Ezetimibe and Atorvastatin vs. Atorvastatin in Patients Age 65 and Older at High Risk for Coronary Heart Disease (CHD)(0653-112): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Ezetimibe and Atorvastatin vs. Atorvastatin in Patients Age 65 and Older at High Risk for Coronary Heart Disease (CHD)(0653-112) (NCT00418834), a randomized phase 3 study. The primary outcome is Percent Change From Baseline in LDL-C at Week 6.

2. Clinical Question

3. Trial Design

This was a Phase 3, randomized, double-blind, parallel-arm study. The official title describes a multicenter study lasting 12 weeks. Its focus was the efficacy and safety of adding ezetimibe 10 mg to atorvastatin 10 mg, compared with titration to atorvastatin 20 mg and to 40 mg, in elderly patients with hypercholesterolemia at high risk for coronary heart disease. The registry record lists an enrollment of 1053.

The posted arm results label one group “Atorva 10 mg + EZ” and the other “Atorva 20 mg / Atorva 40 mg.” Each arm has a reported analysis sample size of 515. The arm descriptions themselves are blank, so details beyond the official title and posted arm labels are not reported in the registry record. In particular, the record does not explain the timing or decision rules for the comparator’s dose titration.

The primary endpoint was percent change from baseline in LDL-C at Week 6, although the study lasted 12 weeks. The registry record also lists a Week 12 LDL-C percent-change outcome and several outcomes based on reaching specified LDL-C thresholds at Week 6 or Week 12. The primary outcome analysis used the Full Analysis Set. The registry record gives that set’s eligibility criteria but does not describe a separate per-protocol population.

The study is marked completed. The start and primary-completion entries are recorded as 2007-01 and 2008-10. Its randomized, double-blind, parallel-group structure supports a between-group comparison, but the registry record does not report further details about concealment, stratification, or the statistical plan.

4. Participant Flow and Accounting

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

Before assignment: Patients were stratified based on baseline LDL-C levels and presence or absence of atherosclerotic vascular disease to achieve balance across treatment groups.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full Analysis Set (FAS): The FAS population includes all randomized patients who took at least 1 dose of study medication and had a baseline (BL) value and at least one post BL value. Post BL measurements up to 3 days following the last dose of double-blind study medication were included in the analysis.

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 in LDL-C at Week 6, measured over Baseline and Week 6.

The primary endpoint is percent change from baseline in low-density lipoprotein cholesterol (LDL-C) at Week 6. It describes how LDL-C values at follow-up relate to each participant’s baseline value, expressed as a percentage change. Negative values indicate a reduction relative to baseline. The posted group estimates are least-squares means, with a 95% confidence interval for each.

LDL-C is a continuous laboratory measure, so the endpoint retains information about the degree of change rather than reducing each participant’s result to whether a threshold was reached. The registry lists threshold-based outcomes separately, including whether LDL-C was below specified cutoffs at Week 6 or Week 12. Those outcomes address goal attainment, while the primary endpoint describes average percentage change.

As a general statistical point, a continuous measure can be useful for comparing average changes between randomized groups. A confidence interval communicates uncertainty around an estimate and the range of values reasonably compatible with the analysis. Neither the endpoint nor its statistical comparison directly measures coronary heart disease events. The registry record does not report a primary clinical-event endpoint in the outcome description.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous: each participant’s result is a percent change in LDL-C. The registry reports least-squares means for the two arms and a 95% confidence interval around each estimate. A least-squares mean is a model-based mean, rather than necessarily the simple arithmetic average of the observed values. The record does not provide enough detail to describe the covariates or other specifications used to estimate these means.

What does the confidence interval convey?

In general, a confidence interval expresses the uncertainty associated with an estimate under the statistical model and its assumptions. A narrower interval indicates greater precision than a wider interval, all else being equal. For the arm-level estimates, the intervals quantify uncertainty around the estimated mean percent change. The registry also reports a confidence interval for the between-group analysis. These intervals concern the specified LDL-C endpoint and should not be interpreted as intervals for clinical outcomes that were not measured in the result being discussed.

The 95% confidence level has a repeated-sampling interpretation: under the model and procedure, intervals constructed in this way would cover the target parameter in 95% of repeated samples. It does not mean there is a 95% probability that this particular interval contains the fixed true parameter. This is a general interpretation of confidence intervals, not an additional finding about the trial.

What does ANCOVA contribute?

The reported comparison method is ANCOVA, short for analysis of covariance. In general, ANCOVA estimates a group contrast while accounting for specified covariates. It can improve precision when covariates predict the outcome and can adjust for baseline measurements if they are included in the model. The registry entry does not identify the covariates, the exact model specification, or whether baseline LDL-C was included. Those details are not reported in the registry record, so the specific adjustment cannot be reconstructed from the method label alone.

