Randomized Study of Obicetrapib in Combination With Ezetimibe: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Randomized Study of Obicetrapib in Combination With Ezetimibe (NCT04770389), a randomized phase 2 study. The primary outcome is Mean Percent Change in Low-Density Lipoprotein Cholesterol (LDL-C) From Baseline to Day 57: Obicetrapib in Combination With Ezetimibe Compared to Placebo [Friedewald].

2. Clinical Question

The trial was designed to evaluate efficacy, safety, and tolerability of obicetrapib with ezetimibe in mild dyslipidemia. The reported primary comparison concerns a laboratory measure and a specified follow-up point; it does not by itself address longer-term outcomes or establish what an individual participant’s response would be. The registry record reports a randomized, placebo-controlled, double-blind Phase 2 study with four masking roles. Detailed eligibility criteria and the planned allocation ratio are not reported in the registry record.

3. Trial Design

This was a randomized, parallel-group, placebo-controlled Phase 2 study. The registry describes quadruple masking and records an enrollment of 112 participants. The listed groups were combination therapy, obicetrapib monotherapy, ezetimibe monotherapy, and placebo. Combination therapy consisted of 5 mg obicetrapib plus 10 mg ezetimibe once daily; the monotherapy groups received one active drug with placebo for the other component, and the placebo group received placebos for both components.

The primary comparison was combination therapy versus placebo. The primary endpoint was mean percent change in LDL-C from baseline to Day 57, measured with the Friedewald formula. Although the study was initially described as having a 12-week treatment period, the registry states that the period was revised to 8 weeks in response to the global COVID-19 pandemic. The primary endpoint timeframe is recorded as 8 weeks.

The registry lists a start date of 2021-02-23, a primary completion date of 2021-05-07, and a completed status. Enrollment is the overall study enrollment recorded in the registry; the available information does not establish that every enrolled participant contributed to the primary endpoint analysis. The endpoint-specific analysis population is described as participants who received at least one dose and had a baseline LDL-C value. The planned allocation ratio, details of sequence generation, concealment procedures, and the full protocol are not reported in the registry record. The registry also does not give enough detail to assess whether every randomized participant remained in their assigned group for analysis.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The study was revised from a 12-week treatment period to an 8-week treatment period in response to the global COVID-19 pandemic. Baseline Population is defined as all participants who received at least one dose of study drug and had a baseline value for LDL-C assessment.

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: The study was revised from a 12-week treatment period to an 8-week treatment period in response to the global COVID-19 pandemic. Baseline Population is defined as all participants who received at least one dose of study drug and had a baseline value for LDL-C assessment.

6. Primary Endpoint

The registry lists the primary outcome as Mean Percent Change in Low-Density Lipoprotein Cholesterol (LDL-C) From Baseline to Day 57: Obicetrapib in Combination With Ezetimibe Compared to Placebo [Friedewald], measured over 8 weeks.

The primary endpoint is mean percent change in LDL-C from baseline to Day 57, with LDL-C determined using the Friedewald formula. It describes the average relative change in a continuous lipid measure over the study’s 8-week treatment period. The comparison of interest is the difference between participants assigned to combination therapy and those assigned to placebo.

Change from baseline focuses the analysis on how the measured value changed during the study, rather than comparing only the groups’ endpoint values. Percent change expresses that change relative to baseline, while the mean summarizes the group-level result. This can be useful for comparing average changes between randomized groups, but a mean does not show the full distribution of participant-level changes. The registry’s stated primary population includes participants who received at least one dose and had a baseline LDL-C assessment; how missing follow-up measurements were handled is not reported in the registry record.

The Friedewald formula is the specified method for determining LDL-C in this endpoint. The choice of measurement method matters because the primary question is tied to that particular LDL-C estimate. The endpoint does not directly measure clinical events, symptoms, or longer-term outcomes. Its interpretation is therefore limited to the specified laboratory measure, comparison, population, and follow-up period.

