A Study to Assess the Cholesterol Lowering Effect of an Ezetimibe/Simvastatin Combination Tablet Compared to Another Cholesterol Lowering Drug in Patients With High Cholesterol and With High Cardiovascular Risk (0653A-809)(COMPLETED): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study to Assess the Cholesterol Lowering Effect of an Ezetimibe/Simvastatin Combination Tablet Compared to Another Cholesterol Lowering Drug in Patients With High Cholesterol and With High Cardiovascular Risk (0653A-809)(COMPLETED) (NCT00479713), a randomized phase 3 study. The primary outcome is Percent Change in Low Density Lipoprotein-Cholesterol (LDL-C) at Study Endpoint After Six Weeks of Treatment.

2. Clinical Question

This was a comparison of two active cholesterol-lowering regimens in a population selected for both high cholesterol and high cardiovascular risk. The registry describes the study as randomized, double-blind, multicenter, and parallel-group. Those design features frame the primary question as a between-group comparison, rather than a test of whether either group changed from its own baseline in isolation.

The endpoint was change in LDL-C, a measure of cholesterol, expressed as percent change from baseline. The posted primary analysis included 305 participants in the ezetimibe/simvastatin arm and 297 in the rosuvastatin arm. These are the arm counts associated with the posted endpoint results; the registry does not give further detail on participant flow between randomization and inclusion in the Full Analysis Set.

The clinical question is limited to the six-week LDL-C endpoint. The registry also lists a secondary outcome concerning the percentage of participants reaching designated LDL-C levels after six weeks, but that outcome does not replace or broaden the primary question. The posted record does not establish what the results imply for longer-term cholesterol control or cardiovascular events.

3. Trial Design

The record describes a completed Phase 3, randomized, double-blind, active-controlled, multicenter, parallel-group study. It enrolled 618 participants. The study compared ezetimibe/simvastatin with rosuvastatin in patients with primary high cholesterol and high cardiovascular risk whose condition was not controlled with prior statin treatment. The official title identifies the regimens as ezetimibe/simvastatin 10 mg/20 mg and rosuvastatin 10 mg.

Randomization is intended to allocate participants to treatment groups by chance, which can help make the groups comparable on average at the start of a trial. Double masking means that treatment assignment is intended to be concealed from participants and relevant study personnel; the registry record does not specify which roles were masked or how masking was maintained. The parallel design means participants were assigned to a treatment group rather than crossing between the two regimens, although the registry does not report further implementation details.

The primary endpoint was assessed at study endpoint after six weeks of treatment, using baseline and week 6 measurements. The primary analysis population was the Full Analysis Set, defined as randomized participants who took at least 1 dose and had both a baseline value and at least one post-baseline value. The arm counts for the posted primary results were 305 and 297, respectively. A participant flow account, including the number excluded from that analysis and the reasons for exclusion, is not reported in the registry record.

The record lists the study as completed and identifies Organon and Co as the sponsor. The registry also lists two unspecified placebo intervention entries, but the described arms identify ezetimibe/simvastatin and an active rosuvastatin comparator. The record does not provide descriptions that would establish how those placebo entries relate to the trial arms. Detailed information about the randomization procedure, allocation concealment, adherence, or treatment discontinuations 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.

Before assignment: Eligible participants were randomized at Visit 2 (Week 6) to either a combination tablet of ezetimibe/simvastatin (10 mg/20 mg) plus a matching placebo for rosuvastatin 10 mg (Group 1) or rosuvastatin 10 mg plus a matching placebo for the combination tablet (Group 2) for a 6-week treatment period.

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 participants who took at least 1 dose of study medication and had a baseline (BL) value and at least one post BL value.

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 in Low Density Lipoprotein-Cholesterol (LDL-C) at Study Endpoint After Six Weeks of Treatment, measured over Baseline and 6 weeks.

The primary endpoint was percent change in LDL-C from baseline at the study endpoint after six weeks of treatment. The registry defines it as the week 6 measurement minus the baseline measurement, divided by the baseline measurement, then multiplied by 100. The endpoint is therefore a relative change measure: it expresses the movement in LDL-C against each participant’s starting value, rather than reporting only the week 6 concentration.

