Dose A has 0 among 31 at risk, Dose B has 0 among 29 at risk, and vehicle has 0 among 30 at risk. These are counts of affected participants as represented in the registry record, not evidence that no event could occur in a larger population or under different circumstances. The registry record lists no serious adverse event terms.

The separate other-adverse-event figures show 0 affected in Dose A, 2 in Dose B, and 0 in vehicle, with the same group-specific at-risk counts recorded for those figures. These counts are descriptive; the record does not provide event types, severity, attribution, or a comparative safety analysis in the information. Death counts are not reported in the registry record.

Zero recorded serious events in these groups should be read narrowly as the posted observation for this trial, not as proof of absence of risk. The registry record does not provide additional detail on adverse-event collection or follow-up that would support broader safety conclusions.

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

The posted results show lower mean ocular itching scores on Day 1 in both AGN-229666 groups than in the vehicle group. The two unadjusted primary mean differences are negative, their reported intervals lie below zero, and their p-values are below 0.001. This describes the observed comparison for the specified score, population, and assessment. It does not by itself establish how participants would fare in other settings, at other times, or on outcomes not measured in this trial.

A statistical difference is not automatically a clinically important difference. The registry record does not report a threshold for a meaningful change in ocular itching, and the numerical results alone do not establish how participants experienced the differences. The score’s definition explains its direction and range, but it does not supply a threshold for interpreting importance. The comparisons also do not establish a mechanism or explain why group means differed.

The findings do not establish that every participant experienced lower itching, because group means summarize variation across participants. Nor do they establish that one dose is superior to the other: the posted comparisons are each against vehicle, and the registry record does not report a direct comparison between the two doses. A numerical difference between the two dose-group means is not a substitute for a prespecified direct test.

Secondary results add context but do not resolve these limits. The itching pattern at Day 15 is directionally similar to the primary result, while the hyperemia comparisons are less conclusive. The record does not report multiplicity handling, the original analysis plan, or missing-data sensitivity analyses, so secondary p-values should not be taken as independent confirmation.

The serious adverse event counts are zero in all groups in the posted record, while the non-serious adverse event counts are not uniformly zero. These small-group counts cannot establish absence of risk. Overall, the registry record describes a favorable numerical pattern for the primary itching comparisons, but important aspects of clinical importance, robustness, and broader applicability are not reported.

17. Why This Trial Matters Statistically

This trial is statistically informative because it places two dose groups alongside a vehicle comparator and posts means, standard deviations, mean differences, intervals, and unadjusted p-values for a defined continuous symptom score. Readers can distinguish the size and direction of the estimated group contrasts from their uncertainty, rather than relying on a p-value alone. The score is also described in enough detail to understand what was assessed and when.

The record illustrates why endpoint-specific interpretation matters. The primary result concerns itching after conjunctival allergen challenge on Day 1. The later itching outcome and the hyperemia outcome do not measure the same thing at the same time, so their evidence cannot simply be combined. Their varying patterns also show why a single overall claim should not be inferred from a set of separate comparisons.

It also highlights the difference between trial results and planning calculations. The per-arm sample-size illustrations are derived from observed effects under explicit assumptions; they are not the trial’s original design rationale and are not observed power. Keeping those purposes separate avoids treating a retrospective calculation as evidence that the original trial was adequately planned.

Finally, the registry record leaves several important statistical details unavailable: the original analysis plan, multiplicity handling, the interval method, and missing-data methods. The posted summaries support a clear description of the observed comparisons, but the absence of those details limits assessment of whether the reported tests match a prespecified confirmatory strategy. This distinction between what the estimates show and what the record does not document is central to a careful reading.

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 limitations affect interpretation. The registry record gives group means and standard deviations but not participant-level data or fuller distribution summaries. Because the itching scale is bounded and uses half-unit increments, the means alone do not show how scores were distributed, whether there were floor effects, or whether the group distributions differed in shape. The record does not report diagnostic checks or alternative analyses.

The analysis population is defined by having an available score at the relevant time point. The posted counts vary by outcome, but reasons for missing scores and methods for handling missingness are not reported in the registry record. Without that information, it is not possible to assess whether the available observations represent the randomized groups equally well.

The registry record also does not report the original statistical analysis plan, the interval confidence level or construction method, multiplicity procedures, or interim analyses. It lists no sponsor-reported analyses, so the posted contrasts should be understood as unadjusted calculations from the available summary statistics rather than as documented sponsor model results. No direct Dose A versus Dose B comparison is reported.

Finally, the record does not provide a clinically meaningful threshold for the itching or hyperemia scales, detailed adverse-event terms, or death counts. These omissions limit conclusions about clinical importance and safety. They do not invalidate the arithmetic of the posted summaries, but they restrict how far those summaries can be generalized or used to support broader claims.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: AGN-229666 for the Treatment of Allergic Conjunctivitis — NCT01754766.
• Registry record last updated 2014-02-04; status last verified 2013-12.
• Results first posted 2014-02-04.
• 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

The registry record describes a completed randomized, double-masked, parallel phase 2 trial of AGN-229666 for allergic conjunctivitis, sponsored by Allergan, with enrollment of 90. The three groups were AGN-229666 Dose A, AGN-229666 Dose B, and vehicle. Each was administered as one drop into each eye on Day 1 and Day 15.

The primary outcome was mean ocular itching score on Day 1 after conjunctival allergen challenge. The posted means were lower in both dose groups than in the vehicle group, with unadjusted mean differences of -1.367 and -1.548 and p-values below 0.001. Secondary outcomes were ocular itching at Day 15 and conjunctival hyperemia score. The record does not report sponsor analyses, multiplicity handling, or missing-data methods.

Serious adverse event counts were zero in each group; other adverse event counts were 0, 2, and 0. Death counts are not reported in the registry record.