Evaluation of LDL Cholesterol in Patients Switched From 10 to 5 Milligrams of Zetia (Ezetimibe): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Evaluation of LDL Cholesterol in Patients Switched From 10 to 5 Milligrams of Zetia (Ezetimibe) (NCT00762229), a randomized na study. The primary outcome is LDL Cholesterol.

2. Clinical Question

3. Trial Design

This was a randomized, parallel-group study comparing ezetimibe 5 mg with ezetimibe 10 mg. The 5 mg dose was formulated by splitting a 10 mg tablet in half; the 10 mg group received a whole tablet. The registry records no masking, so the study was open-label. The recorded phase is NA. Enrollment was 39, and the study status is completed.

The study description identifies a 4-week evaluation of LDL cholesterol following conversion from the 10 mg dose to the split-tablet 5 mg dose. The listed start is 2007-07 and the primary completion is 2008-09. These dates describe the registry record, but do not supply details about recruitment duration, follow-up procedures, or the timing of any measurements other than the stated outcome timeframe.

Outcome arm counts are reported as 14 for ezetimibe 10 mg and 22 for ezetimibe 5 mg. The adverse-event groups have different at-risk counts. The registry record does not explain why the reported counts differ from one another or from the enrollment figure, or whether they reflect exclusions, missing measurements, or distinct analysis populations. Those reasons are not reported in the registry record.

The sponsor is Bronx VA Medical Center. No protocol details are reported in the registry record about eligibility criteria, allocation concealment, adherence, co-interventions, or the planned statistical analysis. Randomization supports a comparative design, but the record alone does not show how those design features were implemented.

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: The drug was prescribed once daily. No patients were excluded after randomization

Overall Study

Reasons for not completing this period:

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 LDL Cholesterol, measured over 4 weeks.

The primary endpoint is LDL cholesterol, reported as a mean in mg/dL at 4 weeks. LDL cholesterol is a continuous measure: individual values can vary across a range rather than being limited to categories such as present or absent. The registry reports the mean and standard deviation for each group. The mean describes the group’s central level, while the standard deviation describes how spread out individual measurements are around that mean.

LDL cholesterol is the central measure because the study’s stated purpose was to compare the effect on LDL levels of continuing ezetimibe 10 mg or converting to a split-tablet 5 mg dose. A between-group comparison addresses whether the observed average levels differ at the stated follow-up time. It does not by itself describe every participant’s response or establish what happened at other times.

The registry record does not report a clinically meaningful difference threshold for this endpoint, nor does it explain how such a threshold was selected. Without that context, statistical uncertainty can be described, but the clinical importance of a particular difference cannot be determined from the posted results alone.

7. Results Posted in the Registry

• Ezetimibe 5 mg: mean 97.00 versus 103.00 on control; difference -6.00 (95% CI -26.25 to 14.25), standardized effect d = -0.18; z-test p = 0.561.

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.

Total Cholesterol

• 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:
  • Ezetimibe 5 mg: mean 167.00 versus 180.00 on control; difference -13.00 (95% CI -40.17 to 14.17), standardized effect d = -0.30; z-test p = 0.348.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Ezetimibe 5 mg and the control. The interval gives the range of effects that remain compatible with the data.

Total cholesterol is the one secondary endpoint posted, measured at the same 4-week timeframe. The broad direction of its group comparison is concordant with the primary LDL cholesterol comparison: the posted mean is lower in the split-tablet 5 mg group than in the whole-tablet 10 mg group. As with the primary outcome, the secondary comparison is uncertain, and its posted interval includes values on both sides of no difference.

This pattern offers some consistency across the two reported cholesterol measures, but it should not be treated as independent confirmation of the primary result. The endpoints are related measures, and results that move in the same direction can still be imprecise. The record does not report a formal joint analysis or a plan for how the secondary result was intended to support interpretation of the primary endpoint.

The secondary comparison is unadjusted. When several outcomes or comparisons are examined, the chance of seeing an apparently notable result by chance can increase. An unadjusted result does not account for the full set of outcomes considered, and the registry record does not report a multiplicity strategy. This means secondary findings generally carry less confirmatory weight than a prespecified primary endpoint, particularly when the analysis plan and hierarchy among endpoints are not reported.

The record lists total cholesterol as a secondary outcome and reports no formal analysis records. It does not say whether additional measures were collected but not posted, whether the secondary outcome was prespecified, or how missing secondary measurements were handled. For that reason, the secondary endpoint is best read as supportive descriptive context rather than as a separate definitive test of the dose comparison. Its agreement in direction with the primary measure does not resolve the primary estimate’s uncertainty.

