A Prospective, Open Label Comparison of Ezetimibe, Niacin, and Colestipol as Adjunct Therapy in Lipid Reduction: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Prospective, Open Label Comparison of Ezetimibe, Niacin, and Colestipol as Adjunct Therapy in Lipid Reduction (NCT00203476), a randomized phase 4 study. The primary outcome is LDL Goal Attainment.

2. Clinical Question

The question concerns whether the recorded frequency of LDL goal attainment differed across the three adjunctive-treatment groups. The registry record lists 30 participants enrolled. For the primary endpoint, it reports 6 participants among 9 in the niacin group, 6 among 9 in the colestipol group, and 9 among 10 in the ezetimibe group. These are descriptive counts for the posted endpoint; they do not, by themselves, establish whether observed group differences are compatible with chance variation or reflect a consistent treatment effect.

The study also planned to assess whether participants reached guideline-based LDL goals in light of their cardiovascular risk, as well as liver-function-test elevations, rhabdomyolysis, and change in HDL from baseline to 12 weeks. The registry record lists these as secondary outcomes. It does not post numerical results for the LDL change or HDL change in the registry record. The focus of the primary comparison is therefore narrower than the broader set of lipid and safety questions described in the study summary.

3. Trial Design

This was a Phase 4, randomized, parallel-group study with no masking. The registry record names the study as a prospective, open-label comparison of ezetimibe, niacin, and colestipol as adjunct therapy in lipid reduction. The study status is completed. Its recorded start is 2005-05, and its primary completion is 2008-01. The sponsor is Tuscaloosa Research & Education Advancement Corporation.

The three arms were statin with niacin, statin with colestipol, and statin with ezetimibe. The arm descriptions report niacin doses from 500-1500mg, with an average of 888mg; colestipol doses from 5-15gm, with an average of 9.5gm; and ezetimibe at 10mg, with an average of 10mg. The primary endpoint was assessed at 12 weeks. The record does not describe additional treatment or follow-up details beyond those details.

Randomized allocation is reported, but the registry record does not report how the random sequence was generated, whether allocation was concealed, or whether randomization was stratified. It also does not report a planned allocation ratio. The posted arm counts for the primary result are 9 for niacin, 9 for colestipol, and 10 for ezetimibe. The record lists overall enrollment as 30, but does not explain the relationship between enrollment and the arm counts in the primary result.

Because masking was none, the study was open label. This describes knowledge of treatment assignment; it does not establish whether the outcome assessment or analysis was otherwise protected from knowledge of group assignment. Such additional procedures are not reported in the registry record. The study is a comparison of adjunct therapies on background statin treatment, rather than a comparison of statin therapy with no treatment. Interpretation should remain within that design and the recorded endpoint.

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 had to be on max tolerated dose of a statin and need additional LDL lowering.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: intention to treat

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: 100% male, age 50 years or greater

6. Primary Endpoint

The registry lists the primary outcome as LDL Goal Attainment, measured over 12 weeks.

The primary endpoint is LDL goal attainment at 12 weeks. The registry record says each participant had an LDL goal calculated using NCEP ATP III guidelines, and identifies the primary measure as a number of participants. The posted result is the count of participants in each arm who attained that goal: 6 in the niacin group, 6 in the colestipol group, and 9 in the ezetimibe group. The corresponding arm counts listed for this outcome are 9, 9, and 10.

A goal-attainment endpoint turns an individual’s LDL result and assigned goal into a categorical outcome: the participant either attained the goal or did not. As a general statistical concept, this can make a guideline-based target directly interpretable, but it does not preserve the full size of each person’s LDL change. Two participants classified the same way may have had different LDL values or changes, and the count alone cannot show how close participants were to their goals. The record does not post the underlying LDL measurements or a numerical summary of change from baseline in the registry record.

The endpoint is relevant to the stated aim of assessing whether participants reached risk-based LDL goals. It should not be treated as interchangeable with the separate question of average LDL reduction from baseline. Nor does goal attainment alone describe the secondary outcomes concerning HDL, liver-function tests, or rhabdomyolysis. The stated primary population is intention to treat, but the record does not explain how missing measurements or participants without an endpoint value were handled.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What kind of outcome is being counted?