Percent change can be useful when participants begin at different baseline levels, because the outcome describes change in relation to baseline. The group estimates are least-squares means, a model-based way of summarizing a continuous outcome. The record does not specify the model terms or covariates used to obtain those estimates, so the exact adjustment underlying the least-squares means is not reported in the registry record.

For this endpoint, more negative values indicate a larger reduction from baseline. The posted arm estimates were -27.66 for ezetimibe/simvastatin and -16.94 for rosuvastatin. The primary endpoint addresses LDL-C change over the specified treatment period; it is not itself a measure of cardiovascular events, long-term outcomes, or overall safety. The registry record does not report a longer-term primary endpoint.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does the arm estimate represent?

The primary endpoint is continuous: each participant’s outcome is a numerical percent change in LDL-C. The posted group values are least-squares means, a form of model-based group summary. In general, a least-squares mean estimates a group mean from a statistical model and may account for factors included in that model. The registry identifies the estimate type but does not describe the model terms, covariates, or handling of baseline values in enough detail to determine precisely what adjustment was made.

The registry gives a 95% confidence interval for each arm estimate. In general, a confidence interval expresses uncertainty around an estimated quantity under the statistical model. The intervals for the two arms are not the same as the interval for their difference: a direct between-group interval is needed to quantify uncertainty in the treatment contrast. The registry reports that contrast separately.

How should the ANOVA comparison be read?

The reported comparison uses analysis of variance (ANOVA) and is labeled as a mean difference in final values. In general, ANOVA is a method for comparing means across groups. The record’s label does not specify whether the analysis used only final measurements, a baseline-adjusted model, or additional factors. It is therefore safest to describe the posted estimate using the registry’s stated analysis label rather than infer unreported model details.

The reported mean difference is -10.72, with a 95% confidence interval from -14.10 to -7.33. The interval represents uncertainty around the estimated between-group difference under the analysis. Since the outcome is percent change, the contrast can be understood in percentage-point terms. The reported p-value is p <=0.001. In general, a p-value measures how compatible the observed data are with a specified null model; it is not the probability that the null hypothesis is true, nor does it measure clinical importance.

What does randomization contribute?

In general, random assignment supports a fair comparison by reducing the influence of systematic differences in treatment allocation. It does not guarantee that every baseline characteristic is identical between groups, and it does not remove the need to define an analysis population or handle missing measurements. The registry identifies randomization and masking but does not describe sequence generation, allocation concealment, or specific masking procedures.

The primary analysis used the Full Analysis Set. The registry defines that population as randomized participants who took at least 1 dose and had a baseline value and at least one post-baseline value. This definition makes inclusion conditional on treatment exposure and availability of measurements. It is not identical to a statement that every randomized participant was included. The number and characteristics of participants excluded from the analysis, and the reasons for exclusion, are not reported in the registry record.

What should be understood about precision and planning?

The confidence intervals communicate precision for the reported estimates. More generally, greater precision corresponds to a narrower interval, while a wider interval leaves more uncertainty about the plausible values of the effect. Precision is not the same as importance: an estimate can be statistically precise without establishing that its magnitude matters to patients or clinical decisions. The registry does not report a clinical threshold for interpreting the LDL-C difference.

The record’s planning assumptions describe sample-size illustrations based on the observed effect, with a two-sided significance level of 0.05, equal allocation, and a normal approximation; planning contrasts are defined as fractions of the observed effect. Such illustrations are hypothetical design calculations, not observed power and not evidence about how the trial was originally planned. The registry does not report the trial’s own sample-size justification or enough detail to identify its original design assumptions.

Over-dispersion is a general concern when outcome variability is greater than a model assumes: standard errors may then be too small, making confidence intervals too narrow and p-values too low. The posted primary endpoint is continuous, and the registry does not report an over-dispersion assessment. This concept is more commonly central to count outcomes, where a variance assumption can be particularly important; it should not be taken as evidence that over-dispersion affected this analysis.

What can the reported test establish?

