A Single Dose Study of MK-8266 (MK-8266-001): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Single Dose Study of MK-8266 (MK-8266-001) (NCT01025791), a randomized phase 1 study. The primary outcome is Number of Participants Who Experienced One or More Adverse Events.

2. Clinical Question

3. Trial Design

This completed phase 1 study, NCT01025791, is titled A Single Dose Study of MK-8266. The registry records randomized allocation, double masking, and a single-group model. It reports enrollment of 25 and lists Hypertension as the condition. The study began on 2009-11-18, with primary completion on 2010-05-14.

The study had three panels. Panels A and B involved healthy male participants; Panel C involved participants with mild-to-moderate hypertension. The registry lists multiple sequences of treatments across periods, including placebo and several MK-8266 dosing regimens. Doses included 0.1 mg, 0.2 mg, 0.4 mg, 0.5 mg, 1.0 mg, and 1.2 mg, as well as schedules in which a dose was followed by one or more additional doses. Panel B included a fed 0.4 mg regimen. The listed period sequences show why the posted treatment groups cannot automatically be interpreted as mutually exclusive parallel groups.

The primary outcome counts participants who experienced one or more adverse events. The registry says participants in groups receiving MK-8266 or placebo in more than one period were counted separately for each period. Thus, the group counts describe period-specific treatment exposure and are not equivalent to counts of distinct people across the whole trial. The posted primary outcome includes 6.0 participants for each listed active regimen and 23.0 for pooled placebo.

The registry lists safety and tolerability as a primary focus, alongside a planned comparison of aortic augmentation index in Panel C. It also names pharmacokinetic outcomes related to food and a heart-rate outcome. Detailed numeric results are not present for every listed outcome. The registry does not report the rationale for the enrollment target, the sequence-generation procedure, washout details, or the basis for the stated analysis model.

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.

Before assignment: For Panel A, 5 treatment periods were planned in this study. For Panels B and C, only 4 treatment periods were planned.

Only the first 6 of 14 groups are shown.

Period 1

Period 2

Period 3

Period 4

Analysis population for the primary outcome, as defined in the registry: All participants who received at least one dose of the investigational 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 Who Experienced One or More Adverse Events, measured over Up to 14 days after administration of last dose of study drug in each study period (Up to 43 Days).

The primary posted endpoint is the number of participants who experienced one or more adverse events. The registry defines an adverse event broadly: an unfavorable and unintended sign, including an abnormal laboratory finding, symptom, or disease associated with medical treatment or a procedure, whether or not it is considered related to that treatment or procedure. The endpoint therefore captures events without requiring investigators to attribute them to MK-8266.

The stated observation period was up to 14 days after administration of the last dose of study drug in each study period, with the registry giving an overall period of up to 43 Days. Participants who received treatment in more than one period could be counted separately for each period. That rule matters when interpreting the denominators: the arm counts reflect treatment-period records and should not be added or treated as a count of unique participants.

Counting participants with at least one event is a direct descriptive way to report how many people in a treatment group had an event during the specified follow-up. It does not describe the number of events per person, the timing or duration of events, or whether an event was related to treatment. The registry’s primary endpoint is a safety measure; it is not the planned blood-pressure-related physiological endpoint of aortic augmentation index. Numerical results for that index are not reported in the registry record, so the posted primary outcome cannot answer that separate efficacy-oriented question.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry presents several kinds of statistical information, and they answer different questions. The primary adverse-event outcome is a count of participants with an event. The secondary heart-rate outcome is reported as a least-squares mean in beats per minute, with standard errors for the group summaries. Some heart-rate comparisons are reported as ANOVA results, while other displayed comparisons are simple, unadjusted recalculations from posted summary statistics. These methods are not interchangeable.

What does a confidence interval describe?

A confidence interval expresses uncertainty around an estimated quantity under the assumptions of the method used to construct it. A narrow interval indicates greater precision than a wide interval, while an interval spanning values on both sides of no difference indicates that the data are compatible with more than one direction of effect. A confidence interval is not a range containing a fixed proportion of individual participant outcomes, nor does it assign a probability to the true value after the data have been observed.

