Study to Compare the Efficacy and Safety of Pitavastatin and Pravastatin in Elderly Patients: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study to Compare the Efficacy and Safety of Pitavastatin and Pravastatin in Elderly Patients (NCT00257686), a randomized phase 3 study. The primary outcome is Percent Change From Baseline in LDL-C.

2. Clinical Question

3. Trial Design

This was a phase 3 randomized, quadruple-masked, parallel-group study, recorded as completed. The registry lists an enrollment of 962. It identifies Kowa Research Europe as the sponsor, gives a start date of 2005-09, and lists primary completion in 2006-05. The condition was hypercholesterolemia or combined dyslipidemia, and the stated purpose was to compare the efficacy and safety of pitavastatin with pravastatin in elderly patients.

Six dose-specific arms are listed: pitavastatin 1 mg, pravastatin 10 mg, pitavastatin 2 mg, pravastatin 20 mg, pitavastatin 4 mg, and pravastatin 40 mg. Each regimen is described as once daily. The official title refers to comparisons following up-titration. The timing, schedule, and rules for any titration are not reported in the registry record, so the exact sequence of doses cannot be reconstructed from the available description.

Random allocation means treatment assignment was intended to be determined by chance rather than by participant or clinician choice. Masking is recorded as quadruple, but the registry does not identify which groups of people were masked or describe how masking was maintained. A parallel design means the listed treatment groups were compared as separate arms; crossover periods are not described. Further details of allocation concealment, stratification, adherence, concomitant care, and trial conduct are not reported in the registry record.

The primary endpoint was measured from baseline to 12 weeks. The registry also lists percent change from baseline in total cholesterol as a secondary outcome. It does not report the trial's original sample-size justification, the planned statistical model, interim analyses, or detailed analysis populations. Those omissions limit what can be inferred about how the trial was planned and how the posted summaries relate to the original protocol.

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.

Overall Study

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.

Only the first 6 of 7 groups are shown.

6. Primary Endpoint

The registry lists the primary outcome as Percent Change From Baseline in LDL-C, measured over Baseline to 12 weeks.

The primary endpoint is percent change from baseline in LDL-C, or low-density lipoprotein cholesterol, measured over the period from baseline to 12 weeks. It is reported as a mean with a standard deviation for each arm. This endpoint expresses average change relative to each participant's baseline level, then summarizes those changes across the arm. A negative mean indicates an average decrease from baseline; the size and precision of that average are distinct from the amount of variation among participants.

As a general statistical rationale, a continuous biomarker can capture the direction and magnitude of change without reducing each participant's result to a binary category. Comparing arm means therefore addresses whether the average recorded change differed between assigned regimens. The standard deviation helps describe how dispersed individual changes were around each arm's mean, but it is not a confidence interval and does not show the uncertainty of the arm mean by itself.

The registry reports the measurement timeframe and summary type, but does not give the assay method, rules for handling values outside expected ranges, or a detailed definition of the analysis population. It also does not report whether the primary endpoint was assessed using an adjusted model. The posted values should therefore be read as the registry's arm-level summaries and unadjusted comparisons, rather than as a complete account of the original endpoint analysis.

7. Results Posted in the Registry

• Pravastatin 10 mg: mean -22.41 versus -31.43 on control; difference 9.02 (95% CI 5.86 to 12.18), standardized effect d = 0.72; z-test p = <0.001.
• Pitavastatin 2 mg: mean -38.99 versus -31.43 on control; difference -7.56 (95% CI -9.91 to -5.21), standardized effect d = -0.61; z-test p = <0.001.
• Pravastatin 20 mg: mean -28.83 versus -31.43 on control; difference 2.60 (95% CI -0.14 to 5.34), standardized effect d = 0.22; z-test p = 0.063.
• Pitavastatin 4 mg: mean -44.31 versus -31.43 on control; difference -12.88 (95% CI -15.34 to -10.42), standardized effect d = -1.01; 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.

