ROMEO (Rosuvastatin in Metabolic syndrOme): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for ROMEO (Rosuvastatin in Metabolic syndrOme) (NCT00395486), a randomized phase 4 study. The primary outcome is Percentage Change From Baseline in Ratio of Apolipoprotein (ApoB/ApoA1) at Week 6.

2. Clinical Question

3. Trial Design

ROMEO was a phase 4, randomised, open-label, parallel-group, multicentre study. It compared rosuvastatin 10mg with atorvastatin 10mg in subjects with metabolic syndrome and raised LDL-C. The official title specifies a 6-week treatment period, and the primary outcome timeframe is baseline and 6 weeks. The registry lists enrollment of 258 participants. The study status is completed; its recorded start was 2006-09 and its primary completion was 2008-06.

Randomisation means treatment assignment was intended to be allocated by chance rather than chosen by participants or investigators. The method used to generate the allocation sequence and whether assignment was concealed before enrolment are not reported in the registry record. In an open-label study, participants and investigators are not masked to treatment assignment. That can matter for outcomes influenced by behaviour or judgement. The primary outcome is a laboratory-derived measure, but the record does not state whether laboratory personnel were masked to allocation.

A parallel-group design assigns participants to one treatment arm and follows those groups over the same study period; it is not a crossover design in which participants receive each treatment in sequence. The record identifies the two arms but does not provide further arm descriptions. The sponsor was AstraZeneca. The study's primary objective, as described in the registry, was to compare the effect of the two drugs on the ApoB/ApoA1 ratio after 6 weeks.

The record does not report the original sample-size justification, the planned statistical analysis methods, or the population definition used for the primary analysis. It also does not report details about treatment adherence, withdrawals, or the handling of participants with missing outcome measurements. These omissions limit how fully the planned design and the analysis conducted can be reconstructed from the registry record alone.

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: Enrolled patients to be randomized should complete 6-week dietary run-in periods. Also, LDL level should be ≥ 130mg/dl \& \< 220mg/dl and triglyceride should be \< 500mg/dl.

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 Percentage Change From Baseline in Ratio of Apolipoprotein (ApoB/ApoA1) at Week 6, measured over Baseline and 6 weeks.

The primary endpoint was percentage change from baseline in the ratio of apolipoprotein B to apolipoprotein A1 (ApoB/ApoA1) at week 6. Apolipoproteins are proteins associated with lipoprotein particles. A ratio combines information from both measures into one quantity, and a percentage change expresses how that quantity shifted relative to its baseline value. The registry says the endpoint was calculated using the ApoB and ApoA1 results, with samples sent to a central laboratory.

In general, a continuous endpoint such as percentage change retains information about the size of measured changes rather than reducing each participant's result to a binary category. Comparing mean changes between randomised groups can estimate the average difference in response over the study period. It does not describe every participant's response, and the group average can conceal variation between individuals.

The reported means were -44.4 for rosuvastatin and -36.5 for atorvastatin, each with a standard deviation. A negative percentage change denotes a decrease from baseline for the measured ratio. The registry describes the measure and timeframe but does not report baseline ApoB or ApoA1 values, the details of the percentage-change calculation, or a threshold defining a clinically meaningful change. Therefore, the endpoint provides a quantified laboratory comparison over 6 weeks, while its clinical interpretation requires context that is not reported in the registry record.

7. Results Posted in the Registry

• Atorvastatin: mean -36.50 versus -44.40 on control; difference 7.90 (95% CI 4.32 to 11.48), standardized effect d = 0.55; z-test p = <0.001.

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.

Percentage of Subjects Reaching Their LDL-C Target Goal

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Atorvastatin: 75.4% (92/122) versus 88.2% (112/127) on control; risk difference -12.8 percentage points (95% CI -22.3 to -3.3), risk ratio 0.86 (0.76–0.96); unadjusted two-proportion z-test p = 0.009.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the proportion with the event is statistically lower for Atorvastatin than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percentage of Subjects Reaching Their Low-Density Lipoprotein-C (LDL-C) and Non High-Density Lipoprotein-C (HDL-C) Target Goal

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Atorvastatin: 66.7% (32/48) versus 78.8% (41/52) on control; risk difference -12.2 percentage points (95% CI -29.5 to 5.2), risk ratio 0.85 (0.66–1.08); unadjusted two-proportion z-test p = 0.171.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Atorvastatin and the control. The interval gives the range of effects that remain compatible with the data.