For heart rate, one unadjusted recalculation compares the pooled Panel B 0.4 mg group with Panel A placebo. The estimated mean difference is -1.94 beats per minute, with a confidence interval from -18.86 to 14.98 and an unadjusted p-value of 0.822. Another comparison contrasts Panel C placebo with Panel A placebo: the estimated mean difference is 1.34, with a confidence interval from -18.7 to 21.38 and an unadjusted p-value of 0.896. These are not direct comparisons of MK-8266 with placebo within Panel C. Their intervals are broad, indicating limited precision.

How do the reported ANOVA results differ?

The registry separately reports ANOVA comparisons for Panel A doses against placebo. For 0.1 mg versus placebo, the reported estimate is -0.53, with a 90% confidence interval from -3.92 to 2.86 and p = 0.396. For 0.2 mg versus placebo, the estimate is 2.33, with a 90% confidence interval from -1.17 to 5.83 and p = 0.133. These are sponsor-reported analyses, distinct from the simple unadjusted recalculations. The confidence intervals include zero, so neither result supplies clear evidence of a difference in this outcome. The registry record does not describe the ANOVA model details or adjustments.

What does an unadjusted recalculation mean?

An unadjusted recalculation uses posted group summary values to estimate a contrast without incorporating a fuller participant-level model or other adjustments. In the heart-rate comparisons, the record marks the pooled standard deviation as approximate, derived from the reported standard errors. The resulting estimates can be useful for orientation, but they may not reproduce the sponsor’s analysis, especially when the original design has repeated periods or sequence structure. No discrepancy is flagged for these calculations, but the registry’s reported ANOVA results remain a separate source of analysis.

Why does over-dispersion matter for count outcomes?

General: binary event counts can be analyzed with methods that model the probability of an event. A key assumption in some simple approaches is that observations are independent and arise from comparable event probabilities. When outcomes vary more across participants or periods than the model allows, uncertainty can be understated; this is one form of over-dispersion or model misspecification. Repeated treatment periods and shared participants can also create dependence between observations. The registry record does not report a model for the primary binary outcome, so it is not possible to assess how those features were handled.

How should the planning illustrations be read?

The participant-count illustrations are not the trial’s design calculation and do not represent observed power. They use the observed heart-rate effect as a planning reference, with two-sided significance level 0.05, equal allocation between two arms, and a normal approximation. The scenarios consider planning for 100%, 75%, and 50% of the observed effect. For example, planning for 75% of the observed effect gives 3,032 participants per arm for 80% power and 4,058 participants per arm for 90% power in one comparison. Such illustrations show how sample-size requirements depend on the effect assumed for a future study; they do not validate the original trial’s enrollment or establish that a future study should use these values.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Panel A MK-8266 0.1 mg (Healthy Males)", "Panel A MK-8266 0.2 mg (Healthy Males)", "Panel A MK-8266 0.5 mg (Healthy Males)", "Panel A MK-8266 1.0 mg (Healthy Males)", "Panel A MK-8266 1.0/0.8 mg (Healthy Males)", "Panel B MK-8266 0.4 mg (Healthy Males)")
n      <- c(6, 6, 6, 6, 6, 6)
events <- c(2, 3, 5, 2, 3, 1)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Panel A MK-8266 0.1 mg (Healthy Males)  6  2  33.3  4.3  77.7  9.7  70.0  9.9  71.0
ARM  Panel A MK-8266 0.2 mg (Healthy Males)  6  3  50.0  11.8  88.2  18.8  81.2  18.4  81.6
ARM  Panel A MK-8266 0.5 mg (Healthy Males)  6  5  83.3  35.9  99.6  43.6  97.0  42.1  96.3
ARM  Panel A MK-8266 1.0 mg (Healthy Males)  6  2  33.3  4.3  77.7  9.7  70.0  9.9  71.0
ARM  Panel A MK-8266 1.0/0.8 mg (Healthy Males)  6  3  50.0  11.8  88.2  18.8  81.2  18.4  81.6
ARM  Panel B MK-8266 0.4 mg (Healthy Males)  6  1  16.7  0.4  64.1  3.0  56.4  3.7  57.9

