A Study to Evaluate the Safety of Combination Montelukast/Loratadine in Mexican Participants With Allergic Rhinitis (MK-0476A-484): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study to Evaluate the Safety of Combination Montelukast/Loratadine in Mexican Participants With Allergic Rhinitis (MK-0476A-484) (NCT01673620), a randomized phase 3 study. The primary outcome is Number of Participants Experiencing at Least One Adverse Event (AE).

2. Clinical Question

3. Trial Design

This was a Phase 3, randomized, double-blind, parallel-group, placebo-controlled study of combination montelukast 10 mg/loratadine 10 mg in Mexican participants with allergic rhinitis. The registry record identifies Organon and Co as the sponsor and lists the study status as completed. The recorded start date is 2012-07-04, and the primary completion date is 2012-10-10.

The active-treatment arm received the combination tablet orally once daily for 2 weeks. The control arm received a matching placebo tablet on the same schedule. Double blinding means that the study was described as masking participants and relevant study personnel to assigned treatment, but details of how masking was maintained or assessed are not reported in the registry record. Likewise, the method used to generate the random allocation sequence and the process for concealing assignments are not reported in the registry record.

The posted arm counts are 47 for combination treatment and 22 for placebo, within the overall enrollment of 69. Those counts describe the posted results and do not explain why the arm sizes differ. The primary endpoint population was defined as randomized participants who received at least one dose of study drug. The primary adverse-event timeframe was up to 4 weeks, while the assigned treatment course was 2 weeks.

The registry record lists 2 outcome measures and 0 analyses. It does not report the original sample-size justification, the planned statistical analysis methods, or whether interim analyses were planned or conducted. The posted comparison and its planning illustrations should therefore be read as registry-reported statistical information, not as a complete account of the trial's original 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: The All-Patients-as-Treated (APaT) population consisted of all randomized participants who received at least one dose of study drug.

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 Number of Participants Experiencing at Least One Adverse Event (AE), measured over Up to 4 weeks.

The primary endpoint was the number of participants experiencing at least one adverse event, with the outcome expressed as a participant count. The registry definition includes any unfavorable and unintended change in body structure, function, or chemistry that was temporally associated with study treatment, whether or not it was considered related to treatment. The timeframe was up to 4 weeks. This is an occurrence endpoint: a participant is counted if at least one qualifying event occurred, rather than being counted separately for every event.

Safety studies use adverse-event endpoints to describe the kinds of unwanted health events reported during or after exposure to an intervention. Counting participants with at least one event offers a participant-level summary, but it does not describe event severity, duration, recurrence, or the total number of events. Those details require separate outcome measures or event listings. The registry record also distinguishes serious events from other adverse events in its safety information.

The endpoint is not a direct measure of symptom relief or comparative efficacy. Its definition also does not mean that every counted event was caused by study treatment: the definition explicitly allows events whether or not considered related. The posted primary counts are 6 participants in the combination arm and 2 in the placebo arm. The result is limited to the recorded population, treatment course, endpoint definition, and follow-up timeframe; the registry record does not report additional detail about how adverse events were collected or adjudicated.

7. Results Posted in the Registry

• Montelukast 10 mg/Loratadine 10 mg: 12.8% (6/47) versus 9.1% (2/22) on control; risk difference 3.7 percentage points (95% CI -11.7 to 19.0), risk ratio 1.40 (0.31–6.41); unadjusted two-proportion z-test p = 0.657.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is binary at the participant level: each participant either experienced at least one adverse event during the stated timeframe or did not. A count of participants with an event is different from a total event count. One participant with several events still contributes as one participant to this particular endpoint. The posted comparison turns the arm-level counts into proportions and then expresses the arm contrast as a risk difference, with the combination-treatment arm compared against placebo.

What does a risk difference describe?

In general, a risk difference subtracts the event proportion in one group from the event proportion in the comparison group, using a stated direction. It is an absolute measure on the probability scale. Here, the reported risk difference is 0.037, where a positive value corresponds to a higher observed event proportion in the combination arm under the comparison's direction. The registry also reports the underlying proportions as 0.128 for combination treatment and 0.091 for placebo. Those values and the risk difference are reported estimates; they are not proof that the treatment caused a change.

How do relative measures differ?

In general, a risk ratio compares the event probabilities by division, whereas an odds ratio compares the odds of an event. Both describe relative rather than absolute contrast, and their numerical values need not match. The reported risk ratio is 1.404, with a confidence interval from 0.308 to 6.408. The reported odds ratio is 1.463, with a confidence interval from 0.271 to 7.909. Because these intervals include the value corresponding to no relative difference, they do not pinpoint a clear direction or magnitude of association. These are different summaries of the same posted outcome, not separate trials or separate evidence sources.