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

• Total Cholesterol

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous, so the posted group summaries use means and standard deviations. A mean provides a single summary of the observed values in a group. A standard deviation describes how dispersed those values are around the mean. These quantities answer different questions: the mean describes the average level, while the standard deviation reflects variability among measurements. Neither alone indicates how precise the between-group comparison is.

The registry reports 103.0 mg/dL as the mean for ezetimibe 10 mg and 97.0 mg/dL for ezetimibe 5 mg. The comparison is stated as the 5 mg group relative to the 10 mg group, with a mean difference of -6.0 mg/dL. The sign is meaningful only alongside that direction: a negative estimate corresponds to a lower posted mean for the 5 mg group. It should not be interpreted as a change from baseline, because a baseline-to-follow-up comparison is not reported in the record.

A confidence interval gives a range of values reasonably compatible with the observed data under the statistical method used. For the mean difference, the reported interval is -26.25 to 14.25 mg/dL. It includes zero, the value corresponding to no mean difference, and it also includes differences on either side of zero. This wide span signals that the estimate is imprecise: the data do not narrow the plausible between-group difference to a single direction or a small range. A confidence interval is not a guarantee that the true effect lies inside the particular interval, nor does it assign a probability to each value within it.

The unadjusted p-value for the primary comparison is 0.561. A p-value describes how unusual data at least as inconsistent with a specified no-difference model would be, if that model and the test assumptions held. It does not measure the size or clinical importance of an effect, and it is not the probability that the no-difference model is true. The p-value should be interpreted together with the estimate and interval, not as a stand-alone decision rule. The registry record does not report a multiplicity adjustment or a prespecified decision threshold for interpreting this result.

The comparison includes a pooled standard deviation of 33.35 mg/dL and a standardized effect estimate of -0.180. Standardizing expresses the mean difference relative to the variation used in the comparison, allowing the estimated separation to be considered in relation to the spread of measurements. It is not a separate clinical endpoint, and it does not replace the mean difference in mg/dL. A standardized effect can be especially sensitive to the variability estimate when groups are small, so its numerical value should be read alongside the original measurement scale and confidence interval.

The design is recorded as randomized, parallel, and unmasked. In general, random assignment is intended to make treatment groups comparable at the start of a trial, while a parallel design means participants remain in their assigned group rather than crossing between study treatments. Randomization does not by itself guarantee that groups are balanced in a small trial, and the record does not provide baseline characteristics to assess their comparability. With no masking, awareness of the assigned treatment may influence behavior, care, or measurement procedures; the record does not describe safeguards against those possibilities.

The reported group sizes are 14 and 22 for the primary endpoint. The registry also lists a total enrollment of 39. The reason these counts do not align is not reported in the registry record. In general, missing outcome measurements or exclusions can affect both the analysis population and the interpretation of randomized comparisons. The record does not identify whether the analysis was intention-to-treat, per-protocol, or based on participants with available measurements, and it does not describe imputation or other missing-data methods.

No formal analysis records are listed, even though outcome summaries and a comparison are posted. The record does not specify a regression model, covariate adjustment, test implementation, or prespecified analysis plan. Accordingly, the mean difference, interval, and p-value can be described as posted, but the full analysis method cannot be independently reconstructed from the registry record. The registered comparison should not be extended to unreported analyses or assumptions.

More generally, variability matters because uncertainty in a mean difference depends not only on the observed separation between group means but also on the spread of the measurements and the amount of information available. When measurements are highly variable relative to the difference, estimates tend to be less precise. The reported standard deviations and confidence interval convey that the observed group averages come with substantial uncertainty. This principle is general; the specific interpretation remains anchored to the trial’s posted estimates.

11. Confidence Intervals and Precision

The primary mean difference is -6.0 mg/dL, with a 95% confidence interval from -26.25 to 14.25 mg/dL. The estimate is centered on a modest observed separation, but the interval covers a much broader range, including values that favor either group. The interval therefore conveys more than the point estimate alone: it shows that the study does not pin down the direction or size of the difference precisely.

The interval includes zero, which is consistent with the unadjusted p-value of 0.561. Neither result establishes that the group means are equal. An interval that includes zero can still be compatible with meaningful differences in either direction, depending on what differences matter clinically. The registry record does not report a threshold for clinical importance, so the interval cannot be classified against such a threshold.

The group standard deviations are 24.0 mg/dL for ezetimibe 10 mg and 38.0 mg/dL for ezetimibe 5 mg. Variation in individual measurements is an important part of why a group comparison may be uncertain. The available arm counts are 14 and 22, and the record does not describe the outcome analysis population or the reason counts differ from overall enrollment. That reporting gap further limits assessment of the precision and representativeness of the estimate.

