Pravastatin 80 mg Tablets Dosed in Healthy Subjects Under Non-Fasting Conditions: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Pravastatin 80 mg Tablets Dosed in Healthy Subjects Under Non-Fasting Conditions (NCT00829309), a randomized phase 1 study. The primary outcome is Cmax - Maximum Observed Concentration - Pravastatin in Plasma.

2. Clinical Question

3. Trial Design

This was a completed Phase 1, randomized, unmasked crossover study sponsored by Teva Pharmaceuticals USA. It compared Teva Pravastatin Sodium Tablets 80 mg with Pravachol® Tablets 80 mg under non-fasting conditions in healthy adult male subjects. The brief summary describes a single oral dose of one 80 mg tablet. The study began and reached primary completion in 2005-03.

The crossover structure is reflected in the registry’s sequence descriptions: one sequence received the test tablet in the first period and the reference tablet in the second, while the other sequence received the reference tablet first and the test tablet second. Randomization is reported, but the registry record does not state how allocation to sequences was generated or concealed. Masking is listed as none. Details such as period length, washout, adherence, and handling of period or sequence effects are not reported in the registry record.

Enrollment was 16. The primary outcome description says that data from all subjects who completed the study were included in the statistical analysis. Each posted treatment summary contains 15 observations. The record does not explain the relationship between the enrollment count and the analysis counts, so no reason for that difference can be established from the registry information.

The primary endpoint was Cmax, the maximum observed plasma concentration of pravastatin, measured in ng/mL. Blood samples were collected over a 16 hour period. There are three posted outcome measures and three analyses, but no secondary outcomes are posted in the record. The sponsor’s stated objective was a relative-bioavailability comparison; the posted primary outcome data support interpretation of Cmax specifically, rather than a broad conclusion about all pharmacokinetic measures.

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.

First Intervention

Washout: 7 Days

Reasons for not completing this period:

Second Intervention

Analysis population for the primary outcome, as defined in the registry: Data from all subjects who completed the study were included in the statistical analysis.

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 Cmax - Maximum Observed Concentration - Pravastatin in Plasma, measured over Blood samples collected over 16 hour period.

Cmax is the maximum concentration observed in plasma during the sampling period. It is a continuous measure, in ng/mL, and the registry gives its mean and standard deviation for each treatment. As a pharmacokinetic endpoint, peak concentration describes one feature of the concentration profile after dosing. The study collected blood samples over a 16 hour period and defined the primary outcome as the maximum observed concentration within that period.

The study description identifies relative bioavailability, including rate and extent of absorption, as its overall purpose. Cmax is used in such comparisons because it captures the observed peak in the concentration profile, which can contribute information about absorption. It does not, by itself, summarize the entire concentration profile or measure every possible aspect of the rate and extent of absorption. Other pharmacokinetic measures may address different features, but no secondary outcome results are posted in the registry record.

The primary outcome population is described as all subjects who completed the study. The posted means are 126.7 ng/mL for Pravastatin and 130.6 ng/mL for Pravachol®. The posted standard deviations are 60.95 and 58.86 ng/mL, respectively. These summaries describe the observed Cmax values; they are not individual concentration profiles and do not show the timing of each subject’s peak.

7. Results Posted in the Registry

• Pravachol®: mean 130.64 versus 126.69 on control; difference 3.95 (95% CI -38.93 to 46.83), standardized effect d = 0.07; z-test p = 0.857.

8. Statistical Interpretation

9. Statistical Methods Explained

What does the mean summarize?

The primary measure is continuous: each subject has an observed maximum plasma concentration, and the treatment summaries report the arithmetic mean of those values. The mean provides a measure of the central level of the observations. The registry also reports standard deviations, which describe how spread out individual observations are around their group mean. The Pravastatin mean is 126.7 ng/mL with a standard deviation of 60.95; the Pravachol® mean is 130.6 ng/mL with a standard deviation of 58.86. A standard deviation describes variability among observations, not uncertainty in the mean by itself.

How does the simple re-calculation differ?

The re-calculated comparison is a simple unadjusted mean difference based on the posted summary statistics. It expresses the Pravachol® mean relative to the Pravastatin mean as an absolute difference in ng/mL. The estimate is 3.95 ng/mL, with the subtraction direction defined as Pravachol® minus Pravastatin. The corresponding interval is -38.93 to 46.83, and the unadjusted p-value is 0.857. This summary does not incorporate a reported crossover model, covariate adjustment, or other trial-specific analysis features. The method used by the sponsor for its own ratio analysis is not reported in the registry record.

