Bioequivalence Study of Test and Reference 120 mg Etoricoxib Film-coated Tablets in Healthy Volunteers: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Bioequivalence Study of Test and Reference 120 mg Etoricoxib Film-coated Tablets in Healthy Volunteers (NCT05014490), a randomized phase 1 study. The primary outcome is Maximum Plasma Concentration (Cmax).

2. Clinical Question

This is a pharmacokinetic comparison in healthy volunteers, not a trial of clinical outcomes or treatment of a disease. The primary endpoint is a measure of drug concentration in plasma. The study title and registry description identify the objective as assessing bioequivalence between the two products. That objective concerns the similarity of their measured drug exposure under the study conditions; it does not, by itself, establish how either product affects symptoms, complications, or other clinical outcomes.

The crossover design means that the comparison concerns products administered within a study organized around two treatment sequences and two periods. The registry record does not report how many participants were assigned to each sequence, the sequence allocation details, or the interval between periods. Those details would help readers assess the conduct of the crossover but cannot be inferred from the title alone.

3. Trial Design

The registry describes a randomized, open-label, single-dose, two-sequence, two-period, crossover comparison. It lists the study as Phase 1 and reports enrollment of 28 healthy volunteers. The products were Exib 120 mg etoricoxib film-coated tablets and Arcoxia 120 mg etoricoxib film-coated tablets, each administered as a single oral dose under fasting conditions. Masking is listed as none, so the study was open-label.

In a crossover study, participants are assigned to sequences that determine the order in which treatments are received. This design allows each participant to contribute observations under both treatments, which can make within-person comparisons informative. The registry record does not give the sequence assignments, period-specific participant counts, washout interval, or any details about how period or sequence effects were handled in the sponsor’s analysis. These aspects should therefore not be assumed.

The study began on 2021-02-24, reached primary completion on 2021-03-24, and is listed as completed. Blood sampling for pharmacokinetic analysis covered up to 72 hours post-dose. The record lists two outcome measures and two analyses. It identifies Cmax as the primary endpoint and states that it is based on etoricoxib plasma concentration. The analysis population is described as all participants who completed the study and had their samples analyzed; the number completing is not separately reported in the registry record.

The study’s original sample-size justification, planned enrollment rationale, protocol-specific statistical methods, and any interim analyses are not reported in the registry record. The planning illustrations associated with the posted results are separate from the original design and should not be read as evidence of the trial’s planned or observed power.

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

Second Intervention

Analysis population for the primary outcome, as defined in the registry: All participants that completed the study had their samples analyzed.

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 Maximum Plasma Concentration (Cmax), measured over Blood sampling for pharmacokinetic analysis covered up to 72 hours post-dose..

The primary endpoint is maximum plasma concentration (Cmax), measured in ng/mL. It summarizes the highest measured concentration of etoricoxib in plasma during the pharmacokinetic sampling period. In this study, blood sampling for pharmacokinetic analysis covered up to 72 hours post-dose, and the registry states that Cmax values are based on etoricoxib plasma concentration.

Cmax is used in pharmacokinetic comparisons because it describes peak concentration after a dose. Comparing this measure between a test product and a reference product helps characterize whether the products produce similar concentration profiles under the study conditions. It is one aspect of drug exposure; it does not describe every feature of the concentration-time profile or directly measure a clinical outcome.

The posted group summaries report arithmetic means and standard deviations for Cmax. The registry also posts an equivalence analysis using the ratio of the test-to-reference geometric means. These are distinct summaries: a difference between arithmetic means is not the same estimand as a ratio of geometric means. Interpretation of the formal equivalence result depends on its analysis method and acceptance limits, which are not reported in the registry record.

All participants who completed the study had their samples analyzed, according to the endpoint description. The number of completers and any details about samples that could not be analyzed are not reported in the registry record.

7. Results Posted in the Registry

• Test (Exib): mean 1,949 versus 1,916 on control; difference 32.36 (95% CI -276.74 to 341.45), standardized effect d = 0.05; z-test p = 0.837.