Percentage Change of Glucose Level

• 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:
  • Atorvastatin: mean 2.78 versus -0.60 on control; difference 3.38 (95% CI 0.35 to 6.41), standardized effect d = 0.28; z-test p = 0.029.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Atorvastatin than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The secondary outcomes broaden the study's focus beyond the ApoB/ApoA1 ratio. They include LDL-C target attainment, a combined LDL-C and non-HDL-C target, glucose change, insulin-resistance measures using HOMA-R and QUICKI, and changes in LDL-C, total cholesterol, and HDL-C. Together, these outcomes describe several related but distinct aspects of lipid and metabolic measurements.

The posted secondary comparisons do not all tell the same statistical story. Some have unadjusted p-values below 0.05, while other comparisons have intervals that include no difference. This variation is not inherently contradictory: each outcome measures a different quantity, may have a different analysis population, and has its own uncertainty. The secondary results can be viewed as contextual evidence alongside the primary finding, but they should not be treated as independent confirmations of it.

Multiplicity matters because examining many outcomes creates more opportunities for a nominally small p-value to arise by chance. The registry lists 11 secondary outcomes and reports no secondary analyses in its reported-analyses listing. It does not state whether a hierarchy, correction, or other multiplicity strategy was used. Without that information, the individual unadjusted secondary p-values carry less weight than they would in a single prespecified comparison with a clearly reported analysis plan.

The secondary outcomes are most useful for describing the range of measurements recorded and identifying questions for further evaluation. They cannot establish that all measured metabolic dimensions changed in a consistent way, and they do not alter the definition of the primary endpoint. Differences in denominators also warrant care when comparing outcomes; the registry does not explain all outcome-specific analysis counts.

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

• Percentage of Subjects Reaching Their LDL-C Target Goal
• Percentage of Subjects Reaching Their Low-Density Lipoprotein-C (LDL-C) and Non High-Density Lipoprotein-C (HDL-C) Target Goal
• Percentage Change of Glucose Level
• Percentage Change of Insulin Resistance Using HOMA-R
• Percentage Change of Insulin Resistance Using QUICKI
• Percentage Reduction of Low-Density Lipoprotein-C (LDL-C)
• Percentage Change of Total Cholesterol (TC)
• Percentage Change of High-Density Lipoprotein-C (HDL-C)

9. Statistical Interpretation

10. Statistical Methods Explained

The primary results are reported as means and standard deviations for a continuous outcome. The mean is the arithmetic average of participant-level percentage changes within an arm. The standard deviation describes how dispersed those measurements are around the arm mean. It is not the same as the uncertainty around the mean: the standard error concerns uncertainty in the estimated mean and depends on both variability and the number of observations. The registry reports standard deviations and outcome counts for both primary arms.

What does the mean difference represent?

The comparison is expressed as atorvastatin minus rosuvastatin. With this direction, a positive difference means the atorvastatin group mean is higher than the rosuvastatin group mean. For the primary outcome, the difference is 7.9. Since both arm means are negative, the larger, less negative mean in the atorvastatin group corresponds to a smaller average decrease from baseline than the rosuvastatin mean. This is a comparison of group averages, not a statement that each participant experienced the same change. Reversing the subtraction order would reverse the sign, so the direction used to define a difference is essential to interpretation.

What does the confidence interval add?

A confidence interval gives a range of values compatible with the observed data under the assumptions of the method used to construct it. It conveys uncertainty about the estimated group difference rather than the spread of individual outcomes. The primary interval extends from 4.323 to 11.48 in the stated comparison direction. Because the interval does not include zero, it is consistent with a nonzero difference at the conventional two-sided 0.05 level. A confidence interval is not a guarantee that the true value lies in the reported range, and its width does not tell whether a difference matters clinically. That requires a meaningful-effect threshold, which is not reported in the registry record.

How should the p-value be understood?

The primary p-value is reported as <0.001. In general, a p-value is calculated under a null hypothesis, commonly a hypothesis of no group difference, and a specified statistical model. It measures how compatible the observed result is with that null model; it does not give the probability that the null hypothesis is true. A small p-value is not a measure of the size of the effect, the likelihood of benefit for an individual, or the quality of the study. The record labels the comparison as unadjusted and does not report the full analysis method used by the trial investigators.

