Bempedoic Acid + Ezetimibe Fixed-Dose Combination (FDC) Study in Patients With Type 2 Diabetes and Elevated LDL-C: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Bempedoic Acid + Ezetimibe Fixed-Dose Combination (FDC) Study in Patients With Type 2 Diabetes and Elevated LDL-C (NCT03531905), a randomized phase 2 study. The primary outcome is Percent Change From Baseline to Week 12/End of Study (EOS) in Low-density Lipoprotein Cholesterol (LDL-C).

2. Clinical Question

The registry describes a 12-week study evaluating LDL-C lowering, other lipid and glycemic measures, and safety. The main posted comparison is the difference in adjusted mean percent change between the bempedoic acid plus ezetimibe combination and placebo. The combination was also compared with ezetimibe alone, and ezetimibe alone with placebo. These are separate treatment contrasts within the study’s factorial design; each contrast addresses a different comparison rather than a single all-purpose question.

The registry reports an adjusted comparison for the primary endpoint, but does not report a separate primary question about clinical events or long-term outcomes. The endpoint is a laboratory measure of lipid change over the stated follow-up. Thus, the central statistical question is about the estimated short-term difference in LDL-C change between study groups, and the precision and analysis choices that qualify that estimate.

3. Trial Design

The registry record describes a randomized, triple-masked, factorial phase 2 study. Enrollment was 242. The study’s brief summary identifies a 12-week assessment in participants with type 2 diabetes and elevated LDL-C. The listed interventions were a bempedoic acid plus ezetimibe fixed-dose combination, ezetimibe, and placebo preparations. The arm descriptions indicate that placebo preparations accompanied active study treatments.

The primary outcome was percent change in LDL-C from baseline to Week 12 or end of study. The registry reports three adjusted comparisons: combination versus placebo, combination versus ezetimibe, and ezetimibe versus placebo. The reported primary endpoint group sizes were 55 for the combination, 59 for ezetimibe, and 57 for placebo. These are analysis counts for the posted endpoint, not a breakdown of the full enrollment.

The primary analysis population was the Efficacy Analysis Set: randomized participants who received at least one dose, excluding participants at three study sites, with only participants who had available data analyzed. The registry does not report why those sites were excluded. Safety results use different at-risk denominators, and the registry record does not explain the difference between those denominators and the primary endpoint analysis counts.

The study began on 2018-05-09, had primary completion on 2019-06-18, and is listed as completed. Further detail about allocation procedures, masking procedures, or the rationale for the design is 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.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Efficacy Analysis Set (EAS): all randomized participants who received at least one dose of investigational medicinal product (Full Analysis Set), excluding participants at three study sites. Only participants with available data were analyzed.

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 Percent Change From Baseline to Week 12/End of Study (EOS) in Low-density Lipoprotein Cholesterol (LDL-C), measured over Baseline; Week 12.

The primary endpoint is percent change in low-density lipoprotein cholesterol (LDL-C) from baseline to Week 12 or end of study. LDL-C is a blood lipid measure, and the endpoint expresses the change relative to each participant’s baseline value. The registry defines baseline using the average of LDL-C values from Screening Visit 3 and Treatment Visit 1, the last two non-missing values on or before Day 1. If only one value was available, that value was used.

The endpoint is useful for describing a short-term change in a measured lipid parameter across randomized groups. Percent change puts the follow-up value in relation to baseline rather than reporting only a follow-up concentration. In this trial, the posted treatment contrast is a difference between adjusted mean percent changes. A negative contrast indicates that the group listed first had a lower estimated percent change than the comparison group, according to the registry’s ordering of groups.

Blood samples were drawn after a minimum 10-hour fast at prespecified intervals. For LDL-C, measured values were used when available. The primary analysis used analysis of covariance (ANCOVA), with treatment as a factor and baseline lipid value as a covariate. The registry states that missing LDL-C data were imputed using last observation carried forward. This is a laboratory endpoint over the stated follow-up; the registry does not report that it measures clinical events or establishes longer-term outcomes.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does ANCOVA contribute?

