Safety, Pharmacodynamics, and Pharmacokinetics of Different Dosing Regimens of MK-8266 in Participants With Hypertension (MK-8266-008): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Safety, Pharmacodynamics, and Pharmacokinetics of Different Dosing Regimens of MK-8266 in Participants With Hypertension (MK-8266-008) (NCT01244035), a randomized phase 1 study. The primary outcome is Adverse Events (AEs).

2. Clinical Question

3. Trial Design

This was a Phase 1, randomized, double-blind crossover study of MK-8266 dosing regimens and placebo in participants with hypertension. The study description says it was designed as two sequential, double-dummy, placebo-controlled, three-period randomized crossover studies. Only Part I was completed. The registry record lists overall enrollment of 31 participants.

In a crossover design, participants are assigned to sequences of treatments across periods, rather than remaining in one parallel treatment group throughout the study. The listed Part I sequences vary the order of treatments across three periods. This design can permit within-participant comparisons, but a valid analysis may need to account for period, sequence, and the relationship between repeated measurements from the same participant. The statistical model used for the posted primary outcome is not reported in the registry record.

The primary results include three MK-8266 regimens and placebo. The reported counts are 9.0 of 25.0 participants for MK-8266 1.3 mg BID, 16.0 of 26.0 for MK-8266 0.9 mg FDD, 8.0 of 26.0 for MK-8266 1 mg QD, and 9.0 of 27.0 for placebo. These treatment-specific denominators are not the same as the overall enrollment, and the record does not explain why they differ.

The record lists six interventions as Treatment A through Treatment F and includes sequences for both parts. It does not give a mapping from those lettered treatments to each named dose in the posted results. The study status is completed, with a primary completion date of 2010-12-23. Details such as the crossover washout arrangements, the original sample-size rationale, and the model used for analysis are not reported in the registry record.

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.

Part 1: Period 1

Reasons for not completing this period:

Part 1: Period 2

Reasons for not completing this period:

Part 1: Period 3

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: All participants who received 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.

Population: This was a 3-period crossover study, with a total of 31 randomized participants at Baseline in Sequences A, B, and C.

6. Primary Endpoint

The registry lists the primary outcome as Adverse Events (AEs), measured over MK-8266 1.3 mg BID and 0.9 mg FDD groups: Up to Day 4 in each period; MK-8266 1 mg QD group: the last AE was reported on day 10 after the last dose; Placebo group: Up to 10-14 days after the last dose of placebo.

The primary endpoint is the number of participants with one or more clinical or laboratory adverse events. An adverse event is defined in the registry record as an unfavorable and unintended change in the body’s structure, function, or chemistry that occurs in temporal association with use of the sponsor’s product, whether or not considered related to the product. The endpoint population is all participants who received at least one dose of study treatment.

Counting participants with at least one event is a binary outcome: each participant is classified according to whether an event occurred during the specified observation period. This makes the result interpretable as the frequency of participants experiencing an event, rather than the total number of event episodes. A participant with multiple events still contributes once to this endpoint.

Safety and tolerability were among the study’s stated aims, so this endpoint addresses whether participants experienced any reported clinical or laboratory adverse event during the relevant observation window. The observation periods differ by regimen: the listed timeframe extends up to Day 4 in each period for the 1.3 mg BID and 0.9 mg FDD groups, to the last adverse event reported on day 10 after the last dose for the 1 mg QD group, and up to 10-14 days after the last placebo dose for placebo. These differing descriptions matter when interpreting the counts: the registry record does not describe a single identical follow-up window across all groups.