The primary measure is a binary participant-level outcome: attainment or non-attainment of an LDL goal calculated using NCEP ATP III guidelines. The registry reports the number attaining the goal in each group. A binary outcome condenses an individual result into a category. That can be useful when the clinical question is explicitly about reaching a target, but it discards detail about the measured LDL values and how far each participant was from the goal. The posted counts therefore answer a different question from a comparison of average LDL change.

For a randomized comparison, a statistical analysis would ordinarily quantify how different the groups appear and how uncertain that difference is. A confidence interval is a range of values compatible with the data and the specified statistical model; its width reflects precision under that model. A hypothesis test can assess how compatible the observed data are with a null hypothesis, but a p-value does not measure the size or clinical importance of an effect. Neither a confidence interval nor a p-value for the primary group comparison is reported in the registry record.

How should the group counts be read?

The registry records 6 participants attaining the goal among 9 in the niacin arm, 6 among 9 in the colestipol arm, and 9 among 10 in the ezetimibe arm. These are raw counts and the listed arm sizes. No additional proportion or comparative effect is calculated in this explanation. Counts alone do not account for sampling uncertainty, and the unequal listed group sizes are relevant when interpreting them. A formal comparison would need to state its effect measure, analysis method, assumptions, and handling of missing outcome data; these details are not reported in the registry record.

In general, a confidence interval around a group comparison helps distinguish a relatively precise estimate from one compatible with a broad range of possible differences. It does not guarantee that all sources of bias have been addressed. Randomization helps balance prognostic factors on average, but in a study with limited enrollment the realized groups can still differ by chance. Lack of masking may also matter for outcomes or decisions influenced by participant or investigator awareness. The record does not describe the detailed methods needed to assess these issues.

What does the record say about analysis?

The primary outcome identifies the population as intention to treat. As a general principle, intention-to-treat analysis aims to retain participants in their randomized groups, regardless of treatment adherence or changes after assignment. That principle is useful because removing participants based on post-randomization events can compromise the advantages of randomization. The label alone, however, does not show how the analysis was implemented. The registry record does not report the handling of missing primary outcomes, adherence, treatment discontinuation, or deviations from assigned therapy.

The record reports no analyses. It consequently does not identify a statistical test or model for the primary comparison, an adjustment for baseline factors, or a method for the secondary outcomes. It also does not report a prespecified analysis plan or say whether any analyses were adjusted for multiple comparisons. No inference should be attributed to an unreported model or test.

How do the planning illustrations differ from observed evidence?

Planning illustrations use assumptions to show how sample size might vary with the effect selected for detection and the desired statistical properties. They are design calculations, not findings from the randomized comparison. The stated illustration assumptions include a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation; the effect to detect is described as a stated fraction of the observed effect. Such illustrations are not observed power and do not demonstrate that the study was adequately sized for its actual objective. The registry record does not report the trial’s own sample-size justification, and numerical planning results are not included in the registry record.

As a general concept, power concerns the probability that a planned test will detect a specified effect under stated assumptions. It depends on the assumed effect, variability or event frequency, sample size, analysis, and significance threshold. Retrospective calculations based on the observed effect do not establish the probability that the completed study has correctly detected a true effect. A small observed difference can lead to a small planning estimate, while an exaggerated observed effect can make a study appear more informative than it was. Planning illustrations should therefore be separated from the actual evidence and from any claim about observed power.

Why can over-dispersion matter?

As a general statistical issue, over-dispersion occurs when observed variation is greater than a model assumes. A model that underestimates variation can produce overly narrow confidence intervals and overly optimistic tests. This is especially relevant to count outcomes when event rates vary across participants or clusters, but the primary endpoint is a participant-level binary goal-attainment measure, not a reported over-dispersed count model. The registry record does not describe a model or report a dispersion assessment. No claim that over-dispersion was present or addressed is warranted.

