A Study to Evaluate the Pharmacokinetics and Safety of Cobimetinib in Volunteers With and Without Liver Damage: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study to Evaluate the Pharmacokinetics and Safety of Cobimetinib in Volunteers With and Without Liver Damage (NCT02300025), a non-randomized phase 1 study. The primary outcome is Maximum Observed Plasma Concentration (Cmax).

2. Clinical Question

The question is pharmacokinetic rather than a test of clinical efficacy. Cmax describes the highest observed concentration in plasma after dosing. Comparing this measure across hepatic-function categories can help characterize drug exposure in the studied groups. The record also describes safety and tolerability as study objectives, but it does not provide a complete account of all safety outcomes or a detailed statistical plan.

Because cohort membership was not randomized, any difference in exposure between groups would be an observed association in this study, not a randomized estimate of the effect of hepatic impairment alone. Other group differences could also contribute. The record does not report adjusted estimates or information that would allow those influences to be separated.

3. Trial Design

This was a Phase 1, non-randomized, open-label, parallel-group study. It evaluated a single 10 mg dose of cobimetinib in fasted male and female adult volunteers with normal hepatic function or varying degrees of hepatic impairment. The impairment categories were based on the Child-Pugh classification. The registry lists a planned enrollment of 28 participants and a completed study status.

The four cohorts were normal hepatic function, mild hepatic impairment, moderate hepatic impairment, and severe hepatic impairment. The record describes target sample sizes of 18 volunteers with varying degrees of hepatic function and up to 12 healthy control volunteers. It does not provide a detailed account of the final enrolled count in each cohort. The safety results list participants at risk within each cohort, but those counts are not a substitute for a full enrollment and disposition account.

Open-label means masking was not used. Non-randomized allocation means participants were not assigned at random to the hepatic-function cohorts; the categories reflect their hepatic-function classification. The parallel-group model means the cohorts were studied as separate groups rather than participants moving through each condition. Since assignment was not randomized, the groups should not be interpreted as equivalent apart from hepatic function.

The record gives a study start of 2014-08 and a primary completion of 2015-01. The anticipated study duration was 7.5 weeks. The record does not report the rationale for these enrollment targets or a formal sample-size justification. It also does not report an interim-analysis plan, detailed eligibility criteria, or further operational details. The study is marked completed, but that status alone does not establish that every outcome is reported in the registry.

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

Analysis population for the primary outcome, as defined in the registry: Pharmacokinetic (PK) population included all participants who received at least one dose of cobimetinib and had evaluable PK data.

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: Safety population included all participants who received at least one dose of cobimetinib and had at least one post-dose safety assessment.

6. Primary Endpoint

The registry lists the primary outcome as Maximum Observed Plasma Concentration (Cmax), measured over Pre-dose (0 hours [hrs]), 0.5, 1, 2, 4, 6, 8, 12, 24, 48, 72, 96, 144, 216, 264, 336, 456, and 576 hrs post-dose.

The primary endpoint is maximum observed plasma concentration, or Cmax, measured in nanograms per milliliter (ng/mL). It is a continuous pharmacokinetic measure: for each participant with evaluable pharmacokinetic data, it represents the highest plasma concentration observed over the stated post-dose measurement schedule. The registry lists a mean as the summary parameter and standard deviation as the dispersion measure. The measurement schedule begins at pre-dose (0 hours [hrs]) and continues through 0.5, 1, 2, 4, 6, 8, 12, 24, 48, 72, 96, 144, 216, 264, 336, 456, and 576 hrs post-dose.

In general, Cmax is used to describe peak drug exposure after administration. It complements other pharmacokinetic measures that may describe exposure over time or the rate at which concentration changes. A group mean gives a central summary, while the standard deviation describes the spread of participant values around that mean. These summaries do not reveal the full distribution or the precision of a group comparison.

The record does not report the observed Cmax means or standard deviations by cohort, nor a between-group estimate or confidence interval. The endpoint definition and schedule therefore identify what was intended to be measured, but do not establish the size or precision of any observed cohort difference.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry describes a continuous primary measure summarized by a mean and standard deviation. It does not report the numerical outcome estimates or a detailed analysis plan. The explanations below describe general statistical concepts relevant to reading this type of study; they do not establish which additional procedures were used.