7. Results Posted in the Registry

• MK-8266 1.3 mg BID: 36.0% (9/25) versus 33.3% (9/27) on control; risk difference 2.7 percentage points (95% CI -23.2 to 28.6), risk ratio 1.08 (0.51–2.28); unadjusted two-proportion z-test p = 0.840.
• MK-8266 0.9 mg FDD: 61.5% (16/26) versus 33.3% (9/27) on control; risk difference 28.2 percentage points (95% CI 2.4 to 54.0), risk ratio 1.85 (1.00–3.41); unadjusted two-proportion z-test p = 0.040.
• MK-8266 1 mg QD: 30.8% (8/26) versus 33.3% (9/27) on control; risk difference -2.6 percentage points (95% CI -27.7 to 22.6), risk ratio 0.92 (0.42–2.02); unadjusted two-proportion z-test p = 0.842.

8. Statistical Interpretation

9. Statistical Methods Explained

These comparisons concern a binary outcome: whether each participant had one or more adverse events. For a treatment group and placebo, a risk difference expresses the difference between the proportions of participants with an event. A value above zero indicates a larger event proportion in the treatment group under the posted comparison’s direction; a value below zero indicates a smaller proportion. The estimate should be read alongside its confidence interval, because the estimate alone does not show how much uncertainty remains.

What does a confidence interval convey?

General explanation: a confidence interval describes the range of estimates reasonably compatible with the observed data under the method used. A narrower interval indicates greater precision; a wider one indicates less precision. If an interval for a risk difference includes zero, the data are compatible with no difference as well as with differences in either direction. An interval that excludes zero indicates that zero is not among the values in that interval, but it does not establish that the effect is clinically important or that the analysis is free of bias.

For MK-8266 1.3 mg BID, the risk-difference estimate is 0.027 and the interval is -0.232 to 0.285. For MK-8266 0.9 mg FDD, the estimate is 0.282 and the interval is 0.024 to 0.540. For MK-8266 1 mg QD, the estimate is -0.026 and the interval is -0.277 to 0.226. The interval for the FDD comparison excludes zero, while the other two include it. The intervals are broad, and therefore the estimates remain uncertain.

How should the p-values be read?

The posted p-values are unadjusted: 0.84 for 1.3 mg BID, 0.04 for 0.9 mg FDD, and 0.842 for 1 mg QD. General explanation: a p-value describes how unusual data at least as inconsistent with a specified null hypothesis would be if that hypothesis and the analysis assumptions were true. It is not the probability that the null hypothesis is true, nor does it measure the size or importance of an effect. A p-value also does not address whether the model adequately reflects the design or whether multiple comparisons were considered.

The registry record does not report the sponsor’s model, any covariates, or whether the sponsor conducted inferential tests for these specific comparisons. The risk differences and p-values posted with the counts should therefore be interpreted as unadjusted comparisons, not as evidence that a crossover-aware analysis was performed. In a crossover study, observations may be related because a participant receives treatments in multiple periods. General explanation: when observations are dependent, treating them as independent can misstate uncertainty; an appropriate analysis generally needs to reflect the design. Whether that was done for the posted results is not reported in the registry record.

Why can over-dispersion matter?

General explanation: over-dispersion occurs when observed variability is greater than a statistical model expects. It can make standard errors too small if a model assumes less variability than the data contain. The primary endpoint is a participant-level event indicator, and no dispersion estimate is reported. The registry record does not describe a model or dispersion assessment, so over-dispersion cannot be evaluated from the posted results.

What do the planning illustrations mean?

The planning display uses the observed risk-difference estimates to illustrate participant requirements under specified assumptions. It considers the full observed effect and smaller fractions of that effect. These are hypothetical planning calculations, not the sample size used in the completed trial, and not an indication of the probability that the observed result is true. The assumptions used for these calculations are reported separately in the sample-size interpretation. The trial’s own design assumptions and sample-size justification are not reported in the registry record.

The calculations are based on posted summary counts and use a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. Such illustrations are sensitive to the estimated effect used as their starting point. In particular, a small observed difference can imply very large participant requirements when the goal is to detect that difference reliably. The displays should be regarded as planning aids, rather than evidence about what the trial was designed to detect.