A confidence interval addresses uncertainty in an estimated group difference under a statistical method; it does not capture every possible source of uncertainty, such as incomplete outcome reporting, departures from assumptions, or limitations in generalizing beyond the study participants. The posted interval is useful for judging statistical precision, but it cannot by itself settle clinical relevance or equivalence.

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 planning figures describe participants per arm, not total events. They are illustrative calculations based on the observed effect, not the trial’s original design assumptions. The calculation assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, a normal approximation, and detection of a stated fraction of the observed effect. The registry record does not report the trial’s own sample-size justification or original planning assumptions.

The 80% power column gives the number of participants per arm estimated to be needed for an 80% chance of detecting the specified effect under the stated assumptions, if that effect is real and the assumptions hold. The 90% power column gives the corresponding planning number for a 90% chance. These are design illustrations, not estimates of how likely the completed trial was to find a difference. They are not observed power.

The display considers planning for 100%, 75%, and 50% of the observed effect. A smaller effect is harder to distinguish from random variation, so planning to detect a smaller effect requires more participants. The curve expresses this same relationship across effect sizes: the participant requirement rises as the effect to detect becomes smaller. These figures depend on the observed estimate, which is itself uncertain, and should not be treated as evidence that the observed effect is the true or clinically important target.

The illustrations also do not indicate how many participants were actually enrolled or analyzed; those counts are reported separately in the registry record. They cannot show whether the original trial was adequately planned, because its own design assumptions and justification are not reported in the registry record.

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 = -6.000; pooled standard deviation σ = 33.348.
2. n = 2 × (1.96 + 0.842)² × 33.348² / -6.000² = 484.9, rounded up to 485 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 <- -6                      # observed difference in means
sigma <- 33.348427954835                     # 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(762229)
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 = 485 (80% power), 650 (90% power)
 75% of observed effect: n per arm = 863 (80% power), 1,155 (90% power)
 50% of observed effect: n per arm = 1,940 (80% power), 2,597 (90% power)
power.t.test: 485.9 
Simulated power at n = 485 per arm: 0.802 (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. Multiplicity, Missing Data and Analysis Populations

The registry record does not report a plan for handling multiplicity across the primary and secondary outcomes, or any other comparisons. Multiplicity arises when more than one statistical question is examined: even if each test is interpreted using the same nominal threshold, considering many results can make chance findings more likely. A prespecified hierarchy, adjustment, or clear designation of confirmatory and exploratory outcomes can help readers understand how results should be weighed. No such approach is reported in the registry record.

The primary outcome is identified as LDL cholesterol, and total cholesterol is listed as a secondary outcome. The record does not describe whether the secondary endpoint was prespecified in the protocol, whether additional endpoints were measured, or whether analyses were conducted but not posted. The posted comparison p-values are unadjusted, so they should not be interpreted as if they account for testing multiple outcomes.

Missing-data handling is also not reported. The outcome counts are 14 and 22, while overall enrollment is 39; adverse-event at-risk counts are reported separately. The registry does not explain these differences or state whether all randomized participants were included in the efficacy analysis. It does not report withdrawals, reasons for missing measurements, imputation, or sensitivity analyses. Without those details, the extent to which missing outcomes might affect the estimated comparison cannot be assessed.

The analysis population is not specified. In particular, the record does not say whether the primary analysis followed an intention-to-treat principle, included only participants who completed follow-up, or used another population definition. These choices can affect the interpretation of a randomized comparison. The registry also does not report a detailed statistical analysis plan, interim analyses, or any method for adjusting the primary comparison. Those details are not reported in the registry record, so they should not be inferred from the posted summaries.

15. 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 5% reporting threshold.

The adverse-event figures report zero serious adverse events among 15 participants at risk in the ezetimibe 10 mg group and zero among 23 participants at risk in the ezetimibe 5 mg group. The figures for other adverse events are also zero in both groups, with the same at-risk counts. These are counts within the reported safety groups, not evidence that such events are impossible or that the groups have identical safety profiles.

The registry record does not report death counts. The safety denominators differ from the primary outcome arm counts and from the overall enrollment figure; the reasons are not reported in the registry record. The record also does not list serious adverse-event terms. With the reported counts and limited follow-up description, the safety information should be read as a report of observed events within the recorded groups, not as a precise estimate of uncommon harms or as a complete account of safety.

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

The results describe a randomized comparison of ezetimibe 5 mg, made by splitting a 10 mg tablet, with a whole 10 mg tablet. At 4 weeks, the posted LDL cholesterol means were different numerically, but the estimated difference is uncertain. The confidence interval includes zero and extends in both directions, so the data do not clearly distinguish a lower average in one group from a higher average in the other.