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 10 outcome measures and 26 analyses. It does not report a multiplicity-control strategy, such as a hierarchy among outcomes or an adjustment across comparisons. Without that information, the reported p-values should be interpreted as unadjusted unless the record explicitly identifies otherwise. In particular, secondary p-values do not by themselves establish confirmatory evidence when numerous outcomes and contrasts may have been examined.

The record does not report how missing outcome data were handled, whether any participants withdrew or had incomplete periods, or whether analyses used imputation. Missing-data procedures can affect both the estimates and their uncertainty, particularly in a multi-period study where participants may contribute different numbers of periods. The registry’s primary endpoint population is described as all participants who received at least one dose of the investigational drug, but details of the analysis population for the secondary outcomes are not reported in the registry record.

For the primary binary outcome, the registry provides group counts but no comparative estimate or inferential test; the record indicates that values were missing or not estimable for a two-arm comparison. The absence of a posted comparison means that a treatment contrast and its precision cannot be evaluated from the primary results. It does not justify treating observed count differences as statistically established.

The randomized and double-masked labels describe important design features, but the registry does not report the randomization procedure, allocation concealment details, masking success, or the statistical model used to account for treatment sequence and period. The record also does not state whether interim analyses occurred. These omissions limit assessment of multiplicity, missingness, and model assumptions; they should be treated as documentation gaps rather than filled by assumptions about standard practice.

12. Safety Results

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

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

Most frequent non-serious adverse event terms

The serious adverse-event figures are zero affected participants in every listed group, including pooled placebo, and the registry reports zero deaths. The figures describe the study’s recorded safety experience during follow-up; they are not proof that serious events cannot occur. When group counts are small, zero observed events can still leave substantial uncertainty about uncommon outcomes.

The primary adverse-event endpoint is broader than serious events. It includes any qualifying unfavorable and unintended sign, symptom, disease, or abnormal laboratory finding, regardless of whether it was considered related to treatment. The registry records other adverse events in the groups, including 5.0 of 6.0 participants in the Panel A 0.5 mg group and 10.0 of 23.0 in pooled placebo. These counts do not indicate severity, causality, or the number of events per person.

Because participants receiving treatment in more than one period could be counted separately, group counts should be interpreted at the treatment-period level. They are not necessarily counts of unique people across the complete study. The record does not provide detailed serious-event terms, and it does not establish comparative safety through a statistical test.

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

The posted primary results describe adverse events observed in a small phase 1 study with multiple dose regimens and treatment periods. They show that adverse events were recorded in active-treatment groups and in pooled placebo, while no serious adverse events or deaths were recorded in the listed groups. The counts are useful as a descriptive record of what occurred during the stated follow-up.

Those observations do not establish that MK-8266 caused or did not cause the events. The endpoint counts events whether or not investigators considered them related to treatment. Nor do the counts provide a precise estimate of how event experience would compare in larger or different populations. There is no posted primary comparative estimate, confidence interval, or statistical test for the binary adverse-event outcome.

The registry’s planned aortic augmentation index question is separate. The record identifies a mean decrease of at least 5 percentage points as clinically meaningful, but the numerical result for that outcome is not reported in the registry record. Consequently, the posted adverse-event findings do not show whether the index changed, whether the stated meaningful-change threshold was reached, or how precisely any such change was estimated.

The secondary heart-rate findings are also not a proxy for aortic augmentation index. Their comparisons are imprecise, and the registry record does not fully describe the analysis plan or multiplicity handling. The results therefore support cautious descriptive interpretation rather than a broad conclusion about physiological effects, safety in other populations, or outcomes beyond the study’s recorded periods.