Percent Change From Baseline in TC

• 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:
  • Pravastatin 10 mg: mean -15.34 versus -22.19 on control; difference 6.85 (95% CI 4.40 to 9.30), standardized effect d = 0.71; z-test p = <0.001.
  • Pitavastatin 2 mg: mean -26.68 versus -22.19 on control; difference -4.49 (95% CI -6.22 to -2.76), standardized effect d = -0.49; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Pravastatin 10 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Pitavastatin 2 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The registry lists percent change from baseline in total cholesterol as a secondary endpoint, measured over the same baseline-to-12-week period as the primary endpoint. Across the six arms, the posted mean changes are negative. The available summary follows a broad pattern in which the pitavastatin arms have more negative means than the corresponding pravastatin dose arms. That direction is consistent with the general pattern of the primary LDL-C summaries, but total cholesterol and LDL-C are distinct measures and should not be treated as interchangeable outcomes.

The posted unadjusted secondary comparisons are limited to pravastatin 10 mg and pitavastatin 2 mg relative to pitavastatin 1 mg. Both are accompanied by p-values less than 0.001 and confidence intervals that exclude zero. The registry does not post inferential comparisons for the remaining total-cholesterol arms. Accordingly, the secondary summaries add context to the primary outcome but do not provide a complete set of pairwise statistical tests across all regimens.

Secondary findings generally carry less confirmatory weight than a prespecified primary endpoint, especially when many outcomes or contrasts are examined. As a general statistical concern, examining multiple hypotheses increases the chance that at least one result will appear noteworthy by chance if no adjustment or hierarchy is used. The registry does not report whether multiplicity was addressed, whether secondary outcomes were prespecified in a detailed analysis plan, or how missing secondary measurements were handled. The posted secondary p-values should therefore be regarded as unadjusted evidence rather than definitive confirmation of a broader pattern.

The registry identifies the total-cholesterol measure but does not report a complete analysis plan or clinical-importance threshold for it. The secondary results can describe whether the observed arm averages move in a similar direction to the primary measure, but they cannot independently establish clinical outcomes or compensate for uncertainty in the primary analysis. They are best read as supportive descriptive information, with the stated limitations on inference and reporting.

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

• Percent Change From Baseline in TC

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is a continuous variable summarized by its mean and standard deviation. In general, the mean gives the arithmetic average of participant-level changes, whereas the standard deviation describes how much those changes vary around the mean. These summaries answer different questions: a mean locates the center of the arm's observed results, while a standard deviation describes their spread. A relatively narrow spread does not itself establish a precise difference between arms, because uncertainty in a comparison also depends on how many observations contribute and how the comparison is estimated.

What does a mean difference represent?

The posted unadjusted contrasts compare each listed arm with pitavastatin 1 mg. For this outcome, the estimate corresponds to the difference between the arm means. Its sign reflects which mean is more negative: a positive estimate occurs when the comparator's mean is less negative than the reference mean, while a negative estimate occurs when it is more negative. This is a descriptive orientation, not a ranking of clinical value. The contrasts do not constitute all pairwise comparisons among the six arms, and the record does not report a model adjusting for baseline values or other covariates.

In general, an unadjusted comparison uses the posted group summaries without a reported covariate adjustment. Randomization can support comparisons between assigned groups, but a registry summary alone does not show whether the original analysis used additional methods, how protocol deviations were handled, or whether all randomized participants contributed to each result. The detailed statistical analysis plan and the trial's analysis populations are not reported in the registry record.

How should the p-values be read?

In general, a p-value measures how incompatible the observed data are with a specified null model, under the assumptions used for the test. A small p-value is not the probability that the null hypothesis is true, and it does not measure the size or clinical importance of a difference. The posted unadjusted p-values are less than 0.001 for the comparisons with pravastatin 10 mg, pitavastatin 2 mg, and pitavastatin 4 mg. The p-values for pravastatin 20 mg and pravastatin 40 mg are 0.063 and 0.119. These values do not report whether the original trial used a multiplicity procedure; such a procedure is not reported in the registry record.

