Safety Study of MK-8237 Treatment in House-Dust-Mite Allergic Adolescents (MK-8237-008): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Safety Study of MK-8237 Treatment in House-Dust-Mite Allergic Adolescents (MK-8237-008) (NCT01678807), a randomized phase 1 study. The primary outcome is Percentage of Participants Who Experienced At Least One Adverse Event (AE).

2. Clinical Question

3. Trial Design

This was a Phase 1, randomized, double-masked, parallel-group study of MK-8237 in adolescents with house-dust-mite allergic rhinitis or rhinoconjunctivitis. The registry record lists enrollment of 195 and the posted outcome data include 65 participants per group: MK-8237 12 DU, MK-8237 6 DU, and placebo. The record does not report the randomization procedure or the allocation ratio as a protocol detail.

Participants were assigned to one of the three treatments. Both active treatments and placebo were rapidly dissolving sublingual tablets taken once daily for 28 days. The trial status is completed; the recorded start was 2012-10 and primary completion was 2013-05. These dates describe the study record and do not provide additional information about individual treatment duration or follow-up.

The primary endpoint was the percentage of participants who experienced at least one adverse event. Its assessment window ran from the first dose through the last dose of treatment plus 2 weeks of follow-up, up to 42 days. The endpoint population was defined as all randomized participants who received at least one dose of study treatment. The registry record does not report further details about adherence, participant disposition, or the handling of participants with incomplete outcome information.

The study’s stated purpose was to evaluate safety of the two MK-8237 doses compared with placebo. The record does not report the trial’s original sample-size justification, detailed statistical analysis plan, or any interim analysis plan. The posted sample-size illustrations are therefore distinct from the design rationale used by the trial team.

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: All randomized participants who receive at least one dose of study treatment

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Participants Who Experienced At Least One Adverse Event (AE), measured over From first dose to last dose of treatment plus 2 weeks of follow-up, up to 42 days.

The primary endpoint measures the percentage of participants who experienced at least one adverse event during the stated assessment window: from first dose to last dose of treatment plus 2 weeks of follow-up, up to 42 days. An adverse event was defined broadly as an untoward medical occurrence after administration of a pharmaceutical product. The definition did not require a causal relationship with treatment. It also included an unfavorable or unintended sign, symptom, or disease temporally associated with the product or a protocol-specified procedure, and worsening of a preexisting condition in that time context.

This kind of endpoint is used to describe how often participants experience an event during a defined period. The percentage is a participant-level measure: a participant with at least one event is counted as having experienced an adverse event, rather than being represented according to the total number of events. The endpoint therefore does not describe the number, duration, severity, or relatedness of all events unless those details are separately reported.

The registry also defines serious adverse events by specified consequences, including death, life-threatening events, persistent or significant disability, hospitalization, congenital anomaly or birth defect, cancer, overdose, and other important medical events. Seriousness and whether an event is considered related to treatment are distinct concepts. The posted primary endpoint encompasses adverse events generally, not only serious adverse events.

7. Results Posted in the Registry

• MK-8237 12 DU: 56.9% (37/65) versus 43.1% (28/65) on control; risk difference 13.8 percentage points (95% CI -3.2 to 30.9), risk ratio 1.32 (0.93–1.88); unadjusted two-proportion z-test p = 0.114.
• MK-8237 6 DU: 53.8% (35/65) versus 43.1% (28/65) on control; risk difference 10.8 percentage points (95% CI -6.3 to 27.9), risk ratio 1.25 (0.87–1.79); unadjusted two-proportion z-test p = 0.219.

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 in the assessment window or did not. The reported group percentages describe the proportion with an event. A comparison of these proportions can be expressed as a risk difference, meaning the active-treatment proportion minus the placebo proportion. General explanation: a risk difference of zero corresponds to equal proportions, while values on either side represent differences in opposite directions.

What does the confidence interval describe?