The reported test addresses the treatment-group comparison for the primary outcome under the stated ANOVA analysis. General statistical reasoning distinguishes this test from the broader question of whether a treatment regimen has meaningful effects across time, populations, or outcomes. The registry record reports one primary endpoint and one posted secondary outcome, but does not state a testing hierarchy or adjustment for multiple comparisons. The p-value should therefore be read as the reported result for this comparison, not as evidence that all possible outcomes or analyses have been accounted for.

10. Analyses Reported by the Sponsor

The registry reports the sponsor’s primary comparison as an ANOVA mean difference (final values) of -10.72, with a 95% confidence interval from -14.10 to -7.33 and p <=0.001. The arm-level least-squares mean estimates are -27.66 for ezetimibe/simvastatin and -16.94 for rosuvastatin. The reported comparison is consistent in direction with the more negative arm estimate for ezetimibe/simvastatin.

The registry record indicates no discrepancy between the sponsor’s reported analysis and the simple unadjusted recalculation. The sponsor’s own analysis takes precedence when describing the trial’s reported inferential result. An unadjusted recalculation from summary statistics cannot reproduce model details that the record does not report, and it should not be treated as a substitute for the sponsor’s analysis.

The sponsor’s estimate and confidence interval quantify the posted treatment contrast under the registry-reported method. The available information does not identify all model specifications or establish whether other analyses were conducted. A distinction should therefore be maintained between the sponsor’s reported result and any simplified recalculation: the latter can serve as a check on the posted summary, but it does not supply unreported protocol or analysis details.

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 10 outcome measures and 11 analyses, while one secondary outcome is posted: the percentage of participants achieving designated LDL-C levels after six weeks. The primary endpoint is percent change in LDL-C at study endpoint after six weeks. The presence of several outcome measures and analyses makes it important to know whether comparisons were prioritized or adjusted to account for multiple testing. A testing hierarchy, multiplicity adjustment, or prespecified strategy for interpreting multiple outcomes is not reported in the registry record.

Without that information, the reported p-value should be interpreted as the result for the posted primary comparison, rather than as a statement about the full family of outcomes and analyses. General statistical reasoning notes that testing more hypotheses can increase the chance of at least one apparently unusual result if no adjustment is made. The record does not establish whether such adjustments were used, so neither their use nor their absence should be assumed.

The Full Analysis Set includes randomized participants who took at least 1 dose and had a baseline value and at least one post-baseline value. This definition gives some information about eligibility for the primary analysis, but the record does not report the number of randomized participants missing endpoint data, the reasons for missingness, or how incomplete measurements were handled. Imputation procedures, sensitivity analyses, and assumptions about missing outcomes are not reported in the registry record.

The record also does not report a per-protocol population or describe how adherence affected inclusion in the endpoint analysis. The total enrollment is 618, while the posted endpoint arm counts are 305 and 297. A detailed participant flow that reconciles randomization, treatment exposure, available measurements, and analysis inclusion is not reported in the registry record. These omissions limit assessment of how the analysis population relates to all randomized participants.

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

The posted result describes a short-term difference in LDL-C percent change between two active treatment groups. In the primary analysis, the ezetimibe/simvastatin estimate was -27.66 and the rosuvastatin estimate was -16.94. The reported between-group mean difference was -10.72, with a 95% confidence interval from -14.10 to -7.33. These statistics indicate the direction and estimated size of the difference under the registry-reported analysis, alongside its statistical uncertainty.

The result does not show how every participant responded. Group means can conceal variation among individuals, and the registry record does not provide participant-level distributions or responder details for the primary endpoint. The primary outcome is a laboratory measure of LDL-C change; it is not a direct measure of cardiovascular events, quality of life, or long-term health outcomes.

The result is specific to the population and analysis defined in the record: patients with primary high cholesterol and high cardiovascular risk not controlled with prior statin treatment, analyzed in the Full Analysis Set, at the six-week endpoint. It does not establish whether the contrast would be the same in other populations, with different treatment histories, or over a longer period. Such extensions are not reported in the registry record.

Statistical evidence and clinical importance are related but distinct. The confidence interval describes uncertainty around the estimated contrast, and the reported p-value addresses compatibility with a null comparison under the analysis assumptions. Neither supplies a clinical threshold for judging importance. The registry does not report such a threshold. No treatment recommendation follows from these statistics alone, and the posted LDL-C result should not be interpreted as a finding about outcomes that were not reported.