What does the p-value add?

In general, a p-value measures how unusual data at least as incompatible with a specified null model would be, assuming that model and the analysis conditions hold. It is not the probability that the null hypothesis is true, and it does not measure the probability that chance alone caused the observed result. The reported unadjusted p-value is 0.657. This value does not provide evidence of a clear departure from a no-difference model under the calculation used, but it does not demonstrate equality of the groups. Interpretation also depends on the estimate, interval, outcome definition, and trial context.

The registry record reports 0 analyses, while a comparison is posted. The method used for the sponsor's original analysis is not reported in the registry record. The posted comparison is an unadjusted recalculation from the recorded summary statistics, and no discrepancy is flagged. It should not be mistaken for a fully described prespecified model: adjustment variables, any stratification, and the original analysis specification are not reported in the registry record.

Why does the event count matter for precision?

General statistical reasoning: estimates based on few observed events can change substantially when the event count changes, so their uncertainty can be considerable. A confidence interval communicates a range of values compatible with the data and calculation method; a broad interval indicates that the estimate is not tightly determined. In this trial, the arm counts are 6 and 2, and the reported intervals for the risk difference, risk ratio, and odds ratio are broad. The data therefore support a less precise comparison than a larger body of event information might support.

What is over-dispersion?

General concept: over-dispersion arises when outcome variability is greater than a statistical model assumes. It can make standard errors too small if the model does not account for that extra variability. The primary endpoint is a participant-level binary outcome, and the registry record does not report an over-dispersion assessment or a model that requires such an assessment. No claim about over-dispersion in this trial can be made from the posted record.

What is not established by these methods?

Randomization supports a planned comparison of assigned groups, but the registry record does not describe the allocation procedure, outcome missingness, or adherence beyond the arm descriptions. Blinding is reported, but implementation details are not. The primary population includes randomized participants who received at least one dose, rather than all randomized participants regardless of dosing. The record does not report how this population was applied to every analysis or how missing outcomes were handled. These omissions limit assessment of the analysis process; they do not justify filling in unreported methods by assumption.

10. Confidence Intervals and Precision

A confidence interval describes statistical uncertainty around an estimate under the method used to calculate it. It is not a guarantee that the true value lies within the interval, nor does it express the probability that a particular treatment effect is true. Its width is useful for judging how precisely the data locate the estimate: a narrower interval indicates greater precision, while a wider interval leaves more plausible values compatible with the data.

The risk difference is 0.037, with a confidence interval from -0.117 to 0.190. This interval extends across zero and includes both negative and positive values. In the comparison's direction, zero corresponds to no risk difference. The estimate therefore does not precisely determine whether the event proportion was lower or higher in the combination arm, or by how much. This uncertainty is important even though the point estimate itself is positive.

The relative-effect intervals are also wide: 0.308 to 6.408 for the risk ratio and 0.271 to 7.909 for the odds ratio. Each includes the value corresponding to no relative difference. The posted counts—6 participants with an event in the combination arm and 2 in placebo—are limited, and the small number of events is consistent with substantial uncertainty. The confidence intervals, rather than the point estimates alone, show how much the comparison remains unresolved.

The reported p-value of 0.657 is not a measure of precision and should not replace the interval. Nor does an interval spanning the no-difference value prove that the groups are equivalent. The registry record does not report a prespecified equivalence or noninferiority margin. The result is best read as an imprecise estimate of the observed safety contrast over the reported timeframe, rather than as a precise estimate of a stable underlying difference.

11. 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 estimates are expressed as participants per arm for 80% power and participants per arm for 90% power. They are not total events. The calculation uses the observed effect as its reference and illustrates planning for 100%, 75%, and 50% of that observed effect. For the 100% effect illustration, the estimates are 1,131 participants per arm for 80% power and 1,513 participants per arm for 90% power. For planning for 75% of the observed effect, they are 1,936 participants per arm for 80% power and 2,591 participants per arm for 90% power. For planning for 50% of the observed effect, they are 4,187 participants per arm for 80% power and 5,605 participants per arm for 90% power.

In general, power is the probability that a study will meet its statistical decision criterion if a specified effect is truly present and the assumptions used for planning hold. The 80% and 90% columns represent different target probabilities under the planning model; the higher target generally calls for a larger planned sample. The calculations assume a two-sided significance level of 0.05, equal allocation between arms, and a normal approximation. Smaller effects need more participants because they are harder to distinguish from random variation.