General explanation: a confidence interval describes the range of effect estimates that are reasonably compatible with the observed data under the method used. It communicates uncertainty about the estimated difference, rather than giving a guarantee that the true value lies in the interval. In this study, the registry reports a 95% confidence interval for each percent difference. Each interval includes zero, so the data are compatible with no difference as well as with a range of nonzero differences. The breadth of the intervals is relevant: it shows that the observed group sizes do not pin down the difference precisely.

The registry reports percent differences for the active groups versus placebo: 13.8 for 12 DU and 10.8 for 6 DU. The associated 95% confidence intervals are -3.4 to 30.3 and -6.4 to 27.4, respectively. The unadjusted re-calculations use the posted participant counts and group sizes to estimate risk differences and confidence intervals. Recalculated p-values are 0.114 and 0.219. These are simple, unadjusted comparisons from summary statistics; they are not a substitute for an analysis using participant-level data or any methods that may have been specified in the trial plan.

How should a p-value be read?

General explanation: a p-value measures how unusual data at least as different as those observed would be under a particular null hypothesis and statistical model. It is not the probability that the null hypothesis is true, nor does it tell how important a difference is. A p-value should be interpreted with the effect estimate, interval, study design, and analysis plan. The registry record does not report p-values for its sponsor-reported comparisons. The p-values stated above come from unadjusted re-calculations.

When event counts are analyzed as proportions, several effect measures are possible. General explanation: a risk difference expresses an absolute difference in proportions, while a risk ratio compares the proportions as a ratio and an odds ratio compares the odds. These measures answer different questions and may have different numerical scales. The main interpretation uses the registry’s reported percent differences and the re-calculated unadjusted risk-difference comparisons. The record does not specify the method used for the sponsor’s interval calculations.

What does randomization contribute?

General explanation: random allocation is intended to reduce systematic differences between treatment groups at baseline, so comparisons can be more informative about treatment assignment than comparisons of non-randomized groups. Randomization does not ensure that groups will be identical, especially in a study with modest group sizes, and it does not eliminate uncertainty. The registry identifies the study as randomized, but does not report the randomization method, stratification factors, or allocation concealment details. Double masking indicates that the study is recorded as double-masked; further details about who was masked and how masking was maintained are not reported in the registry record.

The primary analysis population is described as all randomized participants who receive at least one dose of study treatment. This definition excludes randomized participants who received no dose, if any, but the record does not report whether such participants occurred. The registry record does not report how missing endpoint data were handled, whether any participants were excluded after dosing, or whether sensitivity analyses were performed.

The record lists two outcome measures overall, four analyses, and zero posted secondary outcomes. It does not report whether the two active-versus-placebo comparisons were adjusted for multiplicity. General explanation: when multiple comparisons are considered, the chance of at least one apparently unusual result can increase if each test is interpreted separately. A prespecified multiplicity strategy can address this issue, but the registry record does not report one. The unadjusted re-calculations should therefore not be presented as multiplicity-adjusted evidence.

For a binary endpoint, the uncertainty in an estimated proportion or difference depends on the event frequency and the number of participants contributing data. General explanation: larger samples generally narrow uncertainty, while sparse outcomes can make estimates less stable. The posted group sizes are equal, and the observed adverse-event percentages are not rare in these data. Even so, the confidence intervals remain broad enough that the magnitude of the difference is uncertain. The study’s own sample-size assumptions and formal analysis plan are not reported in the registry record.

10. Confidence Intervals and Precision

The primary comparisons have meaningful uncertainty. For 12 DU versus placebo, the registry reports a percent difference of 13.8 and a 95% confidence interval from -3.4 to 30.3. For 6 DU versus placebo, it reports a percent difference of 10.8 and a 95% confidence interval from -6.4 to 27.4. Because both intervals include zero, the posted results do not rule out no difference. Their positive upper limits also leave room for larger increases in the event percentage than the point estimates alone suggest.

General explanation: a confidence interval is useful because it conveys both the direction and precision of an estimate. An interval spanning zero signals that the data are compatible with no difference under the stated comparison, while the interval’s width indicates how uncertain the effect size remains. It should not be interpreted as a range containing every plausible value or as a probability statement about the true effect.