8. Statistical Interpretation

9. Statistical Methods Explained

The registry presents two kinds of statistical summaries for the primary pharmacokinetic endpoint. The arm-level summaries give a mean and standard deviation for Cmax in each treatment group. A separate posted analysis gives the ratio of test to reference geometric means, with a 90% confidence interval, and labels the analysis as equivalence. A simple unadjusted recalculation from the posted summary statistics gives a mean difference, its confidence interval, and an unadjusted p-value. These are different estimands and should be interpreted separately.

What does the mean difference describe?

The arithmetic mean is the average of the measured Cmax values within a treatment group. The recalculated mean difference compares the Test (Exib) mean with the Reference (Arcoxia®) mean. Its estimate is 32.36 ng/mL. A positive estimate indicates that the posted test-group mean is higher than the reference-group mean, while the confidence interval communicates uncertainty around that estimate. The 95% confidence interval extends from -276.7 to 341.4. Because it includes zero, the recalculation does not provide clear evidence of a nonzero difference at the usual interpretation of a two-sided test. That statement is not a conclusion about equivalence.

The p-value of 0.837 is an unadjusted result associated with the recalculated comparison. In general, a p-value describes how compatible the observed data are with a specified null hypothesis under the statistical model used. It is not the probability that the null hypothesis is true, and a large p-value does not demonstrate that two treatments are equivalent. The recalculation is explicitly unadjusted and based on posted summary statistics; it does not reproduce every potential feature of a crossover analysis.

Why distinguish arithmetic and geometric means?

The arithmetic mean summarizes values on their original scale. A geometric mean is based on multiplicative summaries and is often used when pharmacokinetic values are analyzed on a logarithmic scale. In general, ratios of geometric means express relative rather than absolute differences. The posted ratio of 102.15 is therefore not interchangeable with the arithmetic mean difference of 32.36 ng/mL. The registry record does not report the method used for the sponsor’s equivalence analysis, so the precise transformation, model, and handling of the crossover structure cannot be described from the registry entry.

For a formal equivalence assessment, the confidence interval is judged against prespecified acceptance limits. In general, equivalence is not established merely because a difference test is nonsignificant or because a ratio appears close to 100. The acceptance limits for this study are not reported in the registry record. The record labels the posted result as an equivalence analysis, but without the limits and analysis details, the reader cannot independently verify the formal decision from the interval alone.

What does a confidence interval add?

A confidence interval gives a range of estimates compatible with the data and the assumptions of the analysis. In repeated use of a method, intervals constructed at a stated confidence level have a long-run coverage interpretation. The 95% interval for the unadjusted mean difference and the 90% interval for the geometric mean ratio correspond to different summaries and confidence levels. Neither interval removes uncertainty; each describes it on its own scale. The arithmetic difference is expressed in ng/mL, whereas the ratio is expressed as a percentage of the reference geometric mean.

Standard deviations describe variability among observations within a group. They are not the same as standard errors, which describe uncertainty in an estimated mean. The posted standard deviations are 577.4 for Test (Exib) and 602.4 for Reference (Arcoxia®). The registry also reports standard errors in the recalculation inputs, but the key interpretation is that group variability and estimate precision answer different questions. In a crossover design, within-person variability and the correlation between treatment-period measurements can influence the precision of a paired comparison. Those participant-level quantities are not reported in the registry record.

How does the crossover design affect interpretation?

In general, a crossover trial compares treatments within participants, with treatment order determined by assigned sequence. This can control for stable differences between participants, because each participant can serve as their own comparison. It also makes period, sequence, and carryover considerations relevant to analysis and conduct. The registry record identifies two sequences and two periods, but does not report the interval between periods, participant allocation by sequence, or how the sponsor modeled these effects. The unadjusted recalculation from group summaries should therefore be read as a limited summary-based comparison, not as a reconstruction of the full crossover analysis.

The reported analysis method is not reported in the registry record. The registry does not specify the analysis model, transformations, covariates, handling of period or sequence effects, or the exact population definition beyond stating that samples from all study completers were analyzed. These details would be necessary for a fuller audit of the analysis.

What does the planning illustration represent?

The planning illustration is computed from the observed effect rather than the trial’s original design assumptions. It uses a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation; the effect to detect is a stated fraction of the observed effect. It gives participants per arm for 80% and 90% power. These calculations are hypothetical planning aids, not a report of the study’s observed power or its original sample-size justification. The registry record does not report the original sample-size assumptions or justification.