What are the secondary comparisons?

The secondary outcomes use more than one type of summary. Continuous outcomes, such as percentage change in glucose, are presented as arm means and standard deviations, with mean differences for comparisons. Binary target outcomes are reported as percentages of participants reaching a goal; a risk difference compares the proportions in the two arms by subtracting one from the other. A risk difference of zero represents equal observed proportions. The uncertainty interval for a risk difference can include zero even when the arm percentages are not identical. The registry also lists ratios for the binary outcomes, but interpretation depends on the specific measure and comparison direction.

For the LDL-C target outcome, the recorded counts were 112 of 127 participants in the rosuvastatin arm and 92 of 122 in the atorvastatin arm. For the combined LDL-C and non-HDL-C target outcome, the recorded counts were 41 of 52 and 32 of 48, respectively. These are outcome-specific denominators, and they should not be treated as the overall arm sizes. The registry does not explain why the denominator for the combined target differs from the main primary outcome counts.

Why can variation and model assumptions matter?

For a continuous outcome, the uncertainty in a mean comparison is influenced by the dispersion of participant measurements and the number of observations. Greater variation generally makes a mean difference less precise when other factors are held constant. For a binary outcome, precision depends on the observed proportions and group counts. In general, normal approximations can be less reliable when data are sparse or proportions are near their boundaries. The registry record does not provide enough detail to assess whether alternative methods were used or whether assumptions were checked.

Over-dispersion is a general issue for count outcomes: it occurs when observed variation exceeds what a chosen model expects, and can make standard errors too small if ignored. The primary endpoint is continuous rather than a count, so that particular issue should not be presumed to apply to its analysis. More broadly, any statistical model relies on assumptions, and the registry does not report diagnostic checks, covariate adjustment, or the exact estimation procedure for these results.

The comparisons are described as unadjusted. That means they are presented without a reported adjustment for multiple comparisons or other covariates; the record does not establish whether the original investigator analysis used additional adjustments. The reported analyses list for the secondary outcomes is empty. Accordingly, the posted comparison statistics allow a straightforward group-level reading but do not reveal the complete statistical analysis plan, handling of missing observations, or analysis population definitions.

11. Confidence Intervals and Precision

The primary estimate is a mean difference of 7.9, comparing atorvastatin with rosuvastatin. Its 95% confidence interval runs from 4.323 to 11.48. The interval indicates the range of differences that remain compatible with the observed data under the calculation's assumptions. It is entirely above zero in this comparison direction, so the data are more consistent with a higher mean percentage change in the atorvastatin arm than in the rosuvastatin arm. Since both arm means are below zero, this corresponds to a greater average decrease in the rosuvastatin arm.

The interval gives more information than the p-value alone because it displays both direction and uncertainty in the estimated difference. It does not indicate the range of individual participant changes; those vary around the means, with standard deviations of 14.7 and 14.1. Nor does it determine whether the difference is important to patients or clinicians. The registry does not report a clinical-importance threshold for this endpoint, and the outcome is measured over 6 weeks.

For binary secondary outcomes, confidence intervals address uncertainty in differences between proportions. For example, the interval for the combined LDL-C and non-HDL-C target risk difference ranges from -0.295 to 0.052, including zero. In general, an interval that includes zero does not rule out no difference under the comparison's assumptions, while also allowing effects in either direction within the interval. The interpretation remains limited by the outcome-specific counts and the absence of reported multiplicity handling.

Precision is affected by sample size, variability, and the analysis method. The registry reports outcome counts, but does not explain missing observations or provide the original statistical analysis plan. Confidence intervals and p-values should therefore be read as summaries of the posted comparisons, not as a complete account of all uncertainty about study conduct or clinical meaning.

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 are illustrative estimates, not the trial's original design calculations. For this continuous primary outcome, the figures are participants per arm. They are based on a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set at the stated fraction of the observed effect. The registry does not report the assumptions or justification used when the trial was originally planned.

The 80% power column means the estimated number of participants per arm for a design that would have an 80% chance of detecting the specified effect under those planning assumptions, if that effect were the true effect. The 90% power column has the analogous meaning with a higher chance of detecting it. These are planning concepts, not guarantees for a particular trial, and they depend on the assumptions and statistical method used.