These are planning illustrations based on the observed effect, not observed power and not evidence about the study's original design. The trial's own design assumptions and original sample-size justification are not reported in the registry record. The displayed calculations therefore cannot establish what sample size the investigators originally intended or whether the completed enrollment met their original plan.

12. 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, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.091; treatment proportion p₁ = 0.128; average p̄ = 0.109.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.4412 = 0.8648.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.4405 = 0.3707.
4. n = (0.8648 + 0.3707)² / (0.0368)² = 1,130.2, rounded up to 1,131 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
p0 <- 0.0909090909090909                          # control proportion
p1 <- 0.127659574468085                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^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 (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(1673620)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 1,131 (80% power), 1,513 (90% power)
 75% of observed effect: n per arm = 1,936 (80% power), 2,591 (90% power)
 50% of observed effect: n per arm = 4,187 (80% power), 5,605 (90% power)
power.prop.test: 1130.2 
Simulated power at n = 1,131 per arm: 0.800 (20000 replicates)

The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-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.

13. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when a study makes several statistical comparisons or evaluates several outcomes: the chance of at least one apparently notable result can increase as the number of tests grows. General approaches include prespecifying a primary outcome, adjusting decision thresholds, or defining a testing sequence. The registry record lists 2 outcome measures but posts 0 secondary results. It does not report a multiplicity strategy, whether any adjustment was planned, or how the two outcome measures were related in the analysis plan. No claim about multiplicity control can therefore be made.

The record identifies the primary endpoint population as All-Patients-as-Treated: randomized participants who received at least one dose of study drug. That definition describes the population for the endpoint, but the registry record does not report details about exclusions from that population, adherence handling, or how participants with incomplete outcome information were treated. A missing-data method is not reported in the registry record. It is therefore not possible to determine from the posted information whether missing outcomes were absent, how common they were, or whether any imputation or sensitivity analysis was used.

The registry lists 0 analyses, and a detailed statistical analysis plan is not reported in the registry record. Information about adjustment for baseline characteristics, prespecified subgroup analyses, and any interim analyses is also not reported in the registry record. These omissions matter because analysis choices can affect uncertainty estimates and the interpretation of a comparison. They do not establish that an unreported method was or was not used; they mean that the method cannot be verified from the registry record.

The primary comparison is unadjusted. The p-value is reported as unadjusted, and no correction for multiple testing is stated. The result should therefore be interpreted as the posted comparison for the primary adverse-event endpoint, without assuming that it accounts for other outcomes or analyses. Since no secondary results are posted, consistency across endpoints cannot be assessed.

14. 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 information lists 0 related serious adverse events among 47 participants at risk in the combination arm and 0 among 22 at risk in the placebo arm. The separate figures for other adverse events assessed as related are 3 among 47 in the combination arm and 0 among 22 in placebo. These categories should not be conflated: the serious-event figures are distinct from the other adverse-event figures.

The reported related-event counts do not describe every adverse event regardless of relationship, and a count of participants affected is not necessarily the same as a count of all individual events. The registry record does not provide serious-event terms in its listed serious-event summary. Deaths are not reported in the registry record. These entries should not be interpreted as a complete narrative of all safety events or as proof that no unlisted events occurred.

As with the primary endpoint, attribution is important. An adverse event can occur during a study without being considered caused by treatment. The posted related-event figures specifically concern events assessed as related; they do not replace the broader primary endpoint, which counts participants experiencing at least one adverse event whether or not considered related. The arm sizes and event counts are limited, so these figures are descriptive and do not establish a comparative safety profile beyond the recorded information.

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

The primary result describes the number of participants with at least one adverse event during a timeframe of up to 4 weeks: 6 in the combination-treatment arm and 2 in the placebo arm. The reported proportions are 0.128 and 0.091, and the estimated risk difference is 0.037 in the direction of a higher observed proportion with combination treatment. The confidence interval for that difference, -0.117 to 0.190, includes values on either side of no difference. The comparison is therefore uncertain and imprecise.

These findings do not establish that the combination caused more adverse events, and they do not establish that the two groups had equivalent event risks. The reported unadjusted p-value of 0.657 does not resolve that uncertainty. The point estimate, confidence interval, and small event counts should be considered together rather than treating any one statistic as a definitive conclusion.

The result also does not answer whether the combination improves allergic rhinitis symptoms or has a particular effect on other outcomes. The stated purpose was to assess safety and tolerability, and the primary endpoint counts participants with at least one adverse event. The record does not post secondary results. Nor does the primary count capture every detail relevant to safety, such as event severity, timing, duration, recurrence, or whether each event was judged related to treatment.