General statistical considerations also caution against treating an observed effect as a stable planning target. An estimate from a small study can be imprecise, and planning based on it can produce very different sample-size requirements depending on the effect assumed. The illustration is useful for showing how assumptions influence planning, but it cannot explain why the trial enrolled 28 participants or establish whether its design was adequate for a formal equivalence objective.

10. Confidence Intervals and Precision

The arithmetic mean difference estimate is 32.36 ng/mL, and its 95% confidence interval ranges from -276.7 to 341.4. This interval includes zero and spans values in both directions. It is therefore important not to treat the point estimate alone as a precise description of the comparison. The interval allows for substantial uncertainty about the size and direction of an arithmetic mean difference under the unadjusted recalculation.

The registry’s separate equivalence analysis reports a test-to-reference geometric mean ratio of 102.15 and a 90% confidence interval from 94.54 to 110.37. That interval describes uncertainty on the ratio scale, not the ng/mL difference scale. It should be interpreted against the study’s equivalence limits, but those limits are not reported in the registry record. Consequently, the interval’s formal relation to the acceptance criteria cannot be assessed from the posted information alone.

In general, a confidence interval expresses the precision of an estimate under the analysis assumptions; narrower intervals indicate greater precision than wider intervals on the same scale. The standard deviations, 577.4 for Test (Exib) and 602.4 for Reference (Arcoxia®), describe variation in the observed Cmax values and are not confidence intervals. Because the study is a crossover, within-participant variation and the association between a participant’s measurements under the two products are relevant to precision. These participant-level details are not reported in the registry record, so the posted summary statistics do not permit a full assessment of crossover-specific precision.

The study enrolled 28 participants, and 28 are listed for each treatment summary. These counts should be understood in the context of a crossover, not as evidence that there were separate groups of 28 unique participants for each product. The registry states that all participants who completed the study had samples analyzed, but does not separately report the number completing or the number with analyzable observations for each period.

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 planning figures are participants per arm, not total event counts. They are illustrations based on the observed effect and are not the original design justification. The listed 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 trial’s own original sample-size assumptions and justification are not reported in the registry record.

The 80% power column gives the illustrative number of participants per arm under the stated assumptions for a design with an 80% chance of detecting the assumed effect, if that effect and the model assumptions hold. The 90% power column gives the corresponding planning number for a 90% chance. These are planning concepts, not guarantees about results in a future study. The posted figures are 5,221 and 6,990 participants per arm for planning for 100% of the observed effect; 9,282 and 12,426 for planning for 75% of the observed effect; and 20,884 and 27,957 for planning for 50% of the observed effect, respectively for 80% and 90% power.

Smaller assumed effects require more participants to reach the same target power, which is why the figures increase as the assumed fraction of the observed effect decreases. This is not observed power: it is a hypothetical planning illustration calculated from the observed effect, rather than an estimate of the probability that the completed trial detected an effect. The illustration also does not substitute for an equivalence sample-size calculation based on prespecified acceptance limits, which are not reported in the registry record.

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 = 32.356; pooled standard deviation σ = 590.071.
2. n = 2 × (1.96 + 0.842)² × 590.071² / 32.356² = 5,220.8, rounded up to 5,221 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 <- 32.356                      # observed difference in means
sigma <- 590.07107312467                     # 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(5014490)
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 = 5,221 (80% power), 6,990 (90% power)
 75% of observed effect: n per arm = 9,282 (80% power), 12,426 (90% power)
 50% of observed effect: n per arm = 20,884 (80% power), 27,957 (90% power)
power.t.test: 5221.8 
Simulated power at n = 5,221 per arm: 0.798 (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 registry posts the sponsor’s equivalence analysis as a test-to-reference geometric mean ratio of 102.15, with a 90% confidence interval from 94.54 to 110.37. The registry labels the result as an equivalence analysis. Its method is not reported in the registry record, and the acceptance limits are also not reported, so the formal basis for an equivalence decision cannot be independently evaluated from the posted result alone.

The unadjusted recalculation is a different analysis: it compares the posted arithmetic means and gives a mean difference of 32.36 ng/mL, a 95% confidence interval from -276.7 to 341.4, and an unadjusted p-value of 0.837. It is based on summary statistics and does not reconstruct the sponsor’s crossover analysis or its geometric-mean ratio estimand. These results should not be treated as competing estimates of the same quantity.