Confidence intervals provide an estimate of uncertainty around a contrast. In general, a 95% confidence interval is generated by a method that, under its assumptions, would cover the target parameter in 95% of repeated samples. It is not a guarantee that the parameter lies in this particular interval, nor does it resolve whether an effect matters clinically. An interval that includes zero is compatible with no difference under the method used, as well as with values on either side of zero. Intervals that exclude zero indicate greater evidence of a nonzero difference under the same assumptions, but do not account for unreported multiplicity or model choices.

What do the planning calculations assume?

For the planning illustrations, the stated assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set to the stated fraction of the observed effect. These are illustrative planning assumptions, not reported assumptions from the trial's original design. The original design's sample-size rationale is not reported in the registry record.

As a general concept, power is the probability that a study will detect an effect of a specified size under a specified model and assumptions. The planning calculations use assumed effects and sample sizes to illustrate that concept. They should not be confused with a calculation of power based on the study's observed results. The record does not report interim analyses, the statistical model for the original primary analysis, or adjustments for multiple comparisons. The unadjusted estimates and p-values therefore should not be treated as a complete substitute for the prespecified analysis plan.

What can the summaries not establish?

Arm-level means do not reveal the distribution's full shape, outliers, or whether results differed across participant subgroups. Standard deviations provide a measure of spread but cannot convey all those details. The registry does not report participant-level data, an assessment of model assumptions, or a detailed account of missing observations. General inferential methods depend on assumptions about the data and the analysis; the record does not contain enough information to verify every such assumption. The interpretations are therefore limited to the posted descriptive summaries and unadjusted contrasts.

11. Confidence Intervals and Precision

Precision concerns how narrowly the data locate an estimated contrast, rather than whether that contrast is important. The primary comparisons are accompanied by 95% confidence intervals. For pravastatin 10 mg relative to pitavastatin 1 mg, the estimate is 9.02 and the interval runs from 5.864 to 12.18. For pitavastatin 2 mg, the estimate is -7.56 and the interval runs from -9.911 to -5.209. For pitavastatin 4 mg, the estimate is -12.88 and the interval runs from -15.34 to -10.42. These intervals do not include zero.

The intervals for pravastatin 20 mg and pravastatin 40 mg do include zero: their estimates are 2.6 and -2.55, with intervals from -0.136 to 5.336 and from -5.759 to 0.659, respectively. In general, an interval including zero leaves the direction of the underlying difference uncertain under the method used. It does not prove that the groups are identical. Conversely, excluding zero does not establish clinical importance, and the registry does not report a threshold for interpreting importance.

The width of an interval reflects statistical uncertainty under the calculation's assumptions. It is influenced by the amount of information and variability, among other factors. The arm standard deviations describe participant-to-participant spread, while the confidence intervals describe uncertainty around estimated differences; those quantities should not be confused. The record does not report adjusted confidence intervals or a procedure accounting for the set of comparisons. Because the posted intervals are unadjusted, they do not communicate the additional uncertainty that might arise from selecting among multiple comparisons. Their precision should be understood as precision for the individual unadjusted contrasts, not as a complete statement about all possible treatment comparisons.

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 participants per arm, not total events. They are illustrations based on the observed effect, rather than the trial's original sample-size design. The stated assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation; the effect to detect is the stated fraction of the observed effect. The original design assumptions and sample-size justification are not reported in the registry record.

The 80% power column gives the estimated participants per arm for a future two-arm comparison to have an 80% chance of detecting the specified effect under those planning assumptions, if the assumed effect and model are correct. The 90% power column gives the corresponding planning estimate for a 90% chance. These are planning targets, not guarantees for any future study. The figures are not observed power for this completed trial.

The rows consider planning for 100%, 75%, and 50% of the observed effect. A smaller effect is harder to distinguish from random variation under a given design, so smaller assumed effects require more participants per arm. The pattern is visible across the planning comparisons: when the assumed detectable effect is reduced, the required sample size rises. The calculations use the observed contrast as a starting point, so they should not be interpreted as evidence that the same effect will occur in a new study. The registry does not report the assumptions or target effect used when the original trial was designed.