ANCOVA compares outcome means across treatment groups while including a baseline measure as a covariate. In general, adjusting for baseline can account for differences in the starting value and can improve precision when baseline is related to the follow-up outcome. The registry states that treatment was included as a factor and baseline lipid parameter as a covariate for the LDL-C percent-change analysis. The resulting reported estimates are differences of least-squares means: model-based adjusted group contrasts, rather than raw differences between group summaries.

The posted group estimates are -38.8 for the combination, -19.2 for ezetimibe, and 0.9 for placebo. A direct subtraction of those displayed values would not reproduce every adjusted contrast exactly. That is not unexpected when estimates are rounded and the reported comparisons come from an adjusted model. The sponsor’s ANCOVA results are the relevant reported results for the primary endpoint.

How should the confidence intervals be read?

A confidence interval gives a range of estimates compatible with the observed data under the statistical model and its assumptions. In general, a narrower interval indicates greater precision than a wider interval, while an interval that crosses zero leaves greater uncertainty about the direction of the contrast. Each primary comparison has a 95% interval entirely below zero. The endpoints of the interval describe uncertainty in the group difference, not a range containing a stated proportion of individual responses.

The p-values are reported as p < 0.001 for the primary comparisons. A p-value evaluates how compatible the observed data are with a null comparison under the analysis assumptions; it is not the probability that the null hypothesis is true, and it does not quantify the size or importance of a result. The estimates and confidence intervals are needed to understand direction and precision alongside the p-values.

What do the standard errors describe?

The endpoint summaries report standard errors alongside least-squares means. In general, a standard error describes the sampling uncertainty of an estimated mean, not the spread of individual observations. It is therefore not interchangeable with a standard deviation. Reading the standard errors as participant-to-participant variability would misstate what the registry reports.

How were missing values handled?

The registry says missing primary LDL-C values were imputed using last observation carried forward (LOCF). In general, LOCF carries a participant’s most recent observed measurement forward to a later time point when the later measurement is missing. This approach relies on an assumption about how the unobserved value relates to the last observed value. It can understate uncertainty if the imputed value is treated as though it were observed, and it does not represent all possible patterns of change after dropout. The registry record does not report sensitivity analyses for alternative missing-data assumptions.

The endpoint population was the Efficacy Analysis Set, defined as randomized participants who received at least one dose, excluding participants at three study sites. Only participants with available data were analyzed. Although LOCF is described for missing LDL-C values, the precise implementation and the number of imputed measurements are not reported in the registry record.

What do the recalculated comparisons and planning illustrations mean?

Recalculated comparisons in the posted secondary summaries are simple, unadjusted estimates based on summary statistics. They are useful as descriptive checks, but they do not reproduce the sponsor’s ANCOVA model, its covariate adjustment, or necessarily its analysis population. The record indicates no discrepancy flag for these results. Even so, an unadjusted estimate should not replace a reported adjusted analysis when the two answer different statistical questions.

The sample-size illustrations are planning calculations based on observed effects, not the trial’s own design justification and not observed power. Their stated assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation, with the target effect expressed as a fraction of the observed effect. In general, using a smaller target effect requires more participants to achieve a given planned power, all else equal. These calculations are hypothetical planning aids; they do not establish what the original study was designed to detect. The protocol’s sample-size rationale and any interim-analysis plan are not reported in the registry record.

10. Analyses Reported by the Sponsor

The sponsor’s primary analysis used ANCOVA and reported adjusted differences of least-squares means. For the combination versus placebo, the estimate was -39.6 with a 95% confidence interval from -45.8 to -33.4 and p < 0.001. The combination-versus-ezetimibe and ezetimibe-versus-placebo estimates were -19.5 and -20.1, respectively, each with a 95% confidence interval and p < 0.001.