What is not known about the analysis?

The record does not report how missing outcome data were handled, how participants with incomplete periods were treated, or whether any analysis was restricted to a particular set of completed periods. It also does not report a prespecified analysis plan, a multiplicity adjustment, or a sponsor model for the primary endpoint. Those omissions limit the ability to assess whether the posted comparisons match the intended analysis of this crossover study. No discrepancy is flagged between the posted counts and the unadjusted comparisons.

10. Confidence Intervals and Precision

The risk-difference intervals are wide relative to their point estimates, indicating limited precision. For MK-8266 1.3 mg BID, the estimate is 0.027 and the 95% confidence interval is -0.232 to 0.285. The interval includes zero and allows for both a lower and a higher event frequency relative to placebo. The unadjusted p-value is 0.84.

For MK-8266 0.9 mg FDD, the estimated risk difference is 0.282 and the 95% confidence interval is 0.024 to 0.540. The interval is entirely above zero, but spans a substantial range of possible differences. Its unadjusted p-value is 0.04. The interval’s exclusion of zero is a statement about the estimate under the interval method, not a guarantee that the finding is reliable or unaffected by design and multiplicity considerations.

For MK-8266 1 mg QD, the estimate is -0.026 and the 95% confidence interval is -0.277 to 0.226. This interval includes zero and supports considerable uncertainty about the direction and size of the difference. The unadjusted p-value is 0.842.

General explanation: confidence intervals quantify statistical uncertainty under the analysis assumptions, but they do not account automatically for every design limitation or missing-data issue. Here, treatment-specific counts range from 25.0 to 27.0, and the registry record does not report whether the comparisons account for repeated treatment periods in the crossover design. These features make it important not to interpret a point estimate as a precise or definitive measure of the 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 sample-size displays give the number of participants per arm for these binary outcomes; they do not give a total event count. The planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, a normal approximation, and an effect to detect set to the stated fraction of the observed effect. The rows consider planning for 100% of the observed effect, 75% of the observed effect, and 50% of the observed effect. These assumptions describe the planning illustrations, not the trial’s original design, whose sample-size assumptions are not reported in the registry record.

The 80% power column gives the calculated participants per arm for a planning scenario in which the chosen effect would be detected with 80% power under those assumptions. The 90% power column gives the corresponding participants per arm for 90% power. In plain terms, power is the probability of detecting an effect of the specified size if that effect is real and the planning assumptions hold. It is not a statement about the probability that the treatment effect exists.

Smaller effects need more participants to detect because they are harder to distinguish from random variation. The figures are therefore much larger for the smaller fractions of the observed effect. The observed effect itself comes from small treatment-specific groups, so using it as the planning basis does not make it a stable estimate of the effect that a future study should expect. These figures are planning illustrations, not observed power.

The trial’s completed enrollment was 31, while the calculations are future planning scenarios under equal allocation between two arms. The calculated numbers should not be read as the number actually enrolled in this crossover trial or as a retrospective assessment of whether its design was adequate.

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 = 0.333; treatment proportion p₁ = 0.360; average p̄ = 0.347.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6730 = 1.3191.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.6728 = 0.5662.
4. n = (1.3191 + 0.5662)² / (0.0267)² = 4,998.6, rounded up to 4,999 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 <- 0.333333333333333                          # control proportion
p1 <- 0.36                          # 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(1244035)
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 = 4,999 (80% power), 6,692 (90% power)
 75% of observed effect: n per arm = 8,847 (80% power), 11,843 (90% power)
 50% of observed effect: n per arm = 19,814 (80% power), 26,524 (90% power)
power.prop.test: 4998.6 
Simulated power at n = 4,999 per arm: 0.798 (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

Three regimen-versus-placebo comparisons are posted for the primary adverse-event endpoint. Their p-values are unadjusted: 0.84 for MK-8266 1.3 mg BID, 0.04 for MK-8266 0.9 mg FDD, and 0.842 for MK-8266 1 mg QD. The registry record does not report whether the study used a prespecified multiplicity strategy or adjusted these comparisons for multiple testing. Without that information, the p-value of 0.04 should be treated as a nominal result rather than a result known to control the chance of false-positive findings across the comparisons.