A curve that represents these calculations should be read as a planning relationship between the assumed effect size and the required sample size under the stated assumptions. It is not a depiction of observed participant outcomes. Different allocation, variability, analysis methods, or target effects could change planning needs; the registry does not establish that these illustrations account for such changes. The numeric results are per-arm participant counts, and the event-count convention used for time-to-event outcomes does not apply to this continuous endpoint.

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 = 9.020; pooled standard deviation σ = 12.611.
2. n = 2 × (1.96 + 0.842)² × 12.611² / 9.020² = 30.7, rounded up to 31 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 <- 9.02                      # observed difference in means
sigma <- 12.6108099418559                     # 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(257686)
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 = 31 (80% power), 42 (90% power)
 75% of observed effect: n per arm = 55 (80% power), 74 (90% power)
 50% of observed effect: n per arm = 123 (80% power), 165 (90% power)
power.t.test: 31.7 
Simulated power at n = 31 per arm: 0.791 (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

Six treatment arms create several possible comparisons, and the registry posts multiple unadjusted contrasts against pitavastatin 1 mg for the primary endpoint. It also lists a secondary endpoint with posted contrasts for some arms. When multiple hypotheses are tested, the chance of at least one false-positive result can increase. As a general statistical practice, a prespecified comparison hierarchy or a multiplicity adjustment can address this concern, but neither the original plan nor an adjustment procedure is reported in the registry record. The posted p-values and confidence intervals should therefore be understood as unadjusted for the collection of comparisons.

The registry does not report a detailed missing-data strategy, the number of participants with an observed primary endpoint, reasons for missing measurements, or sensitivity analyses. It also does not identify whether the results use an intention-to-treat, per-protocol, or other analysis population. Although arm-level sample counts are listed for the outcomes, these counts do not by themselves explain how participants without endpoint data were handled or whether all randomized participants contributed to the summaries.

Other important analysis details are not reported in the registry record, including the original statistical analysis plan, any covariate adjustment, interim analyses, model diagnostics, and the handling of protocol deviations. The randomization and masking characteristics are recorded, but operational details about concealment and masking are not posted by the registry description. These gaps do not invalidate the posted summaries; they limit the ability to verify whether the summaries match the prespecified analysis or to assess robustness to alternative assumptions.

For continuous outcomes, missing observations can affect an arm mean if the participants with observed measurements differ from those without them. In general, methods for handling missing data rely on assumptions, and sensitivity analyses can help assess how conclusions change under alternatives. The record does not report which assumptions or methods were used. As a result, confidence intervals and p-values should be interpreted as the posted unadjusted results, without assuming a particular missing-data procedure or analysis population.

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

The primary result describes average percentage change in LDL-C from baseline to 12 weeks across the six randomized arms. The posted means are negative in every arm, and the unadjusted contrasts indicate different average changes for some comparisons with pitavastatin 1 mg. The confidence intervals and p-values convey statistical uncertainty for those individual contrasts under the calculations used. They do not describe each participant's experience, and they do not establish that every person in an arm had a change in the direction of the mean.

These results do not by themselves establish clinical importance. The registry does not report a threshold for a clinically meaningful difference, nor does it post clinical-event outcomes for this question. LDL-C change is a laboratory endpoint; its summary cannot be translated from the registry record into an effect on longer-term health outcomes. The findings also should not be treated as medical advice or as a recommendation about which regimen an individual should receive.

Interpretation is limited to the study population and regimens described in the registry. The record characterizes participants as elderly patients with primary hypercholesterolemia or combined dyslipidemia, but additional eligibility details are not reported. It provides no basis for extending the results to other populations, doses, treatment durations, or clinical settings. The listed once-daily doses and 12-week timeframe describe the posted regimens and outcome period; details of the titration process are absent despite its mention in the official title.

The unadjusted nature of the comparisons and the missing information about multiplicity, missing data, and analysis populations matter when judging certainty. Several intervals exclude zero, while others include zero; neither pattern substitutes for a complete prespecified analysis. The registry record gives useful quantitative summaries, but it does not present enough methodological detail to answer every question about robustness, generalizability, or clinical relevance.