What does Cmax represent?

In general, Cmax is the largest measured plasma concentration for a participant during the scheduled sampling period after a dose. It is a direct summary of peak observed concentration, not a summary of exposure across the entire period. Sampling times matter because a true peak between scheduled measurements might not be captured exactly. The registry lists sampling from pre-dose (0 hours [hrs]) through 576 hrs post-dose, but does not report whether additional sampling or any particular interpolation method was used.

The mean summarizes the central value of a set of measurements. The standard deviation describes the spread of observations around that mean. The mean and standard deviation together can be useful for describing a group, but they do not show every observation, the distribution's shape, or uncertainty in a difference between groups. The registry does not report the cohort-specific Cmax means and standard deviations, so those properties cannot be evaluated from the endpoint definition.

How should group comparisons be understood?

In general, comparisons between group means describe how observed average measurements differ. An unadjusted comparison uses the observed group summaries without accounting for other participant characteristics. An adjusted analysis may use a statistical model to account for prespecified factors, but the record does not report whether such a model was used for the primary endpoint. No adjusted estimates or covariate details are reported.

The non-randomized design is important to interpretation. In a randomized study, random assignment is intended to balance participant characteristics on average. Here, hepatic-function categories define separate cohorts and allocation is non-randomized. Therefore, a difference between cohort means, if reported, would not necessarily be attributable solely to hepatic-function category. General considerations include measured and unmeasured differences between cohorts; the registry does not report enough participant-level detail to assess these.

A confidence interval is a general way to communicate uncertainty around an estimate. Its width reflects the estimate's precision under the selected analysis and assumptions. A p-value, when used, measures how compatible data are with a stated statistical null model; it does not measure the size or clinical importance of a difference. The registry record does not report a confidence interval or p-value for the primary Cmax endpoint, so neither precision nor statistical evidence for a cohort contrast can be assessed.

What do the planning assumptions mean?

The record describes a planning illustration based on an observed effect, using a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The effect to detect is described as a stated fraction of the observed effect. These are assumptions for an illustrative calculation, not evidence that the original study was designed around those assumptions. The record does not report a sample-size justification for the trial's own design, nor does it give the specific planning results or fractions in the registry record recorded for this analysis.

In general, a planning calculation estimates the number of participants per arm associated with a chosen effect size and statistical assumptions. An illustration based on an observed effect is sensitive to the estimate used: an observed effect can be imprecise, especially when data are limited. The resulting sample sizes are planning illustrations, not observed power and not proof that the study could reliably detect a particular effect. The equal-allocation assumption also should not be taken as a description of actual cohort sizes. The study has four hepatic-function cohorts and non-randomized allocation.

Normal approximations rely on conditions under which the sampling distribution is adequately represented by a normal model. Whether those conditions are appropriate depends on the data and analysis. The record does not report diagnostic checks or a model specification. In general, skewness or outliers can affect means and standard deviations, and pharmacokinetic measures can require careful attention to their distribution. No transformation or alternative summary method is reported.

What can be concluded from the reported analysis details?

The outcome definition and analysis-population description identify the intended measure and who could contribute data. They do not reveal the actual estimates. The record does not state whether all scheduled concentrations were available for every participant, whether missing observations were imputed, or how an unevaluable profile was handled. It also does not describe model assumptions, multiplicity procedures, or interim analyses. Those details should not be inferred from the fact that analyses are listed in the registry.

10. Confidence Intervals for Each Arm

No two-arm comparison is shown for this trial, but each arm's mean can be given with a t-based 95% confidence interval computed from the posted mean, spread and number of participants.