For the primary endpoint, planning for 100% of the observed effect gives 53 participants per arm for 80% power and 70 for 90% power. Planning for 75% of the observed effect gives 93 participants per arm for 80% power and 125 for 90% power. Planning for 50% of the observed effect gives 209 participants per arm for 80% power and 280 for 90% power. The pattern illustrates a general principle: smaller effects are harder to distinguish from random variation, so detecting them requires more participants under otherwise similar assumptions. These estimates are not observed power.

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 = 7.900; pooled standard deviation σ = 14.409.
2. n = 2 × (1.96 + 0.842)² × 14.409² / 7.900² = 52.2, rounded up to 53 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 <- 7.9                      # observed difference in means
sigma <- 14.4091949388377                     # 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(395486)
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 = 53 (80% power), 70 (90% power)
 75% of observed effect: n per arm = 93 (80% power), 125 (90% power)
 50% of observed effect: n per arm = 209 (80% power), 280 (90% power)
power.t.test: 53.2 
Simulated power at n = 53 per arm: 0.795 (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 identifies one primary endpoint and lists secondary outcomes, but the reported-analyses listing for the secondary outcomes is empty. It does not report whether the investigators used a hierarchical testing strategy, adjusted p-values, or another method to address multiple comparisons. A multiplicity plan is important because the chance of finding at least one apparently unusual result can increase when many hypotheses are tested. In general, adjustment methods control that issue in different ways and may change how individual p-values or intervals are interpreted. No particular method should be assumed for this study.

The record also does not report the original statistical analysis plan, the analysis population for the primary or secondary outcomes, or whether analyses were intention-to-treat, per-protocol, or based on another population. It does not describe how missing outcome values were handled, whether participants were excluded from particular analyses, or how withdrawals were treated. These details matter because an analysis based on only participants with available measurements can differ from one using a prespecified approach to incomplete data.

There are outcome counts for the primary result and some secondary measures, but counts alone do not explain why data may be unavailable. The primary outcome reports 127 participants in the rosuvastatin arm and 122 in the atorvastatin arm, while the combined target outcome reports smaller arm counts. The reason for these differences is not reported in the registry record. No interim analyses or stopping rules are described in the registry record.

These omissions do not establish that a procedure was or was not used; they mean the procedure is not reported in the registry record. Consequently, the posted p-values and confidence intervals can be interpreted as unadjusted comparisons, but the available record cannot establish how the investigators handled multiplicity, missing data, or analysis populations in their full protocol and analysis.

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.

Most frequent serious adverse event terms

Serious events with the highest arm-level rate: arrhythmia (0.8%), enteritis (0.8%), gastroenteritis (0.8%), haemorrhoids (0.8%), syncope (0.8%).

The registry reports serious adverse events for 0 of 129 participants in the rosuvastatin group and 4 of 124 in the atorvastatin group. It reports other adverse events affecting 0 of 129 and 0 of 124 participants, respectively. These are the posted counts; the record does not provide further event-level descriptions for the serious events in these arms beyond listing serious-event terms.

The serious-event terms listed are arrhythmia, enteritis, gastroenteritis, haemorrhoids, and syncope, each recorded as 0.8%. These percentages should be read as registry-reported figures, not as estimates of comparative risk from a formal analysis. The record does not report a comparative statistical assessment of safety or enough detail to attribute individual events to treatment. Death counts are not reported in the registry record.

Safety counts are descriptive and should be interpreted with the study's size and 6-week timeframe in mind. A count of zero in the posted data does not establish that an event cannot occur, and the record does not provide longer-term safety follow-up. These figures describe what was recorded in this trial; they do not support conclusions about safety outside the study context.

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

The primary comparison shows that the recorded average percentage change in ApoB/ApoA1 was more negative in the rosuvastatin arm than in the atorvastatin arm over 6 weeks. The estimated mean difference, confidence interval, and unadjusted p-value describe the direction and statistical precision of that short-term group-level contrast. They do not show that each participant had the same response, and they do not by themselves establish the practical or clinical importance of the difference.

The measured endpoint is a laboratory ratio, not a direct measure of how participants felt or functioned. The registry does not report a clinically meaningful threshold for change in this ratio or provide longer-term outcomes. It also does not report the detailed participant characteristics and eligibility criteria needed to judge how closely the study population may resemble other populations. Conclusions should therefore remain tied to the population and duration described.