The analysis entry labels its parameter “Mean Difference (Final Values),” while the primary endpoint title describes percent change from baseline. The reported ANCOVA estimate is -13.8, with a 95% confidence interval from -16.0 to -11.7 and p < 0.001. The registry record does not explain this labeling in further detail. Readers should distinguish this sponsor-reported comparison from the separately listed arm-level least-squares mean percent changes rather than infer an unreported calculation or model detail.

How should the p-value be read?

In general, a p-value measures how incompatible the observed data, or more extreme data, are with a specified null model, assuming that model and the analysis assumptions hold. A small p-value can indicate evidence against that null model. It does not measure the probability that the null hypothesis is correct, the probability that the result will replicate, or the clinical importance of the difference. The registry reports p < 0.001 for the ANCOVA comparison.

Statistical significance also does not resolve questions about bias, missing data, model suitability, or the relevance of the endpoint to patient-important outcomes. Those questions require information about trial conduct and the analysis plan. The registry record does not report all such details.

Why does the analysis population matter?

The primary outcome population is the Full Analysis Set. It includes randomized patients who took at least one dose of study medication and had a baseline value and at least one post-baseline value. The description further states that post-baseline measurements up to 3 days following the last dose of double-blind study medication were included. This definition identifies who could contribute to the endpoint analysis, but it is not identical to a statement that every randomized participant contributed an observed Week 6 value.

In general, excluding participants without a qualifying measurement can affect the interpretation if missingness is related to treatment or outcome. The registry record does not describe how missing Week 6 values were handled, whether imputation was used, or the reasons values may have been unavailable. Those details are not reported in the registry record.

What can be inferred from the reported analysis?

The analysis supports a statistical comparison of the specified Week 6 LDL-C endpoint under the reported ANCOVA method. It does not, on its own, establish a difference in cardiovascular events or longer-term outcomes. General statistical considerations such as model assumptions and missing-data mechanisms remain relevant, but the record does not provide enough detail to evaluate each assumption. The same caution applies to multiplicity: a small p-value for one outcome does not indicate whether the broader set of outcomes or analyses was adjusted for multiple testing.

10. Analyses Reported by the Sponsor

The registry reports the sponsor’s between-group analysis as ANCOVA, with a mean difference (final values) of -13.8, a 95% confidence interval from -16.0 to -11.7, and p < 0.001. It also reports the arm-level least-squares mean percent changes and their confidence intervals. The registry record does not give a separate recalculated comparison estimate in the registry record described for this result, so there is no independent numerical re-calculation to set alongside the sponsor’s estimate.

The sponsor’s ANCOVA result is therefore the available inferential comparison in the registry record. The reported interval and p-value describe that analysis, while the group estimates describe the Week 6 endpoint in each arm. The record does not provide enough model detail to reproduce the ANCOVA estimate from the arm summaries alone. In particular, it does not state the covariates or full model specification.

The posted information does not identify a discrepancy between the sponsor analysis and a recalculation. That does not make the reported analysis independently verifiable from the summary statistics; rather, it means no conflicting recalculated result is included in the registry information. Interpretation should remain tied to the stated endpoint, population, and analysis method.

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 28 outcome measures and 28 analyses. It also lists five secondary outcomes, including percent change in LDL-C at Week 12 and threshold-based LDL-C outcomes at Week 6 and Week 12. The primary endpoint is percent change in LDL-C at Week 6. The registry record does not report whether the analyses were arranged in a prespecified testing hierarchy, whether multiplicity adjustments were applied, or how the primary result fits into any broader statistical testing strategy.

As a general statistical issue, testing multiple outcomes or contrasts can increase the chance of at least one apparently significant result when each is judged using an unadjusted threshold. Adjustment procedures or a prespecified hierarchy can address some of that concern, but the choice depends on the trial’s objectives and analysis plan. No such procedure is reported in the registry record. The reported p-value should therefore be read as the result of the listed ANCOVA analysis, not as evidence that all possible multiplicity concerns have been resolved.

The primary outcome population is defined as randomized patients who took at least one dose and had a baseline value and at least one post-baseline value. Measurements up to 3 days following the last dose of double-blind study medication were included. The record does not report the number of participants with missing primary outcome data, reasons for missingness, imputation methods, sensitivity analyses, or whether the analysis followed any other missing-data strategy. Those elements are not reported in the registry record.

The adverse-event entries give counts but do not report at-risk denominators, and death counts are not reported. As a result, the registry information does not support calculation or comparison of event rates. The record also does not describe how safety events were defined or collected beyond the posted categories and listed terms.

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

The result describes the Week 6 change in LDL-C in a randomized comparison of ezetimibe added to atorvastatin 10 mg and atorvastatin dose titration. The posted group estimates are negative, indicating reductions from baseline, and the reported ANCOVA comparison has a 95% confidence interval from -16.0 to -11.7 with p < 0.001. This is statistical evidence for a difference in the analyzed endpoint under the reported method.