These methods principles clarify what would be needed for a full inferential reading, but they do not fill gaps in the registry record. The posted endpoint counts remain descriptive unless accompanied by a reported comparative analysis and its assumptions. A numerical difference between groups should not be recast as statistical significance, precision, or a causal estimate without those elements.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Niacin", "Colestipol", "Ezetimibe")
n      <- c(9, 9, 10)
events <- c(6, 6, 9)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Niacin  9  6  66.7  29.9  92.5  35.4  87.9  34.8  87.8
ARM  Colestipol  9  6  66.7  29.9  92.5  35.4  87.9  34.8  87.8
ARM  Ezetimibe  10  9  90.0  55.5  99.7  59.6  98.2  58.7  97.7

11. Multiplicity, Missing Data and Analysis Populations

The registry record names three secondary outcomes: liver-function-test elevation, incidents of rhabdomyolysis, and change in HDL from baseline to 12 weeks. It also lists four outcome measures in total, consistent with a primary measure and secondary measures, but it does not report an analysis for these outcomes. The registry record does not say whether the primary endpoint was the sole confirmatory test, whether secondary outcomes were exploratory, or whether any method was planned to address multiplicity.

As a general statistical concept, testing several outcomes can increase the chance of at least one apparently unusual result when all are interpreted as independent confirmatory findings. Methods for controlling or otherwise addressing multiplicity depend on the prespecified questions and analysis plan. Since those plans and results are not reported in the registry record, no adjustment or hierarchy of tests can be assumed. Numerical results for the listed secondary outcomes are not reported in the registry record.

The registry identifies the primary population as intention to treat, but does not explain missing-data handling. It does not report whether participants with missing LDL measurements were excluded, classified in a particular way, or included using an imputation method. The listed primary outcome arm counts are 9, 9, and 10, while overall enrollment is 30; the record does not explain the relationship between those figures. The extent and pattern of missing data are therefore not reported in the registry record.

For a complete assessment, readers would need to know how participants were assigned and analyzed, how missing outcomes were handled, which outcomes were prespecified, and what statistical comparisons were planned. These details cannot be inferred from the outcome names or the intention-to-treat label alone.

12. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

Most frequent non-serious adverse event terms

The posted serious-adverse-event figures list 0 affected participants among 10 at risk in each group: niacin, colestipol, and ezetimibe. These are the registry’s recorded counts for serious adverse events, not proof that no serious events occurred outside the recorded reporting period or under other definitions. The record does not provide further detail about event ascertainment or the time period used for these safety counts.

Deaths are not reported in the registry record. No serious adverse-event terms are listed. The adverse-event summary also lists other adverse events in 6 participants among 10 at risk with niacin, 3 among 10 with colestipol, and 3 among 10 with ezetimibe. These counts are distinct from the serious-event figures and should not be conflated with them. The registry record does not provide event descriptions or attribution details in the registry record.

Safety counts are descriptive. A zero recorded count in a group does not establish absence of risk, and comparisons across groups can be imprecise when the available group sizes are limited. The record does not report statistical comparisons of adverse events or a detailed safety analysis. These figures should therefore be read as the posted counts, without interpreting them as evidence that one regimen is safer than another.

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

The registry results show how many participants in each adjunct-treatment group were recorded as attaining an LDL goal at 12 weeks. They are 6 in the niacin group, 6 in the colestipol group, and 9 in the ezetimibe group. These counts provide a direct description of the primary endpoint, which was based on individual goals calculated using NCEP ATP III guidelines.

They do not establish that the groups differ statistically, that a difference is clinically important, or that the observed pattern was caused by the assigned adjunct therapy. The registry record reports no analyses and gives no confidence intervals or hypothesis-test results for the primary comparison. The available result also does not show the magnitude of LDL change, because goal attainment is not the same measure as change from baseline. Although the study summary describes LDL reduction, the posted primary result in the record is a count of goal attainment.

The result does not answer the full set of questions described in the study summary. The record names secondary outcomes concerning liver-function-test elevation, rhabdomyolysis, and change in HDL from baseline to 12 weeks, but numerical findings for those outcomes are not reported in the registry record. Nor does the record establish how any missing outcome information was handled. The endpoint is labeled intention to treat, but the implementation of that approach is not reported.

The randomized design is relevant because randomization is intended to support comparisons between treatment groups. However, the registry record does not report details of sequence generation or allocation concealment, and the study was unmasked. The recorded arm sizes for the primary outcome also do not account for overall enrollment without further explanation. These limitations constrain what can be concluded from the counts.

In short, the posted result is a description of goal attainment in the three groups, not a definitive ranking of treatments. It can motivate questions about the comparative outcomes, but a statistical conclusion requires a reported analysis, an account of uncertainty, and enough information about participants and missing data to judge how the result was obtained. No treatment recommendation follows from these registry counts alone.