More generally, a small early-phase study can provide initial information about recorded tolerability and help characterize questions for further investigation. It cannot, from these posted data alone, settle uncommon safety outcomes or provide a definitive comparative estimate for the unreported primary physiological question. The conclusions should remain limited to the participants, regimens, endpoints, and follow-up recorded in this trial.

14. Why This Trial Matters Statistically

This study is statistically instructive because the registry’s design labels and posted group summaries require careful interpretation together. It is described as randomized and double-masked, yet the model is listed as single group and the arm descriptions show multiple treatment periods and sequences. Since participants could be counted separately across periods, the treatment-group denominators cannot automatically be read as independent sets of unique people. That distinction matters for both descriptive comparisons and any model-based uncertainty estimates.

The primary endpoint is a binary participant count, but the registry does not post a comparative analysis for it. A set of counts may look readily comparable, yet differences in small groups can be highly uncertain. The missing comparative estimate and confidence interval prevent a reader from judging the precision of a treatment contrast. This is an important difference between having outcome counts and having an inferential result.

The record also separates a safety question from a physiological hypothesis about aortic augmentation index. The primary posted outcome addresses adverse events, while numerical results for the stated index outcome are absent. A record may describe a trial’s question without reporting results for every question, and conclusions must follow the outcomes actually reported.

Finally, the heart-rate results demonstrate why estimates, intervals, and analysis provenance all matter. The record contains sponsor-reported ANOVA results as well as unadjusted recalculations based on summary statistics. Their interpretation depends on the contrast, the uncertainty, and the limits of what can be reconstructed from group summaries. Planning illustrations based on an observed secondary effect can show the sensitivity of future sample-size requirements to assumed effect size, but they are not observed power and do not explain the original enrollment target.

15. 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 most consequential limitation is that numerical results for the planned aortic augmentation index outcome are not reported in the registry record. That leaves the principal physiological question unanswered by the posted results, including whether the stated clinically meaningful decrease was observed.

The primary safety outcome is presented as counts without a comparative effect estimate, confidence interval, or inferential test. Group counts are small, and the registry’s period-based counting rule means that treatment-group denominators should not be treated as unique participant totals. The record does not describe a statistical method for handling repeated periods, sequence effects, or dependence within participants.

The study includes healthy male participants in two panels and participants with mild-to-moderate hypertension in another. The available results therefore do not describe a broad population. Several different doses and dose schedules were used, which makes simple comparisons across groups difficult to interpret as dose-response evidence without a specified model and appropriate accounting for the study structure.

Documentation is incomplete for important analytical details. The registry record does not report the sample-size justification, the handling of missing data, the multiplicity strategy, or whether interim analyses were conducted. Detailed numeric results for the listed food-related pharmacokinetic outcomes are also not reported in the registry record. The secondary heart-rate results are imprecise, and recalculations from summary statistics do not replace participant-level analysis that accounts for the design.

Finally, zero recorded serious adverse events in these groups cannot rule out uncommon events. The follow-up window is limited to the periods described in the registry, and the posted counts do not establish event causality. These limitations call for a narrow reading of the record rather than broader claims about treatment effects or safety.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: A Single Dose Study of MK-8266 (MK-8266-001) — NCT01025791.
• Registry record last updated 2019-02-20; status last verified 2018-10.
• Results first posted 2019-02-20.
• 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.

19. Record Summary

NCT01025791 is a completed randomized, double-masked phase 1 study of MK-8266, with 25 participants enrolled. Panels A and B included healthy male participants, and Panel C included participants with mild-to-moderate hypertension. Multiple dose regimens and placebo were administered across periods.

The primary posted outcome counts participants with one or more adverse events. Serious adverse events and deaths were recorded as zero in the listed groups. The registry does not post a comparative analysis of the primary binary outcome, and numerical results for the planned aortic augmentation index question are not reported in the registry record. Secondary heart-rate results are available but imprecise; detailed numerical food-related pharmacokinetic results are not reported. The registry does not document key analysis details, including missing-data procedures and multiplicity handling.