That finding is limited to LDL-C, a laboratory measure, at the stated follow-up time. It does not establish that either strategy changes the chance of coronary heart disease events, improves long-term health, or has a particular safety profile. The registry record does not report a clinical-event result in the primary endpoint information, and the primary endpoint was measured at Week 6 within a 12-week study.

The p-value does not measure the clinical importance of the estimated contrast, and statistical significance is not equivalent to a judgment that an effect is important to patients. The registry record does not provide a threshold for interpreting the size of the LDL-C change as clinically meaningful. The reported confidence interval communicates uncertainty about the statistical estimate, but does not account for every possible source of uncertainty, such as missing outcomes or model misspecification.

Safety counts in the record are not accompanied by at-risk denominators, and death counts are not reported. Therefore, the counts cannot by themselves establish comparative event rates. The record’s summary also does not provide enough information to assess all aspects of the study’s conduct, analysis choices, or applicability beyond the enrolled population.

In general, a randomized comparison can help estimate differences between assigned groups when the trial is conducted and analyzed appropriately. The registry’s description of randomization and double blinding is relevant context, but it does not answer every question about allocation procedures, adherence, missingness, or the analysis model. The result should be understood as evidence about the specified Week 6 LDL-C endpoint, not as a comprehensive evaluation of treatment effects.

13. Why This Trial Matters Statistically

This trial is statistically informative because it compares two active LDL-C-lowering strategies in a randomized, double-blind, parallel-group design. Its primary outcome is a continuous measure, percent change in LDL-C, which preserves information about the magnitude of change rather than only whether participants crossed a threshold. The registry separately lists threshold-based secondary outcomes, making clear that average change and goal attainment are different statistical questions.

The posted arm estimates and ANCOVA comparison illustrate why results should be read at both the group and contrast levels. The least-squares means describe the estimated outcome in each arm; the between-group analysis supplies the formal comparison and its uncertainty. The p-value is not a measure of effect size or practical importance, and the confidence interval is essential context for precision.

The record also illustrates the limits of registry-level summaries. It identifies the analysis population and method label but does not report the full ANCOVA specification, multiplicity approach, or missing-data handling. Those details matter when judging how robustly a reported result answers its intended question. The primary outcome is a laboratory measure at Week 6, whereas the study duration was 12 weeks; evidence about that endpoint is not equivalent to evidence about clinical events or longer-term outcomes.

Finally, safety counts without denominators are not rates. The presence of serious and other adverse-event counts should not be treated as a complete comparative safety analysis. Distinguishing an observed count, an estimated rate, a model-based contrast, and a clinical outcome is central to interpreting trial results responsibly.

14. 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 primary endpoint is a Week 6 LDL-C measure in a study described as lasting 12 weeks. The registry lists Week 12 outcomes, but numerical results for them are not included in the registry record for this result. Consequently, the Week 6 finding alone cannot establish how the endpoint changed later in the study.

The arm descriptions are blank, and the registry provides limited details about the comparator’s titration beyond the official title and posted arm label. The record does not report the schedule or rules used for titration. It also does not identify the covariates in the ANCOVA model or give enough information to reproduce its estimate from summary statistics.

The Full Analysis Set definition requires at least one post-baseline measurement. The registry record does not report missing-outcome counts, reasons for missingness, imputation procedures, or sensitivity analyses. It also does not report whether multiple testing was addressed across the listed outcomes and analyses. These gaps limit assessment of the robustness and broader inferential context of the primary result.

Safety entries include serious and other adverse-event counts, but their at-risk denominators are not reported and death counts are not reported. Without denominators, the counts cannot be interpreted as comparative rates. The listed serious-event terms are not assigned to particular arms in the registry record described for this result.

The enrollment entry and arm analysis sample sizes do not resolve these analytic limitations. The registry record does not report details about adherence, allocation procedures, or a full statistical analysis plan. These omissions should not be filled by assumption.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Ezetimibe and Atorvastatin vs. Atorvastatin in Patients Age 65 and Older at High Risk for Coronary Heart Disease (CHD)(0653-112) — NCT00418834.
• Registry record last updated 2024-05-14; status last verified 2022-02.
• Results first posted 2009-10-06.
• 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.

18. Record Summary

NCT00418834 is a completed Phase 3 randomized, double-blind, parallel-arm study in patients age 65 and older with hypercholesterolemia at high risk for coronary heart disease. The official title describes a multicenter, 12-week comparison of ezetimibe 10 mg added to atorvastatin 10 mg with titration to atorvastatin 20 mg and to 40 mg. The registry lists an enrollment of 1053.

The primary endpoint was percent change from baseline in LDL-C at Week 6, analyzed in the Full Analysis Set. The registry reports least-squares mean estimates for each arm and an ANCOVA comparison with a mean difference (final values) of -13.8, a 95% confidence interval from -16.0 to -11.7, and p < 0.001. The record lists additional LDL-C outcomes and adverse-event counts, but missing-data handling, multiplicity procedures, full model details, and safety denominators are not reported in the registry record.