General statistical explanation: an unadjusted comparison is useful for a transparent, direct description of the posted summaries, but it may not use all information available in a crossover design. A within-subject analysis can account for the fact that subjects receive both treatments, while a suitable model may also account for periods or sequence. Those methods require appropriate data and specified assumptions. Because the registry record does not provide the underlying paired observations or a full analysis method, the simple re-calculation cannot reproduce or verify a crossover model.

What does the sponsor’s ratio describe?

The sponsor’s reported statistic is a geometric test-to-reference ratio multiplied by 100. Its value is 98.45, and the reported 90% confidence interval is 80.08 to 121.03. A ratio compares the test treatment with the reference on a relative rather than an absolute-difference scale. In bioavailability analyses, a geometric ratio is commonly used to summarize relative exposure after considering the multiplicative nature and possible skew of pharmacokinetic measurements. General explanation: logarithmic analysis is often used for positive, right-skewed pharmacokinetic measures, after which results can be expressed back on a ratio scale. The registry record does not identify whether that or another method was used for this sponsor analysis, so the method should not be attributed to the sponsor as a fact.

A ratio of 100 represents equal values on the ratio scale. The confidence interval quantifies uncertainty around the estimated ratio according to the analysis used. Whether an interval supports a formal equivalence conclusion depends on prespecified acceptance limits and the analysis plan. Those limits and the method are not reported in the registry record. The ratio and interval alone therefore should not be treated as an equivalence decision.

What does the p-value say?

General statistical explanation: a p-value describes how compatible observed data are with a specified null hypothesis under the assumptions of the test. The re-calculated p-value is unadjusted and equals 0.857. It is not the probability that the treatments are identical, nor does it quantify the probability that a clinical or pharmacokinetic difference exists. It also does not answer the equivalence question unless an equivalence analysis with an appropriate margin is specified.

General statistical explanation: confidence intervals show a range of values compatible with the observed data and the analysis assumptions at the stated confidence level. The re-calculated interval’s confidence level is not stated in the registry record, so it should not be assigned one. The sponsor’s interval is explicitly reported as a 90% confidence interval. These intervals use different estimands and should not be directly conflated.

Why can over-dispersion matter?

General statistical explanation: when observations vary more than a statistical model anticipates, standard errors can be too small and uncertainty can be understated. Variability is visible in the posted standard deviations, but the registry does not report a model diagnostic or an over-dispersion assessment. The mean-difference re-calculation does not establish whether a particular model’s variance assumptions are appropriate. In pharmacokinetic data, distributions may also be asymmetric, which can motivate a ratio-scale analysis; no specific distributional assessment is reported.

The study is randomized and crossover, but randomization alone does not specify the statistical model. The record reports neither the sponsor’s detailed model nor adjustments for period, sequence, or subject effects. The sponsor’s analysis is therefore best represented by the statistic and interval actually posted, while the simple re-calculation remains a separate, unadjusted descriptive check.

10. Confidence Intervals and Precision

The re-calculated mean difference is 3.95 ng/mL, and its interval runs from -38.93 to 46.83 ng/mL. The interval is wide relative to the point estimate and includes negative and positive differences. This means the posted summary statistics are compatible with a range of mean differences in either direction under the re-calculation. The confidence level for this interval is not reported in the registry record, so it should not be labeled as a particular confidence level.

The sponsor’s estimate is a geometric test-to-reference ratio multiplied by 100 of 98.45. Its 90% confidence interval extends from 80.08 to 121.03. This interval describes uncertainty on the ratio scale, not in ng/mL, and should not be interpreted as interchangeable with the unadjusted mean-difference interval. The registry record does not report equivalence bounds, so the interval’s position cannot be used from this record alone to make a formal equivalence determination.

Precision depends on both the amount of information and the variability of the outcome. The posted standard deviations, 60.95 ng/mL for Pravastatin and 58.86 ng/mL for Pravachol®, show substantial dispersion around their respective means. The outcome summaries include 15 observations per treatment. The record does not report the within-subject correlation or paired variability, which are important for assessing precision in a crossover comparison. Consequently, the unadjusted interval should be read as a summary based on the posted group statistics, not as a substitute for a fully described paired analysis.

A confidence interval is not a guarantee that the true value lies within the displayed endpoints. General explanation: it is an interval procedure whose long-run coverage depends on the analysis assumptions and repeated use in comparable settings. In this study, the sponsor’s ratio interval and the re-calculated difference interval answer related but distinct statistical questions.

11. 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 sample-size figures are planning illustrations, not the number of participants observed in the study. They are stated as participants per arm, not total events. This is a continuous-outcome comparison, so the displayed quantities are participants per arm. The registry record does not give the assumptions used for the original trial design or a justification for its enrollment.