Each group had 65 participants. That sample provides a description of the observed event proportions, but the confidence intervals show that the pairwise differences are not estimated narrowly. The reported percentages are not a complete account of safety: they do not indicate how many events each participant had, how severe they were, whether they were judged related to treatment, or how long they lasted. Those details are not reported for the primary endpoint.

The record does not report precision estimates for other outcomes beyond the posted analyses. Nor does it report whether any interval method was selected in advance or adjusted for the multiple comparisons. The registry’s stated confidence intervals and the unadjusted re-calculations should therefore be understood as descriptions of uncertainty for these specific pairwise comparisons, not as a comprehensive account of every uncertainty in the trial.

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 sample-size figures are planning illustrations based on the observed effect, not the trial’s original design assumptions. For this binary outcome, the figures are participants per arm, not total events. The planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation; the effect to detect is the stated fraction of the observed effect. The trial’s own original design assumptions are not reported in the registry record. The sample-size curve represents the same planning exercise, rather than observed trial evidence.

The 80% power column gives the number of participants per arm used in the illustration to have an 80% chance of detecting the chosen effect under those assumptions, if that effect were the true one. The 90% power column uses a higher target chance of detection and therefore generally requires more participants per arm. These are prospective planning concepts: power depends on the assumed effect and analysis conditions, not on whether the trial later observed a particular result.

The entries are organized by the fraction of the observed effect used for planning. For 12 DU versus placebo, the illustration lists 204 participants per arm for 80% power and 272 for 90% power when planning for 100% of the observed effect; 363 and 485 when planning for 75%; and 814 and 1,089 when planning for 50%. For 6 DU versus placebo, the corresponding figures are 337 and 451 for 100%, 599 and 801 for 75%, and 1,343 and 1,797 for 50%.

Smaller assumed effects require more participants per arm because they are harder to distinguish from random variation. These values are not observed power and do not describe the probability that the completed trial’s findings are correct. They are planning illustrations based on the observed effect and the stated assumptions, not a reconstruction of the trial’s actual design justification.

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 = 0.431; treatment proportion p₁ = 0.569; average p̄ = 0.500.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.7071 = 1.3859.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.7003 = 0.5894.
4. n = (1.3859 + 0.5894)² / (0.1385)² = 203.5, rounded up to 204 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 <- 0.430769230769231                          # control proportion
p1 <- 0.569230769230769                          # 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(1678807)
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 = 204 (80% power), 272 (90% power)
 75% of observed effect: n per arm = 363 (80% power), 485 (90% power)
 50% of observed effect: n per arm = 814 (80% power), 1,089 (90% power)
power.prop.test: 203.5 
Simulated power at n = 204 per arm: 0.812 (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. Analyses Reported by the Sponsor

The registry’s sponsor-reported analyses give a percent difference of 13.8 for MK-8237 12 DU versus placebo, with a 95% confidence interval from -3.4 to 30.3. For MK-8237 6 DU versus placebo, the reported percent difference is 10.8, with a 95% confidence interval from -6.4 to 27.4. The registry does not report p-values for these analyses or identify the statistical method used.

The unadjusted re-calculations use the posted summary counts and estimate risk differences and confidence intervals for the same active-versus-placebo comparisons. Their p-values are 0.114 for 12 DU and 0.219 for 6 DU. These calculations are not the sponsor’s analyses, and they do not replace the registry-reported results. The registry record does not flag a discrepancy between the reported and recalculated results. The sponsor’s own analysis takes precedence if a discrepancy is present; no such discrepancy is recorded for these comparisons.

Differences in the way estimates are expressed or rounded can make reported values look slightly different without representing a substantive disagreement. The sponsor-reported values are stated as percent differences, while the re-calculations are unadjusted risk-difference analyses from summary statistics. The study’s detailed analysis plan and the sponsor’s calculation method are not reported in the registry record, so the two approaches should not be assumed to be identical in every methodological detail.