7. Results Posted in the Registry

• Combination Therapy: mean -45.63 versus -0.17 on control; difference -45.46 (95% CI -55.36 to -35.56), standardized effect d = -2.60; z-test p = <0.001.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Mean Percent Change in Low-Density Lipoprotein Cholesterol (LDL-C) From Baseline to Day 57: Obicetrapib Monotherapy Compared to Placebo [Friedewald]

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Obicetrapib Monotherapy: mean -31.88 versus -0.17 on control; difference -31.71 (95% CI -40.52 to -22.90), standardized effect d = -1.99; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Obicetrapib Monotherapy than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

LS Mean Percent Change in Low-Density Lipoprotein Cholesterol (LDL-C) From Baseline to Day 57: Obicetrapib Monotherapy Compared to Placebo [Friedewald]

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard errors.
• Result:
  • Obicetrapib Monotherapy: mean -31.99 versus 1.37 on control; difference -33.36 (95% CI -43.46 to -23.26), standardized effect d = -1.73; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Obicetrapib Monotherapy than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Mean Percent Change in Low-Density Lipoprotein Cholesterol (LDL-C) From Baseline to Day 57: Obicetrapib Monotherapy Compared to Placebo [PUC]

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Obicetrapib Monotherapy: mean -27.94 versus -1.53 on control; difference -26.41 (95% CI -36.15 to -16.67), standardized effect d = -1.53; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Obicetrapib Monotherapy than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The registry lists a broad set of secondary outcomes, including several ways of summarizing LDL-C change, use of the Friedewald formula or PUC, and ApoB outcomes. It records 27 posted secondary outcome measures and 33 analyses. The available result details include LDL-C comparisons of obicetrapib monotherapy with placebo using the Friedewald method and PUC, as well as a least-squares mean analysis. These results address related but not identical questions, because their summaries, measurement definitions, and analysis methods differ.

The reported secondary LDL-C comparisons generally point in a direction consistent with the primary comparison: the monotherapy group’s reported LDL-C changes are more negative than the placebo group’s. This is a directional pattern across the reported results, not a claim that every secondary outcome had the same result. The registry information available for this analysis does not include results for every listed secondary measure, so the overall set of outcomes cannot be characterized as uniformly positive or negative.

Secondary results can help describe whether patterns extend beyond the primary comparison, but they usually carry less confirmatory weight when many outcomes, measures, or analyses are examined. With multiple opportunities to find a nominally noteworthy result, unadjusted p-values can overstate the strength of evidence if multiplicity is not addressed. The registry does not report a multiplicity adjustment or a prespecified hierarchy for the secondary analyses. Their p-values should therefore be read as individual, unadjusted results unless a fuller analysis plan establishes otherwise.

Differences among means, medians, LS means, and model-based comparisons can also reflect different estimands rather than inconsistency. The registry’s endpoint descriptions and results should be considered together, while avoiding the assumption that a result for one measure automatically confirms another. Secondary findings are informative context for the primary result, but the available information does not establish that they were independently powered or protected against multiplicity.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Mean Percent Change in Low-Density Lipoprotein Cholesterol (LDL-C) From Baseline to Day 57: Obicetrapib Monotherapy Compared to Placebo [Friedewald]
• Median Percent Change in Low-Density Lipoprotein Cholesterol (LDL-C) From Baseline to Day 57: Obicetrapib Monotherapy Compared to Placebo [Friedewald]
• LS Mean Percent Change in Low-Density Lipoprotein Cholesterol (LDL-C) From Baseline to Day 57: Obicetrapib Monotherapy Compared to Placebo [Friedewald]
• Mean Percent Change in Low-Density Lipoprotein Cholesterol (LDL-C) From Baseline to Day 57: Obicetrapib Monotherapy Compared to Placebo [PUC]
• Median Percent Change in Low-Density Lipoprotein Cholesterol (LDL-C) From Baseline to Day 57: Obicetrapib Monotherapy Compared to Placebo [PUC]
• LS Mean Percent Change in Low-Density Lipoprotein Cholesterol (LDL-C) From Baseline to Day 57: Obicetrapib Monotherapy Compared to Placebo [PUC]
• Mean Percent Change in Apolipoprotein-B (ApoB) From Baseline to Day 57: Obicetrapib in Combination With Ezetimibe Compared to Placebo
• Median Percent Change in Apolipoprotein-B (ApoB) From Baseline to Day 57: Obicetrapib in Combination With Ezetimibe Compared to Placebo