Some posted secondary summaries also contain recalculated comparisons based on group summary statistics. Those are simple unadjusted calculations and should not be read as a reconstruction of the sponsor’s covariate-adjusted ANCOVA. For example, secondary recalculations can differ from reported ANCOVA estimates because they use a different calculation and may not share the model’s adjustment. The record does not mark a discrepancy, but this does not make the unadjusted calculation equivalent to the sponsor’s analysis.

Accordingly, the adjusted estimates and intervals reported by the sponsor are the primary basis for interpreting the registry’s primary comparison. The recalculations are supplementary descriptive checks, not a replacement for the reported model.

11. Multiplicity, Missing Data and Analysis Populations

The registry reports several primary treatment contrasts and multiple secondary outcomes. It does not report whether a formal multiplicity procedure was used to control the chance of false-positive findings across the contrasts or endpoints. Without that information, individual p-values should not be interpreted as though they necessarily control an overall error rate across all analyses. This is particularly relevant to secondary outcomes, where multiple measures and comparisons are available.

The record lists 16 outcome measures, reports 11 secondary outcomes, and includes 36 analyses. Those counts describe the scope of posted reporting, but do not establish which analyses were prespecified, how endpoints were ordered, or whether any testing hierarchy was applied. The statistical analysis plan, including any multiplicity strategy, is not reported in the registry record. The registry also does not report an interim-analysis plan.

For the primary endpoint, the registry describes the Efficacy Analysis Set as randomized participants who received at least one dose, excluding participants at three study sites; only participants with available data were analyzed. It further states that missing LDL-C data were imputed using last observation carried forward. The reason for excluding the study sites, the extent of missingness, and sensitivity analyses under alternative assumptions are not reported in the registry record.

In general, missing-data handling can affect both an estimate and its uncertainty, particularly when missingness is related to participants’ unobserved outcomes. LOCF is one specific imputation approach and relies on carrying forward a prior value. The posted description does not establish that this assumption fits all participants. The safety at-risk denominators differ from the primary endpoint analysis counts, but the registry record does not explain the relationship between these populations. These reporting limits do not negate the posted results; they define the scope of what can be concluded from them.

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 3% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: angioedema (1.2%), duodenal ulcer (1.2%).

The registry reports serious adverse events for the three treatment groups using at-risk denominators of 81, 81, and 80. The corresponding counts of participants affected were 0 for the combination, 1 for ezetimibe, and 1 for placebo. Deaths were reported as 0 in each group. The serious-event terms listed include angioedema and duodenal ulcer, each reported as 1.2%; the registry does not associate those terms with a specific group in the posted term summary.

These are descriptive event counts over the study period. With small counts, the difference between groups is imprecisely characterized, and the figures alone do not establish whether an event was caused by a study treatment. The registry also reports other adverse events affecting 8, 6, and 7 participants in the respective groups, but those counts are not a substitute for the serious-event summary.

The safety denominators are not the same as the posted primary endpoint analysis counts. The registry record does not explain the population differences or provide further detail about event collection, follow-up completeness, or causal assessment. These results should therefore be read as the reported safety counts rather than as a comparative safety estimate.

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

The posted primary analysis estimates short-term differences in LDL-C percent change among randomized groups. Its adjusted comparisons favor a more negative percent-change estimate for the combination than for placebo and for ezetimibe alone, and a more negative estimate for ezetimibe than for placebo. The confidence intervals quantify uncertainty around those comparisons under the reported ANCOVA model.

These results do not establish the size or persistence of any effect beyond the study’s stated Week 12 or end-of-study assessment. The registry describes a short-term laboratory endpoint, not a measure of clinical events, long-term health outcomes, or participants’ experience. It also does not provide information sufficient to assess the broader clinical importance of the observed differences.