R code and output

arm <- c("Cohort 1: Normal Hepatic Function", "Cohort 2: Mild Hepatic Impairment", "Cohort 3: Moderate Hepatic Impairment", "Cohort 4: Severe Hepatic Impairment")
n   <- c(10, 6, 6, 6)
m   <- c(10.7, 9, 8.03, 3.97)
sp  <- c(7.41, 4.09, 2.49, 1.77)
sd  <- sp      # posted standard deviations
for (i in seq_along(n)) {
  se <- sd[i] / sqrt(n[i]); h <- qt(0.975, n[i] - 1) * se
  cat(sprintf("CARM|%s|%d|%.3f|%.3f|%.3f|%.3f\n", arm[i], n[i], m[i], sd[i], m[i] - h, m[i] + h))
}

CARM  Cohort 1: Normal Hepatic Function  10  10.700  7.410  5.399  16.001
CARM  Cohort 2: Mild Hepatic Impairment  6  9.000  4.090  4.708  13.292
CARM  Cohort 3: Moderate Hepatic Impairment  6  8.030  2.490  5.417  10.643
CARM  Cohort 4: Severe Hepatic Impairment  6  3.970  1.770  2.112  5.828

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 9 outcome measures and 9 analyses, but the registry entries recorded for this analysis do not identify the complete set of outcomes, their relative priority, or the statistical procedures applied to each. The primary endpoint is identified as maximum observed plasma concentration. The record does not report whether testing across multiple outcomes or cohort contrasts was adjusted for multiplicity. In general, when many hypotheses are tested, the chance of at least one apparently notable result can increase; adjustment methods and an outcome hierarchy can address that concern. No particular method should be attributed to this study without a registry statement.

The registry defines the pharmacokinetic population as participants who received at least one dose of cobimetinib and had evaluable pharmacokinetic data. It does not report the number analyzed in that population by cohort or the handling of missing samples, incomplete concentration profiles, or unevaluable data. No imputation method, missing-data sensitivity analysis, or rule for excluding a participant from a particular outcome is reported. Missingness can matter if the availability of measurements is related to participant characteristics or outcomes; whether that occurred cannot be assessed from the record.

The record also does not report an intention-to-treat analysis, a per-protocol analysis, or another analysis-population definition beyond the pharmacokinetic population. It does not describe interim analyses or stopping rules. These omissions mean that the relationship between enrollment, evaluable pharmacokinetic data, and the reported endpoint analysis cannot be reconstructed from the record alone. The study's completed status does not fill in these analysis details.

12. 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 listed safety results separate serious adverse events from other adverse events for each hepatic-function cohort. No serious adverse events are recorded among the 10 participants at risk in the normal hepatic function cohort, the 6 at risk in the mild impairment cohort, the 6 at risk in the moderate impairment cohort, or the 6 at risk in the severe impairment cohort. Other adverse events are recorded for 3 participants in the normal hepatic function cohort, 3 in the mild impairment cohort, 2 in the moderate impairment cohort, and 1 in the severe impairment cohort.

These are participant counts, not event rates adjusted for follow-up or differences among cohorts. The record does not give detailed descriptions of the other adverse events, their severity, timing, or relationship to cobimetinib. Death counts are not reported in the registry record. The zero serious-event counts describe what is recorded for these cohort sizes; they do not establish that serious events are impossible or that the groups have equivalent safety. Because the study was non-randomized, differences in counts should be read descriptively rather than as a causal comparison.

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

This study was designed to characterize pharmacokinetics, safety, and tolerability after a single dose of cobimetinib across cohorts defined by hepatic function. The registry identifies Cmax as the primary pharmacokinetic endpoint and specifies its units, summary measure, dispersion measure, measurement schedule, and analysis-population definition. Those details explain what the investigators intended to measure, but do not provide the observed cohort results.

The registry record does not report the Cmax means, standard deviations, between-cohort estimates, confidence intervals, or p-values. Therefore, it does not establish how the observed peak concentrations compare across the cohorts or how precisely any comparison was estimated. The absence of those estimates in the record is not evidence that there was no difference. It means the comparative result cannot be characterized from the information recorded.

The study's non-randomized, open-label design also limits what a cohort contrast could mean. In general, a difference in observed concentrations could reflect hepatic-function category, other differences among participants, or both. The record does not report adjusted estimates that would help distinguish those possibilities. The findings, even if available, would pertain to the studied single-dose setting and the participants represented in the analysis; broader applicability is not established by the design description alone.