The record lists nine outcome measures and six analyses, but no secondary outcome results are posted. It does not report whether all outcomes and analyses were prespecified, how the primary endpoint was prioritized, or whether any outcomes were selected after examination of the data. The registry record therefore does not permit a full assessment of selective reporting or the family of statistical tests.

The primary population is described as all participants who received at least one dose of study treatment. The treatment-specific denominators for the adverse-event outcome are 25.0, 26.0, 26.0, and 27.0, while overall enrollment is 31. The record does not explain the differences, report missing-outcome counts, or describe how incomplete treatment periods were handled. It also does not state whether all randomized participants were included in each comparison.

These omissions are especially relevant in a crossover study, where a participant may have outcome information under more than one treatment and may not complete every period. The registry record does not report how the analysis accounted for within-participant dependence, sequence, period, or possible carryover, nor does it specify an analysis population beyond the primary endpoint description. The absence of these details does not establish that the analyses were inappropriate; it means that their handling cannot be assessed from the registry record.

14. 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 posted serious adverse-event figures show zero participants with a serious adverse event in each group: MK-8266 1.3 mg BID, MK-8266 0.9 mg FDD, MK-8266 1 mg QD, and placebo. The listed counts of deaths are also zero in every group. The serious-event groups at risk are 25, 26, 26, and 27 participants, respectively.

These figures describe what was reported in the registry record for the study’s safety results. Zero reported serious events does not demonstrate that the risk of a serious event is zero, particularly with these small group counts. It also does not summarize the broader primary endpoint, which includes any one or more clinical or laboratory adverse events, whether or not considered related to study product. The other adverse-event counts are 9 of 25 for 1.3 mg BID, 16 of 26 for 0.9 mg FDD, 8 of 26 for 1 mg QD, and 9 of 27 for placebo.

The registry record does not provide serious-event terms, and no serious-event terms are listed. It does not describe the adjudication process or give additional follow-up beyond the endpoint timeframes. These counts should be read as reported events in this study, not as a complete characterization of safety in other settings or populations.

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

The posted results show that participants experienced adverse events in each of the three MK-8266 regimen groups and in the placebo group. The number with one or more events was 9.0 of 25.0 for MK-8266 1.3 mg BID, 16.0 of 26.0 for MK-8266 0.9 mg FDD, 8.0 of 26.0 for MK-8266 1 mg QD, and 9.0 of 27.0 for placebo. The estimated differences and intervals vary across regimens, and the intervals are broad.

The 0.9 mg FDD comparison has a risk-difference estimate of 0.282 and a confidence interval from 0.024 to 0.540, with an unadjusted p-value of 0.04. This comparison provides evidence of a higher event frequency in the posted counts under the unadjusted comparison, but it does not establish a definitive treatment effect. The record does not report multiplicity adjustment or the sponsor’s statistical model, and the crossover design raises analysis details that cannot be evaluated from these results alone.

The other two intervals include zero: -0.232 to 0.285 for 1.3 mg BID and -0.277 to 0.226 for 1 mg QD. Those results are compatible with a range of differences in either direction. They should not be described as showing equivalence or as establishing no difference. Failure to obtain a small p-value is not proof that two groups have the same event frequency.

These results do not establish whether the regimens are safe or unsafe, do not identify the cause of individual events, and do not characterize the full safety profile outside the recorded study. The endpoint includes events temporally associated with treatment whether or not considered related, so the event counts alone do not establish causation. The results also do not answer the study’s broader pharmacodynamic or pharmacokinetic aims. Only Part I was completed, and the registry record does not provide secondary outcome results.