The posted analysis population excludes participants at three study sites and is restricted to randomized participants who received at least one dose, with available data analyzed. Missing LDL-C values were handled with LOCF. These design and analysis choices define the population and assumptions to which the estimates apply; they do not support assuming the findings extend to people or settings not represented in the analysis.

Statistical significance is not equivalent to clinical importance, and the reported p-values do not measure the probability that a treatment effect is real. The confidence intervals and point estimates give information about the modeled contrast, while unreported multiplicity handling and incomplete secondary reporting limit the strength of conclusions from additional tests. The registry record does not report enough detail to infer a sample-size rationale, all protocol decisions, or results for outcomes without posted numerical data.

14. Why This Trial Matters Statistically

This trial is statistically informative because it reports an adjusted primary endpoint comparison alongside arm-level estimates, confidence intervals, and p-values. That combination lets readers distinguish the estimated magnitude of a contrast from its precision and from a test against a null difference. The three reported comparisons also make clear that the registry is addressing more than one treatment contrast.

The endpoint analysis illustrates why the model matters. ANCOVA adjusts for baseline lipid value, whereas a recalculation from summary statistics is unadjusted. Those calculations can be useful for orientation, but they answer different questions and should not be treated as interchangeable. The primary result is most appropriately interpreted using the sponsor’s reported adjusted estimate and interval.

The record also highlights limits that are common to registry-based interpretation: the analysis population excludes three sites, missing values were imputed with LOCF, and the multiplicity strategy is not reported. Secondary results are therefore less definitive than the primary comparison, particularly when the available outcomes and analyses involve multiple tests. The planning illustrations are based on observed effects and stated assumptions; they are not evidence of the original design’s power or rationale.

These distinctions matter because statistical evidence depends not only on the numerical estimate but also on the population, model, missing-data approach, and scope of testing. Reporting those boundaries helps readers avoid extending a short-term laboratory finding beyond what the registry analysis directly addresses.

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.

Several trial-specific limits affect interpretation. The primary efficacy population excluded participants from three study sites, but the reason for exclusion is not reported in the registry record. The analysis also included only participants with available data after the stated LOCF procedure. The amount and pattern of missing LDL-C data and sensitivity analyses under alternative missing-data assumptions are not reported.

The primary outcome is a short-term lipid measure, with assessment at Week 12 or end of study. Longer follow-up and clinical outcomes are not reported in the registry record. Although the study summary mentions glycemic measures and safety, the posted secondary results do not provide a complete numerical account of all listed outcome measures. A multiplicity strategy and the study’s sample-size justification are also not reported.

The primary analysis counts differ from the safety at-risk denominators, and the registry does not explain that difference. The safety event counts are small and descriptive; the posted term summary does not link each serious-event term to a specific treatment group. These results do not, on their own, provide a precise comparative safety estimate.

The trial is listed as phase 2 and randomized, triple-masked, and factorial, but further details about the randomization and masking procedures are not reported in the registry record. These limitations constrain interpretation of the posted analysis; they do not change the numerical results reported for the stated endpoint and analysis population.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Bempedoic Acid + Ezetimibe Fixed-Dose Combination (FDC) Study in Patients With Type 2 Diabetes and Elevated LDL-C — NCT03531905.
• Registry record last updated 2020-04-09; status last verified 2020-04.
• Results first posted 2020-04-09.
• 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

NCT03531905 is a completed randomized, triple-masked, factorial phase 2 study of bempedoic acid plus ezetimibe, ezetimibe alone, and placebo in participants with type 2 diabetes and elevated LDL-C. The primary endpoint was percent change in LDL-C from baseline to Week 12 or end of study, analyzed using ANCOVA in the Efficacy Analysis Set with LOCF for missing LDL-C values.

The registry reports three adjusted primary comparisons, each with a 95% confidence interval entirely below zero and p < 0.001. The record also posts selected secondary outcomes and descriptive safety counts. Interpretation is limited by the excluded study sites, the available-data analysis and imputation approach, and the absence of reported multiplicity and sample-size planning details.