This does not establish that the two doses have equivalent effects. Equivalence requires a prespecified range of differences considered acceptably small, together with an analysis designed to assess whether the uncertainty lies within that range. The registry record does not report an equivalence margin or an equivalence analysis. Likewise, the posted result does not establish non-inferiority, which also requires a defined margin and an appropriate analysis.

The result also does not establish that a particular participant would experience the group average, or that the observed comparison would apply to people outside the studied population and conditions. Individual measurements vary, and the record provides limited information about eligibility, baseline characteristics, adherence, and missing outcomes. The recorded four-week timeframe does not address longer-term outcomes.

The findings should not be reduced to the p-value alone. The estimate gives the observed direction and magnitude on the LDL scale, while the confidence interval communicates that a wide range of differences remains compatible with the data. The registry record does not specify what magnitude of change would be clinically meaningful, so the statistical result cannot settle that question.

In short, the posted data are a limited, short-term description of the recorded groups. They do not prove no difference, demonstrate equivalence, or establish an effect beyond the measured outcome and timeframe. The sample-size illustrations are planning calculations based on the observed effect; they do not change the uncertainty of the completed comparison.

17. Why This Trial Matters Statistically

This trial is statistically instructive because a small observed difference and an imprecise estimate are not the same as evidence of equivalence. The primary estimate is negative, but the confidence interval crosses zero and includes differences in both directions. Reading the point estimate without its interval could overstate certainty about the direction or size of the comparison.

The study also shows why standard deviations and group counts matter when interpreting mean comparisons. The reported measurements vary within each arm, and the outcome counts are limited. In general, a comparison can remain uncertain when the observed separation between group means is modest relative to variation and the available information. The interval makes that uncertainty visible on the original measurement scale.

Another statistical lesson is the importance of connecting the analysis to the design. Randomization is a useful basis for comparison, but interpretation also depends on clear reporting of the analysis population, missing outcomes, endpoint hierarchy, and planned methods. Those details are not reported in the registry record. Their absence makes it harder to assess how the posted summaries relate to all randomized participants and how multiple outcomes were considered.

Finally, the planning illustrations should not be mistaken for a retrospective judgment about the trial’s power. They use the observed effect and stated calculation assumptions, while the original design justification is not reported. Because the observed effect is uncertain, planning directly from it can also produce unstable estimates of the number needed for future research. The illustrations are best understood as conditional examples of how target effect size and desired power influence sample-size planning.

18. 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 important details unavailable for interpreting this specific study. Although enrollment is listed as 39, the primary outcome counts are 14 and 22, and the safety groups have their own at-risk counts. The record does not explain these differences or report participant flow, exclusions, withdrawals, or reasons for missing measurements. This limits assessment of whether the posted outcome summaries represent all randomized participants.

Eligibility criteria and baseline characteristics are not reported in the available record. It is therefore not possible to assess how similar the assigned groups were on measured characteristics before treatment, or how well the participants represent other populations. The record also does not provide details about adherence to the assigned dose, tablet splitting, or other care during follow-up.

The trial is described as unmasked, but no information is reported about blinding of outcome measurement or other protections against differences in study procedures. The primary outcome is measured at 4 weeks, and longer-term results are not reported. The record also does not describe the rationale for selecting this follow-up time or provide results for outcomes beyond the listed cholesterol measures.

The analysis plan, original sample-size justification, missing-data methods, multiplicity strategy, and analysis population are not reported in the registry record. The absence of these details does not establish that no such plans or methods existed; it means they cannot be evaluated from the registry entry. The study’s relatively small reported outcome groups and wide primary confidence interval further limit precision. These limitations constrain conclusions to the posted short-term summaries rather than supporting a definitive claim about equivalence or the size of a lasting effect.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Evaluation of LDL Cholesterol in Patients Switched From 10 to 5 Milligrams of Zetia (Ezetimibe) — NCT00762229.
• Registry record last updated 2013-06-14; status last verified 2013-06.
• Results first posted 2013-06-14.
• 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.

22. Record Summary

The registry record describes a completed randomized, parallel-group, unmasked study sponsored by Bronx VA Medical Center. It compared a whole ezetimibe 10 mg tablet with ezetimibe 5 mg made by splitting a 10 mg tablet. The listed enrollment was 39, and the primary outcome was LDL cholesterol in mg/dL at 4 weeks.

The posted primary comparison estimates a mean difference of -6.0 mg/dL for 5 mg compared with 10 mg, with a 95% confidence interval from -26.25 to 14.25 mg/dL and an unadjusted p-value of 0.561. The interval indicates substantial uncertainty and does not establish equivalence. Total cholesterol is the listed secondary endpoint. The registry record does not report the original sample-size justification, analysis population, missing-data methods, or multiplicity plan.