9. Statistical Interpretation

10. Statistical Methods Explained

The primary measure is continuous: each participant has a percent change in LDL-C, and the reported primary statistic is the group mean change. A mean difference compares the average outcome between two groups. Here, the registry’s sponsor-reported comparison is an LS mean difference, which is an estimate produced by a model rather than simply subtracting the two displayed arm means. Least-squares means are often used to express adjusted or model-based group averages, but the specific adjustments used in this trial are not reported in the registry record.

What does randomization contribute?

Randomization is intended to create groups that are comparable on average with respect to factors measured and unmeasured before treatment assignment. It supports a between-group interpretation by reducing the risk that treatment selection explains the observed difference. It does not guarantee identical groups in a particular study, and it does not eliminate issues such as missing outcome measurements, deviations from assigned treatment, or analysis choices. The registry records random allocation, but the sequence-generation and allocation-concealment methods are not reported in the registry record.

What does masking contribute?

The registry records quadruple masking and describes the study as double-blind in its official title and summary. Masking is intended to limit the influence of knowledge about assigned treatment on participant behavior, care, outcome assessment, and data handling. The record does not identify the specific roles included in the quadruple masking designation or describe how masking was maintained. Accordingly, masking is a design feature recorded for the study, but its implementation cannot be evaluated fully from the registry information.

How should the confidence interval and p-value be read?

A confidence interval communicates uncertainty around an estimated difference. In repeated use under the model’s assumptions, intervals constructed by the same procedure would have their stated coverage rate for the underlying parameter. For an individual result, the interval describes a range of values compatible with the observed data and assumptions; it is not a range containing a stated proportion of individual participant responses. The primary reported interval is 95% and extends from -55.20 to -34.63.

A p-value measures how unusual data at least as inconsistent with a null comparison would be if that null comparison and the analysis assumptions held. It is not the probability that the null is correct, nor does it indicate the chance that the finding is due to random error. The registry reports p < 0.001 for the sponsor’s primary analysis. A smaller p-value does not necessarily mean a larger or more important effect; effect magnitude and uncertainty are better read from the estimate and its interval, alongside the endpoint’s context.

Why can an unadjusted recalculation differ?

The recalculated estimate uses posted group means, standard deviations, and sample sizes to make a simple comparison. It does not reproduce the trial’s full analysis model. The sponsor’s reported LS mean comparison may reflect model structure or information not contained in those summary statistics. Since the record does not provide the full model specification, the recalculated result is best viewed as a check on the general direction and scale of the posted arm results, not as a competing primary analysis. The registry’s sponsor-reported analysis takes precedence.

What does over-dispersion mean in general?

Over-dispersion is a general concern in some statistical models when observed variation is greater than the model expects. When that happens, uncertainty can be understated if the model does not account for the extra variation. It is not a specific finding established by the continuous LDL-C results. The record does not report an over-dispersion assessment or a need for such an adjustment.

Why do endpoint definitions and analysis populations matter?

Results depend on the outcome definition, analysis population, and handling of incomplete data. The primary endpoint specifies percent change, the Friedewald method, and Day 57; the population definition requires at least one dose and a baseline LDL-C value. These details define what the estimate describes. Missing follow-up values, treatment discontinuations, protocol deviations, and sensitivity analyses can affect the interpretation, but their handling is not reported in the registry record.

The secondary results include different summaries and analysis methods, including means, medians, LS means, and, in one reported result, ANCOVA. A median characterizes the center of a distribution differently from a mean, while LS means and ANCOVA are model-based approaches. Such results should not be treated as interchangeable estimates of one identical quantity without considering their endpoint definitions and methods. The registry’s detailed statistical analysis plan, including any prespecified hierarchy or multiplicity procedure, is not reported in the registry record.