The registry’s discrepancy indicator is false, so there is no flagged disagreement between the posted analysis and the recalculation. Even so, the recalculation remains a limited, unadjusted comparison and does not validate the sponsor’s method. Where a discrepancy is flagged, the sponsor’s own analysis takes precedence; that condition does not apply to this record.

14. Multiplicity, Missing Data and Analysis Populations

The registry lists two outcome measures and two analyses, with Cmax identified as the primary endpoint. It does not report whether there were additional prespecified outcomes, whether the two analyses correspond to distinct endpoints or analysis populations, or whether any multiplicity adjustment was planned. Details of multiplicity handling are not reported in the registry record.

In general, multiplicity arises when several outcomes, treatment comparisons, time points, or statistical tests are considered. Without a prespecified strategy, repeated testing can complicate interpretation of nominal p-values and confidence intervals. The posted unadjusted p-value of 0.837 should be read as an unadjusted result; there is no basis in the registry record to infer a correction or a broader family of tests.

The endpoint description states that all participants who completed the study had their samples analyzed. The number of participants who completed the study is not separately reported in the registry record. The record also does not report period-specific missingness, exclusions, reasons for missing samples, handling of values below measurement limits, or imputation procedures. It is therefore not possible to assess how incomplete or unusable measurements were handled beyond the statement about completers’ samples.

The analysis population is not described with a named population definition beyond the endpoint statement. The registry does not report whether the equivalence analysis used all randomized participants, completers, or another prespecified set, nor does it describe how protocol deviations were treated. These details can matter in equivalence analyses, where different analysis populations may offer complementary information.

Interim analyses and any associated stopping rules are not reported in the registry record. The original statistical analysis plan, the study’s original sample-size justification, and the method for the sponsor’s equivalence analysis are also not reported. These omissions limit assessment of whether the posted analyses follow prespecified procedures and how robust the formal interpretation is to missingness, exclusions, or multiple testing.

15. Safety Results

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

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 3% reporting threshold.

Most frequent non-serious adverse event terms

The posted serious adverse event figures are zero for Test (Exib) and zero for Reference (Arcoxia®). The registry lists 28 participants at risk in each treatment group for serious adverse events. It reports no deaths in either group. For other adverse events, it lists 3 affected participants in the Test group and 2 in the Reference group, with 28 at risk in each group.

These are descriptive counts. The registry summary does not provide the terms or descriptions of the other adverse events, their timing, severity, relationship to treatment, or whether individual participants experienced more than one event. Those details are not reported in the registry record. The counts also do not show the participant-level crossover history or exposure timing.

Zero reported serious adverse events in this study means none were recorded in the posted figures; it does not establish that a product has no serious risks. The study enrolled 28 healthy volunteers and involved single-dose administration. The safety figures should therefore be interpreted in the limited context of this study and not as a comprehensive comparison of safety in broader populations or during longer-term use.

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

The study addresses a focused pharmacokinetic question: how Cmax after a single dose of Exib compared with Cmax after a single dose of Arcoxia in healthy adult volunteers under fasting conditions. The posted arithmetic means are 1949.0 ng/mL for Exib and 1916.0 ng/mL for Arcoxia. The registry’s separate equivalence analysis reports a geometric mean ratio of 102.15, with a 90% confidence interval from 94.54 to 110.37.

These results describe drug concentration measurements, not clinical benefit or harm. Cmax is one pharmacokinetic measure and does not capture every aspect of drug exposure or patient experience. The study record does not report clinical outcomes, and the findings should not be extended to claims about symptom control, complications, or effects in patients.

The formal equivalence interpretation cannot be independently confirmed from the registry information because the acceptance limits and analysis method are not reported in the registry record. A nonsignificant unadjusted difference test is not itself evidence of equivalence. Likewise, a ratio near 100 does not establish that formal criteria were met unless it is interpreted against the prespecified limits and the relevant analysis plan.