The safety counts document no serious adverse events in the listed at-risk groups and report other adverse events in each group. They are descriptive and lack event detail in this record. They cannot establish comparative safety, attribute events to the drug, or rule out uncommon outcomes. The record also does not report death counts.

Accordingly, the statistical meaning of the record is primarily about study design and measurement: it defines a pharmacokinetic question and identifies some safety counts. It does not supply enough primary-endpoint results to support a quantitative interpretation of Cmax differences.

14. Why This Trial Matters Statistically

This study illustrates a distinct statistical problem from a conventional randomized efficacy trial. It compares pharmacokinetic measurements across cohorts defined by hepatic-function categories, rather than randomly assigning participants to treatment conditions. That distinction changes the interpretation: the design can describe observed exposure across the studied groups, but it does not ensure that cohort differences are attributable only to hepatic function.

The primary endpoint is a continuous concentration measure. Cmax is a concise way to characterize peak observed plasma concentration, while the sampling schedule establishes when concentrations were assessed. The registry's specification of a mean and standard deviation makes clear how the endpoint was intended to be summarized. Without the actual estimates, however, a reader cannot assess the observed group values, their spread, or the precision of a comparison. This demonstrates why an endpoint definition is not a substitute for a results estimate.

The pharmacokinetic population definition also highlights a key analysis issue: participants must have both received at least one dose and had evaluable pharmacokinetic data to qualify. A complete interpretation would require knowing how many participants met those conditions in each cohort and how missing or incomplete measurements were treated. Those details are not reported in the registry record.

Finally, the record distinguishes a planning illustration from the study's original design justification. Planning calculations based on an observed effect can help illustrate assumptions, but they do not establish observed power or replace a prospective sample-size rationale. The registry does not report that rationale. Taken together, these details show why design, population definition, endpoint reporting, and uncertainty all matter when interpreting a small pharmacokinetic study.

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 registry record does not report the primary Cmax results by cohort. Without means, standard deviations, comparative estimates, confidence intervals, or p-values, the principal pharmacokinetic question cannot be answered quantitatively from this record. The listing of the primary endpoint and its sampling schedule does not resolve that limitation.

The study is non-randomized and open-label. Cohort membership is based on hepatic-function category, so group comparisons may reflect other participant differences as well. The record does not report adjusted estimates, covariates, or participant characteristics sufficient to assess potential confounding. No detailed account of allocation procedures is reported beyond the non-randomized designation.

The record provides target enrollment information and a planned enrollment of 28, but does not give a full cohort-by-cohort enrollment and disposition account. Safety at-risk counts are reported, and the pharmacokinetic population is defined, but the number with evaluable Cmax data in each cohort is not reported. This limits assessment of completeness and of how the analyzed participants relate to enrollment.

Missing-data handling, exclusion rules for unevaluable profiles, statistical model details, multiplicity procedures, and interim analyses are not reported in the registry record. The safety information is also limited: other adverse events are given as counts without detailed event descriptions or attribution, and death counts are not reported. These limitations mean the recorded information supports a description of design and selected safety counts, but not a complete evaluation of efficacy, comparative exposure, or safety.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: A Study to Evaluate the Pharmacokinetics and Safety of Cobimetinib in Volunteers With and Without Liver Damage — NCT02300025.
• Registry record last updated 2016-02-19; status last verified 2016-01.
• Results first posted 2016-02-19.
• 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

The registry record describes a completed Phase 1, non-randomized, open-label, parallel-group study of a single 10 mg dose of cobimetinib in fasted adult volunteers. Cohorts were defined by normal hepatic function or mild, moderate, or severe hepatic impairment using the Child-Pugh classification. Planned enrollment was 28.

The primary endpoint was maximum observed plasma concentration (Cmax), measured in ng/mL and summarized by mean and standard deviation in the pharmacokinetic population. The record defines that population as participants who received at least one dose and had evaluable pharmacokinetic data. It does not report the cohort-level primary endpoint values or comparative precision estimates.

Safety results list zero serious adverse events in each cohort and other adverse-event counts of 3, 3, 2, and 1 participants across the normal, mild, moderate, and severe groups, respectively. Death counts are not reported in the registry record. The record does not report detailed multiplicity, missing-data, or analysis-plan procedures.