13. Why This Trial Matters Statistically

This trial illustrates why a randomized, active-controlled comparison should be interpreted through its between-group estimate rather than by looking only at change within each arm. Both posted arm estimates are reductions from baseline, but the clinical question concerns how those changes differ between randomized groups. The registry reports that contrast directly, with its confidence interval and p-value.

It also illustrates the importance of identifying the analysis population. The Full Analysis Set required treatment exposure and available baseline and post-baseline measurements. That definition clarifies who could contribute to the primary analysis, while leaving questions about participant flow and missing measurements unresolved. A result’s interpretation depends not only on the endpoint and model but also on which participants contributed data.

The record makes a useful distinction between the primary biomarker endpoint and other outcomes. LDL-C change after six weeks is a specific, measurable question. It does not answer broader questions about long-term outcomes or safety. Statistical interpretation is strongest when it stays close to the outcome, time frame, and population actually reported.

Finally, the example shows why model details and multiplicity information matter. The registry identifies an ANOVA comparison and reports a confidence interval, but does not fully specify the model or describe a strategy for multiple outcomes and analyses. Transparent reporting of these details helps readers assess how robustly a result answers the intended question. The posted result is informative, but its scope is bounded by those reporting limits.

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 registry record gives limited detail about the primary statistical model. It identifies least-squares means and an ANOVA comparison labeled as a mean difference in final values, but does not state the model terms, covariates, or baseline adjustment. The exact model behind the estimates therefore cannot be reconstructed from the record.

Participant flow is also incompletely described. The total enrollment is 618, and the primary results include arm counts of 305 and 297, but reasons for exclusion from the Full Analysis Set and the number of participants without endpoint data are not reported. Missing-data methods and sensitivity analyses are not reported in the registry record, limiting assessment of the effect of incomplete measurements.

The record lists 10 outcome measures and 11 analyses but does not describe a prespecified hierarchy or multiplicity adjustment. It also does not give a clinical-importance threshold for the LDL-C difference, which limits interpretation of the effect’s practical significance. The single posted secondary outcome concerns achievement of designated LDL-C levels after six weeks; broader outcomes are not established by the primary result.

Safety reporting is limited in the available record. Serious-event counts are listed as 3 for ezetimibe/simvastatin and 5 for rosuvastatin, and other-event counts as 19 and 30, but the numbers at risk are not reported. These counts therefore cannot be interpreted as event rates from the record. Death counts are not reported. The listed serious-event terms and percentages do not provide enough information to assess comparative safety comprehensively.

Finally, the interventions list includes unspecified placebo entries, while the described arms identify the combination tablet and rosuvastatin. The record does not explain the relationship of those placebo entries to the trial design. Detailed information on adherence, treatment discontinuations, randomization procedures, masking implementation, and the trial’s own sample-size justification is not reported in the registry record.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: A Study to Assess the Cholesterol Lowering Effect of an Ezetimibe/Simvastatin Combination Tablet Compared to Another Cholesterol Lowering Drug in Patients With High Cholesterol and With High Cardiovascular Risk (0653A-809)(COMPLETED) — NCT00479713.
• Registry record last updated 2024-05-16; status last verified 2022-02.
• Results first posted 2009-06-10.
• 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

NCT00479713 is a completed, randomized, double-blind, multicenter, parallel-group Phase 3 study sponsored by Organon and Co. It enrolled 618 participants with primary high cholesterol and high cardiovascular risk not controlled with prior statin treatment. The active comparison was ezetimibe/simvastatin 10 mg/20 mg versus rosuvastatin 10 mg.

The primary endpoint was percent change in LDL-C from baseline after six weeks. In the Full Analysis Set, the arm estimates were -27.66 and -16.94, respectively. The reported ANOVA mean difference was -10.72, with a 95% confidence interval from -14.10 to -7.33 and p <=0.001. The result addresses a six-week biomarker comparison; missing-data handling, full model details, and multiplicity procedures are not reported in the registry record.