11. Confidence Intervals and Precision

The sponsor-reported primary LS mean difference is -44.92, with a 95% confidence interval from -55.20 to -34.63. The interval lies below zero, which is consistent with a lower mean percent change in the combination group than in the placebo group under the reported model. The interval is the most direct indication of the statistical precision of this estimate in the registry results: it presents a range of values compatible with the data and analysis assumptions.

The simple recalculation gives a mean difference of -45.46 and a 95% confidence interval from -55.36 to -35.56. Its interval is similar in direction and general span to the sponsor-reported interval, though the point estimates and endpoints are not identical. This similarity does not make the two methods equivalent. The sponsor’s LS mean analysis is the reported trial analysis; the recalculation uses only posted summary statistics and is not adjusted using any model details that are unavailable in the record.

Confidence intervals express uncertainty about a group-level estimate, not the range of possible responses for individual participants. They also do not capture every source of uncertainty, including possible bias from missing data or limitations in study conduct. The registry record does not report enough information to assess those sources fully. The intervals should therefore be read alongside the specified analysis population, endpoint definition, and follow-up time.

Statistical precision is not the same as clinical importance. The interval and p-value describe the estimated group contrast under statistical assumptions; they do not establish how the result relates to longer-term outcomes or individual circumstances. The registry record does not provide a threshold for interpreting a clinically important difference in this endpoint.

12. 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 illustrations describe participants per arm for the stated comparison, not total events. They are planning illustrations calculated from the observed effect, rather than the original trial’s design calculations. The assumptions listed are a two-sided significance level of 0.05, equal allocation between the two arms, a normal approximation, and an effect to detect set as the stated fraction of the observed effect. The trial’s original sample-size assumptions and justification are not reported in the registry record.

The 80% power column gives the estimated number of participants per arm for a hypothetical study to have an 80% chance of detecting the specified effect under those assumptions, if the effect and model assumptions hold. The 90% power column gives the corresponding planning count for a 90% chance. These are prospective planning quantities: they help illustrate the sample size associated with a chosen target effect and power, but they are not a measure of how likely this completed trial was to detect its result.

For example, the primary comparison’s illustration for 100% of the observed effect lists 3 participants per arm for 80% power and 4 for 90% power; the illustration for 50% of the observed effect lists 10 and 13, respectively. These small counts reflect the large observed effect used as the planning basis and the calculation assumptions. They should not be read as evidence that such counts would be adequate for a future study in a different setting, or as the trial’s intended enrollment target.

Smaller effects require more participants to distinguish them from random variation at the same power and significance level. The illustrations are therefore sensitive to the assumed effect fraction. They are not observed power, and they do not establish the probability that the trial’s result is true. Their purpose is to show how planning requirements change when the effect being targeted is reduced from the observed estimate.

13. 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, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = -45.460; pooled standard deviation σ = 17.490.
2. n = 2 × (1.96 + 0.842)² × 17.490² / -45.460² = 2.3, rounded up to 3 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
delta <- -45.46                      # observed difference in means
sigma <- 17.4900466102458                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^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 (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(4770389)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 3 (80% power), 4 (90% power)
 75% of observed effect: n per arm = 5 (80% power), 6 (90% power)
 50% of observed effect: n per arm = 10 (80% power), 13 (90% power)
power.t.test: 3.6 
Simulated power at n = 3 per arm: 0.669 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-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.

14. Analyses Reported by the Sponsor

The sponsor-reported primary analysis uses a Mixed Models Analysis and reports an LS mean difference of -44.92, with a 95% confidence interval from -55.20 to -34.63 and p < 0.001. The unadjusted recalculation from the posted arm-level summary statistics gives a mean difference of -45.46, with a 95% confidence interval from -55.36 to -35.56 and p <0.001. Both estimates point in the same direction and are close in magnitude.

The estimates are not identical because they do not represent the same calculation. The recalculation is a simple comparison of posted summary statistics. The sponsor’s result is the analysis reported for the trial and uses a model-based LS mean. The full model specification and any adjustments are not reported in the registry record, so the numerical difference cannot be attributed to a particular model feature from the available record.