The planning illustration uses a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. It is calculated from the observed effect, with the effect to detect set to the stated fraction of that observed effect. The displayed rows correspond to planning for 100%, 75%, and 50% of the observed effect. For 100% of the observed effect, the display gives 3,612 participants per arm for 80% power and 4,835 participants per arm for 90% power. For 75%, it gives 6,421 participants per arm for 80% power and 8,596 participants per arm for 90% power. For 50%, it gives 14,447 participants per arm for 80% power and 19,340 participants per arm for 90% power.

The 80% power column represents the planning size associated with an 80% chance of detecting the specified effect under the stated assumptions; the 90% column represents the size associated with a higher target chance under those same assumptions. Smaller effects require more participants in these illustrations. These estimates are not observed power for the completed trial, and they do not establish what the original investigators planned.

12. 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 = 3.950; pooled standard deviation σ = 59.914.
2. n = 2 × (1.96 + 0.842)² × 59.914² / 3.950² = 3,611.6, rounded up to 3,612 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 <- 3.94999999999999                      # observed difference in means
sigma <- 59.9141139465485                     # 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(829309)
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 = 3,612 (80% power), 4,835 (90% power)
 75% of observed effect: n per arm = 6,421 (80% power), 8,596 (90% power)
 50% of observed effect: n per arm = 14,447 (80% power), 19,340 (90% power)
power.t.test: 3612.6 
Simulated power at n = 3,612 per arm: 0.800 (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.

13. Analyses Reported by the Sponsor

The sponsor’s posted analysis reports a geometric test-to-reference ratio multiplied by 100 of 98.45, with a 90% confidence interval from 80.08 to 121.03. The sponsor analysis is the registry’s reported relative-bioavailability result. Its ratio scale is distinct from the unadjusted re-calculation, which compares arithmetic means as a difference in ng/mL and reports an estimate of 3.95 with an interval from -38.93 to 46.83 and an unadjusted p-value of 0.857.

The re-calculation is a simple check based on the posted treatment summaries, not a reconstruction of the sponsor’s analysis. The record does not report the sponsor’s statistical method, the equivalence limits, or a sponsor p-value. It is therefore not possible to establish from the registry record whether the two analyses use comparable assumptions or to infer the sponsor’s formal decision rule. No discrepancy is flagged between the posted outcome and the re-calculation. The sponsor’s reported ratio and interval should be read as the sponsor analysis; the unadjusted difference is supplementary context rather than a replacement for that analysis.

General statistical explanation: relative ratios and absolute differences can tell different parts of the story, particularly when the underlying measure is positive and its variability is multiplicative. The ratio expresses relative scale; the difference expresses an absolute change in the endpoint’s measurement units. Neither should be substituted for the other without specifying the question and analysis.

14. Multiplicity, Missing Data and Analysis Populations

The registry lists three outcome measures and three analyses, but no secondary outcome results are posted. The primary outcome is Cmax, and the sponsor’s posted analysis reports a ratio and confidence interval for the bioequivalence-related comparison. The record does not identify a complete hierarchy of outcomes, a prespecified order of testing, or a procedure for controlling multiplicity. It is therefore not reported in the registry record whether or how the analyses were adjusted for multiple comparisons.

General statistical explanation: when several outcomes or comparisons are tested, the chance of at least one apparently notable result can increase if each is considered separately. Prespecified testing strategies and multiplicity adjustments can address that issue, but the approach depends on the aims and analysis plan. No such plan is reported in the registry record, so no multiplicity-adjusted interpretation can be reconstructed.

The primary outcome population is described as data from all subjects who completed the study. Each treatment summary reports 15 observations. The record does not give a participant flow, explain missing outcome data, describe exclusions, or state how incomplete observations were handled. The relationship between enrollment of 16 and the posted outcome counts is not explained in the registry record. It would be inappropriate to infer why an observation is absent from the posted summaries.

The record does not report an intention-to-treat population, a per-protocol population, or another named analysis population beyond the completed-subject description. It also does not say whether any sensitivity analyses were performed. For a crossover study, the handling of subjects who do not complete every treatment period can matter to the estimand and analysis, but the registry does not supply the needed details.

The sponsor’s method is not reported in the registry record, including any handling of period, sequence, or subject effects. No interim analysis or monitoring plan is reported. These omissions limit reconstruction of the analysis and assessment of how missing data, multiple testing, and crossover features were addressed.

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

The posted results describe Cmax after a single oral dose of Pravastatin 80 mg or Pravachol® 80 mg under non-fasting conditions in healthy adult male subjects. The reported treatment means are 126.7 ng/mL and 130.6 ng/mL, respectively. The simple unadjusted re-calculation estimates a difference of 3.95 ng/mL, with an interval from -38.93 to 46.83 and an unadjusted p-value of 0.857. These results summarize the observed peak concentration data and the uncertainty represented by the stated analyses.