16. Why This Trial Matters Statistically

This trial is statistically informative because it reports a continuous primary outcome across six dose-specific randomized arms, with arm-level means, standard deviations, and unadjusted comparisons against a reference arm. That makes it possible to distinguish the average change in each arm from the uncertainty around selected differences. The pattern also illustrates why direction, magnitude, precision, and clinical meaning are separate interpretive questions.

The confidence intervals demonstrate that results can differ in precision and compatibility with a zero difference across comparisons. Some intervals exclude zero and others include it. A p-value alone would not communicate the range of values compatible with the data, while a mean alone would not communicate uncertainty. Reading estimates together with their intervals gives a fuller account of the posted contrasts, though it cannot replace details absent from the registry record.

The record also illustrates the limits of multiple unadjusted comparisons. Several arms are compared with a common reference, and a secondary outcome is listed. Without a reported plan for multiplicity, the inferential strength of individual p-values is more limited than it would be under a fully specified analysis strategy. Likewise, planning illustrations derived from observed effects can help readers understand how assumed effect size relates to sample requirements, but they are not evidence of observed power or proof that those assumptions were used in the original design.

Finally, the trial highlights the value of transparent reporting beyond endpoint summaries. Analysis populations, missing-data methods, original sample-size justification, and adjusted analyses are not reported in the registry record. Their absence constrains evaluation of how robust the posted estimates are. The statistics support a careful description of average 12-week biomarker changes, while the unanswered methodological questions remain important to interpreting the strength and scope of the evidence.

17. 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 limitations are specific to the registry record. It does not provide detailed eligibility criteria for the elderly population, baseline characteristics, or participant flow through the study. Although enrollment is recorded as 962, the record does not explain how many participants were randomized to each arm, completed follow-up, or contributed data to each endpoint beyond the arm-level outcome counts. Those details would help assess the populations represented by the summaries.

The official title refers to up-titration, but the registry's arm descriptions give once-daily dose regimens without explaining the titration schedule or its timing. The record also does not describe adherence, treatment discontinuation, or concomitant care. These omissions limit reconstruction of the actual treatment exposure over the outcome period.

The primary results are arm means and standard deviations, with unadjusted comparisons and confidence intervals. A full protocol or statistical analysis plan is not reported, and the registry does not identify analysis populations, missing-data procedures, model adjustments, or multiplicity handling. No clinically meaningful threshold is stated. The statistical summaries therefore do not establish whether observed differences were important to patients or how sensitive they might be to analysis choices.

Safety reporting is also limited. The record lists counts of participants affected by serious and other adverse events, but denominators at risk and death counts are not reported. The serious-event terms listed include prostate cancer, acute myocardial infarction, cholecystitis, cholelithiasis, bleeding varicose vein, and hypertensive crisis, each recorded as 1.0%. The registry's presentation does not provide enough detail to infer comparative safety rates or causation from these entries. These limitations are about the detail available in the record, not evidence that unreported procedures or analyses did not occur.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Study to Compare the Efficacy and Safety of Pitavastatin and Pravastatin in Elderly Patients — NCT00257686.
• Registry record last updated 2010-03-16; status last verified 2010-03.
• Results first posted 2010-01-18.
• 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.

21. Record Summary

The registry record describes a completed phase 3 randomized, quadruple-masked, parallel study of once-daily pitavastatin and pravastatin regimens in elderly patients with primary hypercholesterolemia or combined dyslipidemia. Enrollment was 962. The primary endpoint was mean percent change in LDL-C from baseline to 12 weeks; percent change in total cholesterol was listed as a secondary outcome.

All six primary arm means were negative. Unadjusted comparisons against pitavastatin 1 mg had confidence intervals excluding zero for pravastatin 10 mg, pitavastatin 2 mg, and pitavastatin 4 mg; the intervals for pravastatin 20 mg and pravastatin 40 mg included zero. These are average biomarker results, not evidence about individual outcomes or clinical-event effects. The registry does not report multiplicity handling, missing-data methods, analysis populations, the original sample-size justification, or a detailed titration schedule. Interpretation should therefore remain within the scope of the posted summaries and their unadjusted comparisons.