There is no recorded discrepancy flag for the primary result. Even so, the sponsor’s own analysis remains the central trial estimate, while the recalculation is a supplementary check on the posted summaries. It should not be substituted for the sponsor’s analysis or used to infer details of the statistical plan that the registry does not report.

15. Multiplicity, Missing Data and Analysis Populations

The registry lists many outcome measures and analyses, including a primary endpoint and multiple secondary measures. When multiple outcomes or analyses are examined, the chance of obtaining at least one apparently unusual result can increase if each is interpreted using an unadjusted threshold. Multiplicity procedures, such as adjusting the decision threshold or defining a testing hierarchy in advance, can address this issue. Whether and how such procedures were used for this trial is not reported in the registry record.

The primary result is identified as a superiority analysis, but the record does not provide the complete prespecified statistical analysis plan. It does not report whether secondary outcomes were confirmatory, whether tests followed a formal sequence, or whether multiplicity was controlled across outcomes, time points, formulas, and summary measures. Secondary p-values should therefore be interpreted cautiously and should not be treated as definitive confirmation solely because they are small.

The registry defines the primary endpoint population as participants who received at least one dose of study drug and had a baseline LDL-C value. That definition does not by itself specify how participants with missing Day 57 measurements were handled. The record does not report the amount or pattern of missing follow-up data, imputation methods, sensitivity analyses, or whether the primary analysis followed an intention-to-treat principle. It also does not describe how treatment discontinuations or protocol deviations were incorporated into the analysis.

These omissions matter because missing outcome data can affect both the estimated treatment contrast and its uncertainty, particularly if the reasons for missingness differ between groups or relate to the outcome. The available record does not establish whether such problems occurred; it simply does not provide the detail needed to evaluate them. The primary population definition and reported results should be read as the registry’s stated analysis, without inferring an unreported missing-data strategy or a complete multiplicity plan.

16. 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 serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: hyperventilation (3.6%), multiple fractures (3.6%).

The registry reports serious adverse events by group. There were 0 serious adverse events among 28 participants at risk in the placebo group, 0 among 27 in the combination therapy group, and 0 among 28 in the obicetrapib monotherapy group. In the ezetimibe monotherapy group, 2 serious adverse events were reported among 28 participants at risk. The registry also reports 0 deaths in each of the four groups.

The record lists hyperventilation and multiple fractures among the top serious-event terms, each with a reported value of 3.6%. The available information does not identify a group for those terms in the listing, so they should not be assigned to a particular treatment arm based on these details alone. Counts of participants with other adverse events are also reported separately from serious adverse events; those categories should not be conflated.

These figures are descriptive counts from the registry record. They do not establish whether an event was caused by treatment, and they do not provide a complete assessment of safety across all possible outcomes or durations. Group sizes and follow-up are limited, and the record does not provide detailed event narratives, exposure-adjusted analyses, or a full account of the safety analysis methods. The absence of a reported serious event in a group is not proof that no risk exists.

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

The posted primary result indicates a lower mean percent change in LDL-C for the combination group than for placebo over the stated 8-week treatment period, under the sponsor-reported analysis. The estimate is a group-level comparison based on the registry-defined population and the specified Day 57 LDL-C measure. The confidence interval gives a sense of uncertainty around that comparison, while the p-value describes evidence against a null comparison under the model assumptions.

The finding does not say that every participant experienced the same change or that an individual can expect a particular response. A mean summarizes group data and can conceal variation among participants. The registry record does not provide the full distribution of participant-level outcomes in the information summarized by these results.

The result also does not establish effects on clinical outcomes, the persistence of LDL-C changes after treatment, or the comparative long-term safety of the regimens. The primary endpoint is a laboratory measure at a specified follow-up point. The study was a Phase 2 trial, and the registry’s brief summary states that it evaluated efficacy, safety, and tolerability; the posted primary comparison alone cannot answer every question relevant to those aims.