14. Multiplicity, Missing Data and Analysis Populations

The primary endpoint includes two active-treatment comparisons with placebo: 12 DU versus placebo and 6 DU versus placebo. The registry lists four analyses and two outcome measures overall, but zero secondary outcomes are posted. It does not report a multiplicity strategy, such as an adjustment across comparisons, a hierarchy for testing, or a designated primary contrast. The registry-reported analyses do not include p-values.

General explanation: multiplicity becomes relevant when several hypotheses are tested. If each comparison is judged independently, the chance of at least one result appearing unusual under a collection of null hypotheses can be greater than for a single comparison. An adjustment or prespecified testing strategy can control how the collection of results is interpreted. Without a reported plan, the recalculated p-values of 0.114 and 0.219 should be treated as unadjusted comparisons, not as multiplicity-controlled results.

The primary endpoint population is described as randomized participants who received at least one dose. The posted group sizes are 65 per arm. The registry record does not report how many participants were randomized but did not receive treatment, whether outcome data were missing, or how missing or incomplete observations were handled. It also does not report whether the analysis used an intention-to-treat population, a per-protocol population, or another analysis set beyond the endpoint population definition.

General explanation: missing outcome data can affect a proportion estimate if participants with unknown outcomes differ from those with observed outcomes. The direction and size of any effect depend on the amount and pattern of missingness and on the assumptions used to handle it. Since the registry record does not report missing-data counts or methods, the potential effect of missing information cannot be assessed from the posted record.

The record does not report an interim analysis plan or whether interim monitoring was undertaken. It also does not report a detailed statistical analysis plan, prespecified covariate adjustments, or sensitivity analyses. These are absences of reporting in the registry record; they do not establish that such plans or analyses did not exist outside the record.

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 list zero affected participants among 65 at risk in each group: MK-8237 12 DU, MK-8237 6 DU, and placebo. These are counts of participants recorded with a serious adverse event, not a statement that no adverse events of any kind occurred. The primary endpoint includes adverse events generally, and the posted percentages for that endpoint were 56.9% for 12 DU, 53.8% for 6 DU, and 43.1% for placebo.

General explanation: serious adverse events are a subset defined by seriousness criteria, such as life-threatening events or events resulting in hospitalization. A zero count in a study group means none were recorded among the participants at risk in that group during the relevant reporting period. It does not establish that the risk is zero or rule out uncommon events, particularly when the group size is limited.

The record does not list serious adverse event terms. Death counts are not reported in the registry record. The separate counts for other adverse events are 29 in the 12 DU group, 27 in the 6 DU group, and 12 in placebo, among 65 at risk in each group. Those counts should not be treated as interchangeable with the primary endpoint percentages, which report the percentage of participants with at least one adverse event over the specified endpoint window.

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

The results describe short-term adverse-event experience among adolescents with house-dust-mite allergic rhinitis or rhinoconjunctivitis who received MK-8237 or placebo. During the endpoint window, the percentage with at least one adverse event was 56.9% for 12 DU, 53.8% for 6 DU, and 43.1% for placebo. The observed proportions were higher in both active-treatment groups than in the placebo group.

The pairwise estimates are uncertain. The registry-reported 95% confidence intervals for both percent differences include zero, and the unadjusted re-calculated p-values are 0.114 and 0.219. The estimates therefore do not support a precise conclusion about the size of a difference from these data alone. They are compatible with no difference and with a range of differences favoring a higher event percentage in the active groups.

These findings do not establish that MK-8237 caused the reported events. The adverse-event definition did not require a causal relationship, and the posted endpoint aggregates participants with at least one event without presenting event-level detail. The record does not provide the primary endpoint breakdown by severity, relatedness, duration, or specific event term. The serious adverse event figures are separately reported as zero affected participants in each group, but that observation does not exclude rare serious events beyond the study’s observed experience.

The trial was a Phase 1 safety study, and the stated question concerns safety and tolerability over treatment and follow-up lasting up to 42 days. The results do not answer questions about longer-term safety, effectiveness, other patient populations, or other dosing regimens. The registry record does not report the original sample-size rationale, detailed missing-data methods, or multiplicity plan, which further limits how fully the comparisons can be assessed.