The secondary outcomes add measurements of lipid targets and metabolic variables, but the record does not report multiplicity procedures, analysis populations, or missing-data handling. Those gaps limit how confidently the secondary comparisons can be treated as confirmatory. Similarly, the safety results are counts over the recorded study period and do not constitute a comprehensive comparison of long-term safety.

In general, randomisation supports a comparison between treatment groups by reducing systematic differences in expectation, but the registry's description does not provide enough detail to assess sequence generation, concealment, adherence, or all sources of bias. Open-label assignment is relevant to outcomes that may be affected by knowledge of treatment; the central laboratory description offers some information about how samples were handled but does not say whether laboratory personnel were masked.

Thus, the posted data support a specific statistical reading of a short-term laboratory endpoint. They do not establish broader effects, individual outcomes, long-term consequences, or conclusions for groups not characterized in the registry record.

17. Why This Trial Matters Statistically

This trial is a useful example of the distinction between an endpoint's measured scale and its clinical interpretation. The primary outcome is a percentage change in a ratio, reported as a group mean with standard deviations. Understanding the subtraction direction is necessary to interpret the sign of the between-group difference: the comparison is atorvastatin minus rosuvastatin, while both group averages represent decreases from baseline.

It also illustrates how a confidence interval and p-value answer related but different questions. The interval presents a range of plausible values for the contrast under the method's assumptions, while the p-value summarizes compatibility with a no-difference model. Neither alone identifies a clinically important threshold. The interval's direction and width, together with the outcome scale and study context, are more informative than a significance label alone.

The registry's secondary outcomes show why multiple testing and outcome-specific denominators deserve attention. A set of related measures may generate findings with differing apparent strength, and the meaning of a nominal p-value depends partly on how many comparisons were planned and how they were interpreted. The record does not report the full analysis plan or multiplicity handling, making restraint especially important when drawing conclusions from secondary results.

Finally, the record separates the trial's reported results from its planning details. Illustrative sample-size calculations based on observed effects are not the same as original design assumptions, and they are not observed power. This distinction is central to statistical reading: planning estimates describe what a future design might require under stated assumptions, whereas the trial outcomes describe observed group data.

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.

Several trial-specific details that would aid interpretation are not reported in the registry record. The record does not provide the detailed eligibility criteria, baseline characteristics, original sample-size justification, or full statistical analysis plan. Without these, the target population, planned estimand, and relation between design assumptions and final analyses cannot be fully assessed.

The study was open-label, and the record does not state whether laboratory personnel assessing ApoB and ApoA1 were masked. It describes central laboratory handling but does not report details of quality control or whether outcome assessors were blinded. The method of random sequence generation and allocation concealment is also not reported in the registry record.

Outcome counts differ across some reported measures, and the reason for those differences is not reported. The record does not explain missing data, exclusions, withdrawals, adherence, or the analysis population. It does not report whether covariate adjustment or sensitivity analyses were undertaken. These omissions prevent a full assessment of the robustness of the posted comparisons.

The primary outcome is assessed at 6 weeks, so the results address a short-term measurement only. The registry does not provide longer-term follow-up for the primary endpoint. The listed secondary outcomes increase the number of comparisons, but multiplicity handling is not reported. Safety information is also limited to the posted counts and listed serious-event terms; deaths are not reported in the registry record, and no comparative safety analysis is described.

These limitations concern what can be established from the registry record. They do not prove that unreported procedures were absent, but they constrain how completely the design and results can be appraised.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: ROMEO (Rosuvastatin in Metabolic syndrOme) — NCT00395486.
• Registry record last updated 2011-07-11; status last verified 2011-06.
• Results first posted 2011-06-16.
• 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

ROMEO was a completed phase 4, randomised, open-label, parallel-group, multicentre study sponsored by AstraZeneca. It enrolled 258 participants with metabolic syndrome and raised LDL-C and compared rosuvastatin 10mg with atorvastatin 10mg over 6 weeks.

The primary endpoint was percentage change from baseline in ApoB/ApoA1 at week 6. The reported arm means were -44.4 for rosuvastatin and -36.5 for atorvastatin; the mean difference, expressed as atorvastatin minus rosuvastatin, was 7.9, with a 95% confidence interval from 4.323 to 11.48 and an unadjusted p-value of <0.001.

The registry also lists secondary lipid and metabolic outcomes and descriptive adverse-event counts. The original sample-size rationale, multiplicity approach, missing-data handling, and analysis populations are not reported in the registry record.