Statistical evidence and clinical importance are distinct. A confidence interval and p-value describe statistical uncertainty under assumptions, but the registry does not report a threshold for a clinically important change in LDL-C or evidence linking this endpoint result to longer-term outcomes. The result should therefore be understood as a precise comparison of a defined measure in this study, not as a general conclusion for all participants with dyslipidemia or all treatment contexts.

Finally, the registry record does not provide all details needed to assess missing data, multiplicity, model specification, or implementation of randomization and masking. Those omissions do not negate the reported result, but they limit independent evaluation of how robustly it addresses the broader clinical question.

18. Why This Trial Matters Statistically

This trial illustrates how the estimand and method shape the interpretation of a result. The primary question is not simply whether LDL-C changed, but how mean percent change at Day 57 differed between a combination regimen and placebo under a specified measurement method. Naming the endpoint, comparison, population, and timeframe makes clear what the estimate does and does not represent.

The result also shows why model-based and summary-statistic estimates should be distinguished. The sponsor’s LS mean analysis is the trial’s reported primary result, while the unadjusted recalculation provides a separate check using arm-level summaries. Their similar direction offers context, but the recalculation cannot reproduce a model whose complete specification is not reported. Statistical analysis is not just arithmetic on displayed values; the estimand, population, model, and missing-data assumptions matter.

The registry’s multiple secondary measures raise an important interpretive issue: repeated testing can make unadjusted findings less persuasive as confirmatory evidence. A coherent direction across related endpoints can be informative, but it should be considered alongside whether endpoints were prespecified, whether multiplicity was controlled, and whether results were complete. Those details are not reported in the registry record.

Finally, the confidence interval communicates uncertainty in a more useful way than a significance label alone, while the sample-size illustrations demonstrate how planning requirements depend on the assumed effect. The planning values are based on the observed effect and are not the study’s original design justification. Keeping these distinctions clear helps prevent a statistically strong estimate from being overextended beyond its actual population, endpoint, and follow-up.

19. 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 provides a defined primary endpoint and sponsor-reported analysis, but it does not report the complete statistical analysis plan. Important details including the model specification, covariates, missing-data approach, sensitivity analyses, and multiplicity strategy are not reported in the registry record. This limits the ability to reproduce the sponsor’s LS mean result or assess how robust it is to alternative assumptions.

The registry states that treatment duration was revised from 12 weeks to 8 weeks in response to the global COVID-19 pandemic. The implications of that change for recruitment, follow-up, missingness, or study conduct are not detailed in the record. The endpoint-specific population definition excludes participants without a baseline LDL-C value or without at least one dose, and the record does not explain how incomplete Day 57 measurements were handled.

The overall enrollment is 112, while the primary comparison results list 24 participants in the combination group and 27 in the placebo group. The information available does not explain the difference between overall enrollment and the counts contributing to those endpoint summaries. It also does not give a participant flow account sufficient to assess exclusions, discontinuations, or analysis-set construction.

Further limitations include the absence of detailed eligibility criteria, allocation procedures, masking implementation, full baseline characteristics, and a reported clinically important difference threshold. The registry records a Phase 2 randomized, masked study, but these missing details constrain assessment of generalizability and possible sources of bias. The short endpoint timeframe also means the reported comparison addresses Day 57 results, not longer-term persistence or outcomes.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Randomized Study of Obicetrapib in Combination With Ezetimibe — NCT04770389.
• Registry record last updated 2024-04-24; status last verified 2024-03.
• Results first posted 2024-04-24.
• 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.

23. Record Summary

The registry record identifies NCT04770389 as a completed randomized Phase 2 study of obicetrapib in combination with ezetimibe for participants with mild dyslipidemia. It records quadruple masking, a parallel-group design, and enrollment of 112 participants. The treatment period was revised from 12 weeks to 8 weeks in response to the global COVID-19 pandemic.

The primary endpoint was mean percent change in LDL-C from baseline to Day 57 using the Friedewald formula. The sponsor-reported LS mean difference for combination therapy versus placebo was -44.92, with a 95% confidence interval from -55.20 to -34.63 and p < 0.001. Further details about the statistical plan, missing-data handling, and multiplicity procedures are not reported in the registry record.