The sample-size illustrations are not evidence of observed power or of the trial’s original planning rationale. The record does not report the original sample-size justification, detailed crossover analysis, or handling of missing data. The posted means and confidence intervals can be read as estimates with uncertainty, but they do not resolve those gaps. The safety summary reports no serious adverse events and no deaths, alongside 3 other adverse-event reports in the Test group and 2 in the Reference group; it is a limited descriptive account rather than a complete safety assessment.

In short, the registry documents a randomized crossover comparison and posts both arithmetic group summaries and a geometric-mean equivalence result. The data support a description of these measured pharmacokinetic quantities in the study population, while the missing equivalence criteria and analysis details constrain a definitive assessment of the stated bioequivalence objective.

17. Why This Trial Matters Statistically

This trial illustrates why the estimand and scale of an analysis matter. The arithmetic mean difference is expressed in ng/mL, while the sponsor’s posted comparison is a ratio of geometric means. Both concern Cmax, but they answer different statistical questions. Reading one as a substitute for the other would obscure the distinction between an absolute difference and a relative comparison.

It also demonstrates that a nonsignificant test of difference and an equivalence assessment are not interchangeable. The unadjusted p-value of 0.837 concerns a difference comparison, while formal equivalence depends on whether a confidence interval is contained within prespecified acceptance limits. The registry labels its analysis as equivalence but does not report those limits, so readers cannot independently verify the formal criterion from the posted record.

The crossover design makes participant-level information important. Comparisons within a person can account for stable individual differences, but the precision and interpretation depend on how the repeated measurements and design features are handled. Arm-level means and standard deviations do not provide the within-participant correlation or reveal how period and sequence were modeled. The sponsor’s method is not reported in the registry record.

Finally, the planning illustration shows how assumed effect size and desired power affect sample-size requirements, but it does not explain the enrollment of 28 participants. The original design justification is not reported. Keeping the planning illustration separate from the trial’s observed results prevents a hypothetical calculation from being mistaken for evidence about the study’s power or design adequacy.

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.

This registry record does not report the equivalence acceptance limits or the method used for the sponsor’s geometric-mean analysis. Although the posted analysis is labeled as equivalence, those omissions prevent independent confirmation of the formal decision. The original statistical analysis plan and sample-size justification are also not reported.

The registry identifies a two-sequence, two-period crossover design but does not report treatment sequence assignments, participant counts by sequence, the interval between periods, or the handling of period and sequence effects. The posted summary statistics do not include participant-level paired measurements or within-person correlation. As a result, the unadjusted recalculation cannot reproduce a crossover-specific model.

The endpoint description says that all participants who completed the study had their samples analyzed, but the number of completers is not separately reported. The record does not describe missing samples, exclusions, protocol deviations, or the analysis population in detail. It also does not report interim analyses or multiplicity procedures.

The safety summary provides counts but not event terms, severity, timing, or treatment relationship for the other adverse events. Finally, the study is a single-dose comparison in healthy volunteers under fasting conditions and reports a pharmacokinetic endpoint. Its posted results do not address clinical outcomes or longer-term use.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Bioequivalence Study of Test and Reference 120 mg Etoricoxib Film-coated Tablets in Healthy Volunteers — NCT05014490.
• Registry record last updated 2024-11-29; status last verified 2024-11.
• Results first posted 2024-11-29.
• 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

NCT05014490 is a completed, randomized, open-label, Phase 1 crossover study of single-dose Exib 120 mg etoricoxib and Arcoxia 120 mg etoricoxib in healthy adult volunteers under fasting conditions. Enrollment was 28, and the primary endpoint was maximum plasma concentration (Cmax), measured through blood sampling up to 72 hours post-dose.

The posted arithmetic mean Cmax values were 1949.0 ng/mL for Exib and 1916.0 ng/mL for Arcoxia. The unadjusted recalculation estimated a mean difference of 32.36 ng/mL, with a 95% confidence interval from -276.7 to 341.4 and p = 0.837. The registry separately reports a test-to-reference geometric mean ratio of 102.15, with a 90% confidence interval from 94.54 to 110.37, labeled as an equivalence analysis.

The equivalence method and acceptance limits, original sample-size justification, and detailed crossover-analysis procedures are not reported in the registry record. No serious adverse events or deaths were posted; other adverse events were listed for 3 participants in the Test group and 2 in the Reference group.