The appropriate statistical reading is descriptive and bounded: these are the observed event percentages and pairwise comparisons in this study, with confidence intervals that leave considerable uncertainty. The results should not be converted into a general claim about safety outside the population, treatments, and observation period recorded for this trial.

17. Why This Trial Matters Statistically

This trial illustrates why safety outcomes need both an event definition and a clearly bounded observation period. “At least one adverse event” is a participant-level outcome: it communicates how many participants experienced an event, but not how many events occurred in total or how severe, persistent, or treatment-related they were. The registry’s definition also makes clear that an event need not be caused by treatment to be counted.

The comparison emphasizes the difference between an observed contrast and a precise estimate. The active-treatment percentages are higher than the placebo percentage, but the reported confidence intervals include zero and extend across a range of possible differences. Describing the point estimates alone would omit important uncertainty; relying only on a p-value would likewise miss the size and range of effects compatible with the data.

The study also separates general adverse-event reporting from serious adverse-event reporting. Zero serious adverse events were recorded in each group, while the primary endpoint indicates that participants experienced adverse events overall. The distinction matters because a zero serious-event count is not equivalent to an absence of all events, nor does it settle the possibility of uncommon outcomes that may not appear in a study of this size.

Finally, the planning illustrations show how sample-size requirements depend on the effect chosen for planning. Smaller assumed effects require more participants per arm, and the illustrations are not evidence about the power of the completed study. The registry record does not state the original design assumptions, so the planning figures should not be mistaken for the trial’s own rationale. This makes transparent reporting of the analysis plan, missing data, and multiplicity important to interpreting clinical trial 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.
• Participant counts were reconstructed from posted percentages and arm sizes, so small rounding differences are possible.

The registry record describes a focused safety study in adolescents with house-dust-mite allergic rhinitis or rhinoconjunctivitis, using two MK-8237 doses and placebo. Its findings do not directly address other populations, other dosing schedules, or longer-term observation. Treatment was described as once daily for 28 days, and the primary endpoint window extended to up to 42 days; follow-up beyond that period is not reported.

The primary endpoint combines all participants with at least one adverse event. The posted results do not give event-level descriptions, severity grades, relatedness assessments, or duration for those events. Consequently, the endpoint percentages cannot distinguish transient and mild events from events with different clinical significance. The serious adverse event counts are reported separately, but detailed serious event terms are not listed, and death counts are not reported in the registry record.

Each group included 65 participants, and the reported confidence intervals are broad and include zero. The comparisons therefore leave uncertainty about the magnitude of any difference. The registry record does not report the trial’s original sample-size justification, the statistical method behind the sponsor-reported intervals, or whether comparisons were adjusted for multiplicity.

Additional analysis details are not reported in the registry record, including the randomization procedure, masking procedures, participant disposition, missing-data handling, and any sensitivity analyses. The primary endpoint population is defined as randomized participants who received at least one dose, but further details about the analysis set are not provided. These limitations describe what cannot be established from the registry record; they do not show that the study team did not collect or consider such information.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Safety Study of MK-8237 Treatment in House-Dust-Mite Allergic Adolescents (MK-8237-008) — NCT01678807.
• Registry record last updated 2017-09-15; status last verified 2017-09.
• Results first posted 2017-02-13.
• 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

NCT01678807 is a completed Phase 1 randomized, double-masked, parallel-group study of MK-8237 in adolescents with house-dust-mite allergic rhinitis or rhinoconjunctivitis. The study enrolled 195 participants, with 65 in each posted group: 12 DU, 6 DU, and placebo. Tablets were administered sublingually once daily for 28 days.

The primary endpoint was the percentage of participants with at least one adverse event from first dose through last dose plus 2 weeks of follow-up, up to 42 days. The posted percentages were 56.9%, 53.8%, and 43.1%, respectively. The sponsor-reported percent-difference confidence intervals include zero for both active-treatment comparisons. Recalculated unadjusted p-values are 0.114 and 0.219.

Serious adverse event counts were zero in each group. The record does not report the original sample-size rationale, detailed statistical plan, or missing-data methods.