The evidence applies to the registry-described study population and regimen: Mexican participants with allergic rhinitis, an oral once-daily combination tablet for 2 weeks, and a placebo comparator. The endpoint timeframe was up to 4 weeks. The trial's total enrollment was 69, with 47 participants in the combination arm and 22 in placebo. The registry record does not support extending the estimate beyond this study's recorded population, treatment course, and follow-up information.

16. Why This Trial Matters Statistically

This trial is statistically instructive because it separates an observed point estimate from the precision of that estimate. The combination arm had 6 participants with at least one adverse event, compared with 2 in the placebo arm, and the estimated risk difference is positive. Yet the risk-difference interval extends from -0.117 to 0.190. The point estimate alone gives an incomplete account: the interval shows that the direction and magnitude of the underlying contrast remain uncertain.

The example also illustrates why a nonsignificant result is not the same as evidence of no difference. The unadjusted p-value is 0.657, while the confidence interval includes values on both sides of zero. These results do not demonstrate equivalence. Establishing equivalence would require an appropriate prespecified margin and design, neither of which is reported in the registry record.

Rare or infrequent outcomes can be difficult to compare precisely when few participants experience them. Here, the total enrollment was 69 and the primary event counts were limited. The relative-effect intervals are correspondingly broad. This makes it useful to consider absolute and relative summaries together, while recognizing that they are different ways of describing the same observed data.

The record also demonstrates the importance of transparent methods reporting. It identifies the endpoint population and definition, but does not report the original sample-size rationale, detailed analysis plan, missing-data handling, or multiplicity approach. Planning illustrations can clarify how target power and effect assumptions relate to sample size, but they do not reconstruct the study's original design assumptions. Clear distinctions among observed counts, recalculated comparisons, and planning scenarios help prevent overinterpretation.

17. 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 limitation for interpreting this particular result is the limited amount of event information: the posted counts are 6 participants in the combination arm and 2 in placebo, with 69 participants enrolled overall. The comparison is imprecise, as reflected by the confidence interval for the risk difference from -0.117 to 0.190 and the wide intervals for the relative measures. The observed point estimate should not be treated as a stable or definitive estimate of the underlying contrast.

The arm sizes differ: 47 participants are listed for combination treatment and 22 for placebo. The registry record does not explain the difference, so its cause should not be inferred. Randomization is reported, but the method of sequence generation and allocation concealment is not reported in the registry record. The double-blind designation is reported, but details about implementation and assessment of blinding are not.

The treatment schedule was 2 weeks, and the primary endpoint timeframe was up to 4 weeks. Those durations limit the scope of the result; the record does not provide longer-term safety information. The primary endpoint counts participants with at least one event, without reporting the event's severity, duration, recurrence, or individual timing in the outcome summary. The registry's safety summary also does not report deaths, and it lists no serious-event terms.

The original sample-size justification, detailed analysis plan, missing-data methods, and multiplicity approach are not reported in the registry record. There are 0 posted secondary results. Consequently, the posted primary comparison cannot be checked against a complete prespecified analysis plan or compared with a set of posted secondary findings. These limitations describe gaps in the registry record and the scope of the available results; they do not establish what may have been documented elsewhere.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: A Study to Evaluate the Safety of Combination Montelukast/Loratadine in Mexican Participants With Allergic Rhinitis (MK-0476A-484) — NCT01673620.
• Registry record last updated 2024-09-04; status last verified 2022-02.
• Results first posted 2014-11-14.
• 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.

21. Record Summary

The registry record describes a completed Phase 3, randomized, double-blind, parallel-group, placebo-controlled study of montelukast 10 mg/loratadine 10 mg in Mexican participants with allergic rhinitis. Organon and Co is listed as sponsor. The recorded study start date is 2012-07-04, and the primary completion date is 2012-10-10. Overall enrollment was 69.

Participants in the combination arm received an oral tablet once daily for 2 weeks; the placebo arm received a matching tablet on the same schedule. The primary endpoint was the number of participants experiencing at least one adverse event up to 4 weeks, in a population defined as randomized participants who received at least one dose. The posted counts are 6 of 47 in the combination arm and 2 of 22 in placebo. The reported risk difference is 0.037, with a confidence interval from -0.117 to 0.190, and the unadjusted p-value is 0.657.

The registry record lists 2 outcome measures, 0 analyses, and 0 posted secondary results. The primary comparison is imprecise, and several details needed to assess the full analysis plan are not reported in the registry record.