The sponsor’s separate analysis reports a geometric test-to-reference ratio multiplied by 100 of 98.45 and a 90% confidence interval from 80.08 to 121.03. A formal bioequivalence interpretation requires the relevant decision limits and analysis details. Those limits and details are not reported in the registry record, so the posted ratio cannot by itself establish whether prespecified equivalence criteria were met.

The findings do not show that the treatments are identical. Nor does a non-small unadjusted p-value establish equivalence or absence of a difference. The unadjusted estimate and interval concern an absolute mean difference, while the sponsor result concerns a geometric ratio. Both summaries have uncertainty, and the registry does not provide the information needed to reconstruct the sponsor’s statistical analysis fully.

The results are specific to the stated study conditions and endpoint. They do not answer questions about clinical outcomes, repeated dosing, other populations, or conditions other than those described. Cmax is one pharmacokinetic measure, and the registry record does not post secondary outcome results. No medical recommendation follows from these statistical summaries; they describe the reported evidence and its limitations.

16. Why This Trial Matters Statistically

This trial is a useful statistical example because its design and reported analyses invite different kinds of comparison. The crossover sequences place each treatment in different periods, while the sponsor reports relative bioavailability on a geometric ratio scale. A simple re-calculation from the posted treatment summaries instead gives an unadjusted absolute mean difference. Keeping those estimands distinct is essential: a ratio in relative units and a difference in ng/mL are not alternate labels for the same quantity.

The trial also illustrates why a non-significant test and an equivalence assessment answer different questions. The re-calculated p-value is 0.857, but the record does not provide the equivalence margins or the sponsor’s detailed method. The sponsor’s 90% interval is therefore important to report as posted, while avoiding a conclusion that cannot be checked against a stated decision criterion.

Precision is another central issue. The posted variability is substantial relative to the means, and the unadjusted interval spans differences in both directions. The crossover structure may affect the precision of a properly paired analysis, but the registry does not report the paired variability or model details. This makes clear why group means and standard deviations alone do not fully describe the statistical analysis of a crossover study.

Finally, the planning illustrations show how assumed effect size influences sample-size requirements, but they are not evidence about the original design or observed power. Separating design assumptions, observed summaries, sponsor analysis, and re-calculation helps readers distinguish what the registry documents from what cannot be established from the record.

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.

The registry record provides limited detail for evaluating the design and analysis. It identifies a randomized crossover study and lists treatment order sequences, but does not report the randomization procedure, allocation concealment, period duration, washout, or adherence. It also does not describe whether period, sequence, or subject effects were included in the sponsor’s model.

The enrollment count is 16, while each posted treatment summary contains 15 observations. The primary outcome population is described as subjects who completed the study, but the record does not explain the difference between enrollment and the posted analysis counts. There is no participant flow or account of missing data, exclusions, or sensitivity analyses.

The sponsor’s geometric ratio and 90% confidence interval are reported, but the statistical method, equivalence limits, and decision rule are not. The simple unadjusted re-calculation cannot fill those gaps or reproduce a crossover analysis from summary statistics. The confidence level for the re-calculated interval is also not reported in the registry record.

Only Cmax is reported as the primary outcome, and no secondary outcome results are posted. The data concern healthy adult male subjects given a single oral dose under non-fasting conditions, so the record does not establish how the results apply beyond that setting. The registry does not report further population characteristics or the full concentration-time data. These limitations restrict interpretation to the posted endpoint summaries and sponsor statistic.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Pravastatin 80 mg Tablets Dosed in Healthy Subjects Under Non-Fasting Conditions — NCT00829309.
• Registry record last updated 2024-08-20; status last verified 2024-08.
• Results first posted 2009-08-18.
• 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

NCT00829309 is a completed Phase 1 randomized, unmasked crossover study sponsored by Teva Pharmaceuticals USA. It compared a single oral dose of Teva Pravastatin Sodium Tablets 80 mg with Pravachol® Tablets 80 mg under non-fasting conditions in healthy adult male subjects. The study began and reached primary completion in 2005-03, with enrollment of 16.

The primary outcome was maximum observed pravastatin plasma concentration, Cmax, measured in ng/mL from blood samples collected over a 16 hour period. The posted means were 126.7 for Pravastatin and 130.6 for Pravachol®. The sponsor reported a geometric test-to-reference ratio multiplied by 100 of 98.45, with a 90% confidence interval from 80.08 to 121.03. A simple unadjusted re-calculation estimated a mean difference of 3.95 ng/mL, with an interval from -38.93 to 46.83 and an unadjusted p-value of 0.857. The registry does not report the sponsor’s method or equivalence limits, and no secondary outcome results are posted.