The most appropriate reading is limited: these are small-group, registry-reported event counts and unadjusted comparisons with considerable uncertainty. The counts can describe what was recorded in this trial, but they cannot establish a general effect beyond the study or resolve the unanswered questions about analysis methods, missing data, and multiplicity.

16. Why This Trial Matters Statistically

This study illustrates why the design and analysis need to be considered together. A crossover trial assigns participants to treatment sequences across periods, so responses from one person can be related across treatments. Simple treatment-versus-placebo comparisons based only on group counts do not reveal whether that dependence was incorporated into the analysis. The registry record does not report the model used for the primary endpoint, leaving an important feature of the inferential evidence unclear.

It also shows how precision affects interpretation. The estimated risk differences range from -0.026 to 0.282, while the confidence intervals span broad ranges. The modest treatment-specific counts mean the data do not pin down the size of the differences precisely. A single p-value, especially one of 0.04 among several unadjusted comparisons, cannot substitute for the full estimate, interval, and analysis context.

Safety endpoints based on participants with at least one event are easy to understand, but they do not capture the number, duration, seriousness, or clinical importance of every event. The record separately reports zero serious adverse events and zero deaths, while the primary endpoint includes any qualifying adverse event. These measures answer related but distinct questions.

Finally, the study’s description includes two parts, but only Part I was completed. The posted primary results therefore concern a limited portion of the study as designed. The record’s missing details about sample-size rationale, analysis populations, missing data, and multiplicity restrict how confidently the results can be evaluated. Statistically, the value of this trial lies in showing the information contained in the observed event counts while also making clear where uncertainty remains.

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 treatment-specific groups are small, with adverse-event denominators of 25.0 to 27.0 participants. The wide confidence intervals reflect substantial uncertainty in the estimated differences. The overall enrollment is 31, and the registry record does not explain how that enrollment relates to the treatment-specific denominators or whether all randomized participants contributed to each comparison.

The study used a crossover design, but the registry record does not describe the statistical model used for the posted comparisons. It does not report how within-participant dependence, period, sequence, or possible carryover was handled. The unadjusted comparisons therefore do not show whether the analysis fully reflected the design.

Only Part I was completed, although the study was designed to include two parts. The record does not provide the reason Part II was not completed. It also does not report the original sample-size justification, missing-data methods, multiplicity strategy, or a detailed analysis plan. The differing adverse-event observation timeframes across treatment regimens further limit straightforward comparisons of the event counts.

The primary endpoint counts participants with one or more events but does not convey event frequency per participant, duration, severity, or relationship to treatment. The serious-event counts are zero, but small groups cannot establish that serious events do not occur. No secondary outcome results are posted, limiting assessment of the study’s wider pharmacodynamic and pharmacokinetic aims.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Safety, Pharmacodynamics, and Pharmacokinetics of Different Dosing Regimens of MK-8266 in Participants With Hypertension (MK-8266-008) — NCT01244035.
• Registry record last updated 2019-02-28; status last verified 2018-10.
• Results first posted 2019-02-28.
• 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 1 randomized, double-blind crossover study of MK-8266 regimens and placebo in participants with hypertension. It lists enrollment of 31 and says the study was designed as two sequential, three-period crossover parts; only Part I was completed.

The primary endpoint counted participants with one or more clinical or laboratory adverse events. Event counts were 9.0 of 25.0 for MK-8266 1.3 mg BID, 16.0 of 26.0 for MK-8266 0.9 mg FDD, 8.0 of 26.0 for MK-8266 1 mg QD, and 9.0 of 27.0 for placebo. The unadjusted risk-difference intervals are broad; only the 0.9 mg FDD interval excludes zero.

No serious adverse events or deaths are listed. The registry record does not report the sponsor’s statistical model, multiplicity handling, missing-data methods, or original sample-size justification. These limitations constrain interpretation of the posted comparisons.