14. Why This Trial Matters Statistically

This trial is statistically informative as an example of the distinction between a clinically framed endpoint and a complete comparative analysis. LDL goal attainment is tied to an individual target calculated using NCEP ATP III guidelines, so the outcome addresses whether participants reached a stated goal. Yet the posted result is a set of counts rather than a reported estimate of the difference between groups with its uncertainty. A clinically interpretable endpoint still needs an analysis that makes the comparative evidence clear.

The study also illustrates why endpoint definition matters. Goal attainment captures whether a threshold was reached, while LDL reduction from baseline captures the amount of change. These measures can tell different stories because categorizing a continuous measurement loses information about the magnitude of change and distance from the threshold. The study summary refers to both LDL reduction and goal achievement, but the primary result posted in the registry is goal attainment.

Reporting the analysis is essential for distinguishing descriptive findings from inferential claims. The registry identifies randomization and an intention-to-treat population, but it reports no analyses, confidence intervals, or statistical tests in the registry record. It also does not report missing-data handling, multiplicity procedures, or the trial’s sample-size justification. Those omissions limit assessment of precision, bias, and the strength of any comparison.

The record further provides a useful reminder that planning calculations based on an observed effect are not the same as observed evidence or prospective design justification. Planning illustrations depend on assumptions; they cannot substitute for a reported analysis of the trial outcomes. The most defensible statistical reading keeps these elements separate: design, endpoint, observed counts, uncertainty, and planning assumptions each answer different questions.

15. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The registry record leaves several trial-specific uncertainties that constrain interpretation. It reports randomized allocation, but does not describe sequence generation, allocation concealment, stratification, or the allocation ratio. Masking was none. The record does not describe how outcome assessment was conducted or whether any procedures were used to reduce the influence of treatment knowledge.

The primary outcome is labeled intention to treat, but implementation details are not reported. Overall enrollment is 30, while the primary endpoint lists arm counts of 9, 9, and 10. The record does not explain the relationship between these figures or state whether outcome data were unavailable for any participants. The missing-data method and the extent or pattern of missingness are not reported in the registry record.

The registry gives the number attaining the LDL goal but does not report a comparative estimate, confidence interval, p-value, or statistical model. It does not report baseline group characteristics or the individual LDL measurements underlying the goal-attainment outcome. The result therefore cannot show the size of LDL changes or the precision of group comparisons. The registry also does not report the trial’s own sample-size justification or enough information to assess whether the study was designed to detect a clinically meaningful difference.

Three secondary outcomes are named, but their numerical results and analyses are not included in the registry record. The record does not report how multiplicity was addressed or whether the secondary outcomes were designated as exploratory. Safety details are limited to counts; deaths are not reported, and no serious-event terms are listed. Event definitions, timing, and attribution are not described in the registry record.

These limitations are specific to the information recorded for this study. They do not show that particular procedures were absent; they mean the registry record does not report them. Conclusions should therefore be restricted to the descriptive counts and the design features that are explicitly recorded.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: A Prospective, Open Label Comparison of Ezetimibe, Niacin, and Colestipol as Adjunct Therapy in Lipid Reduction — NCT00203476.
• Registry record last updated 2014-08-12; status last verified 2014-08.
• Results first posted 2014-08-12.
• 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

NCT00203476 is a completed Phase 4 randomized, open-label, parallel-group comparison of niacin, colestipol, and ezetimibe as adjuncts to statin therapy. The record lists 30 participants enrolled, with a start date of 2005-05 and primary completion in 2008-01. The primary endpoint was LDL goal attainment at 12 weeks, based on individual goals calculated using NCEP ATP III guidelines.

The posted primary counts are 6 among 9 with niacin, 6 among 9 with colestipol, and 9 among 10 with ezetimibe. The registry record reports no analyses for the endpoint. It also names secondary outcomes concerning liver-function-test elevation, rhabdomyolysis, and HDL change from baseline to 12 weeks, but numerical results for those outcomes are not reported in the registry record. The serious adverse-event counts are 0 among 10 at risk in each group; deaths are not reported in the registry record.

The available information supports a descriptive account of the posted outcomes, but does not provide inferential comparisons, confidence intervals, or missing-data details.