Study Evaluating Ibuprofen 600 mg Extended Release (ER) For Dental Pain: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study Evaluating Ibuprofen 600 mg Extended Release (ER) For Dental Pain (NCT00913627), a randomized phase 2 study. The primary outcome is Time-weighted Sum of Pain Intensity Difference Score From 0 to 12 Hours (SPID 0-12).

2. Clinical Question

3. Trial Design

This was a randomized, double-masked, parallel-group Phase 2 study sponsored by Pfizer. The registry record lists the study as completed, with a start date of 2009-05-07 and primary completion on 2009-08-01. Enrollment was 196. The study description identifies post-operative dental pain as the setting and describes evaluation of a single dose.

Four arms are listed: placebo; ibuprofen IR/ER manufactured by roller compaction; ibuprofen IR/ER manufactured by wet granulation; and naproxen. The ibuprofen formulations each contained 600 mg, while the naproxen caplet was 220 mg naproxen sodium. The stated rationale for including two ibuprofen formulations was concern that manufacturing process might influence the prototype’s performance. The description also refers to characterizing the pharmacokinetic/pharmacodynamic relationship.

The primary endpoint was the time-weighted sum of pain intensity difference from 0 to 12 hours, reported as a mean with standard deviation. The analysis population is described as randomized participants who dosed and had a baseline pain-severity assessment. The posted primary-outcome group counts are 29 for placebo, 53 for roller-compaction ibuprofen, 56 for wet-granulation ibuprofen, and 58 for naproxen. These are the counts attached to the primary outcome, not a statement about the number randomized to each arm.

The registry record does not report the original sample-size justification, the full statistical analysis plan, or further details of the randomization procedure. It also does not report the masking procedures or the handling of missing primary-outcome data. Those details should not be inferred from the randomized and double-masked design labels.

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

Analysis population for the primary outcome, as defined in the registry: Intent-To-Treat (ITT) population: randomized participants who dosed with study product and provided a baseline pain severity assessment.

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 Time-weighted Sum of Pain Intensity Difference Score From 0 to 12 Hours (SPID 0-12), measured over Baseline (0 hour) to 12 hours post dose.

The primary endpoint is the time-weighted sum of pain intensity difference, or SPID, from baseline to 12 hours after dosing. Participants rated pain intensity on a four-point categorical scale: None (0), Mild (1), Moderate (2), and Severe (3). A pain-intensity-difference score represents change from the baseline rating; those scores are combined over time using time weights to form SPID.

The endpoint description gives a possible score range from -12 to 36 and states that higher positive values indicate improvement, defined as a decrease in pain intensity. The reported measure is a mean, with standard deviation describing variation among participants. Because it summarizes repeated ratings across the stated interval, SPID reflects both the direction and the time-weighted pattern of pain-intensity change rather than a rating at a single moment.

As a general statistical point, a prespecified summary endpoint can condense a series of measurements into a quantity that can be compared between randomized groups. That makes group-level comparison more direct, while also meaning that the summary depends on the endpoint’s scoring and time-weighting rules. The registry record describes those general scoring elements but does not report additional details of the time-weighting implementation.

7. Results Posted in the Registry

• Ibuprofen IR/ER (Roller Compaction): mean 16.87 versus 0.05 on control; difference 16.82 (95% CI 12.63 to 21.01), standardized effect d = 1.81; z-test p = <0.001.
• Ibuprofen IR/ER (Wet Granulation): mean 17.34 versus 0.05 on control; difference 17.29 (95% CI 12.94 to 21.64), standardized effect d = 1.71; z-test p = <0.001.
• Naproxen: mean 12.66 versus 0.05 on control; difference 12.61 (95% CI 8.38 to 16.84), standardized effect d = 1.29; 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.

Peak Pain Relief Score

• 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:
  • Ibuprofen IR/ER (Roller Compaction): mean 3.42 versus 1.00 on control; difference 2.42 (95% CI 1.86 to 2.98), standardized effect d = 2.27; z-test p = <0.001.
  • Ibuprofen IR/ER (Wet Granulation): mean 3.39 versus 1.00 on control; difference 2.39 (95% CI 1.83 to 2.95), standardized effect d = 2.23; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Ibuprofen IR/ER (Roller Compaction) 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 higher for Ibuprofen IR/ER (Wet Granulation) than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The posted secondary outcomes cover pain relief, pain intensity, treatment failure, and timing of relief or failure. Listed measures include time to first perceptible relief, time to meaningful relief, time to treatment failure, treatment-failure percentage, time-weighted pain-intensity and pain-relief summaries, and confirmation of perceptible relief by meaningful relief. The record identifies 15 posted secondary outcomes and 17 outcome measures overall.

The available secondary summaries include peak pain relief score. Its group means are higher in the two ibuprofen arms than in placebo, with sponsor-reported ANOVA comparisons against placebo and p-values of <0.001. This is directionally consistent with the primary SPID pattern: the posted group summaries are higher in the active arms than in placebo for the measures described. The secondary outcomes add different views of pain relief and timing, but they do not replace the primary endpoint or establish a direct comparison between the two ibuprofen manufacturing processes.

The registry record lists 301 analyses. In general, examining many outcomes and analyses creates a multiplicity concern: even when each individual test uses a conventional threshold, the chance of at least one apparently notable finding can increase across a family of tests. The record does not report a multiplicity adjustment or define which secondary comparisons formed a confirmatory family. Accordingly, unadjusted secondary results carry less weight than a result interpreted within a clearly prespecified analysis plan with an identified multiplicity strategy.

Not every listed secondary outcome has a posted numerical summary in the registry record described for this analysis. The registry record does not explain the status of each outcome beyond the posted summaries. Broad consistency across reported measures can be informative, but it does not remove uncertainty about multiplicity, incomplete outcome reporting, or the analysis choices used for each measure.

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

• Time to First Perceptible Pain Relief
• Time to Treatment Failure
• Percentage of Participants With Treatment Failure
• Time-weighted Sum of Pain Intensity Difference From 0 to 4 Hours (SPID 0-4) and 4 to 8 Hours (SPID 4-8)
• Time-weighted Sum of Pain Relief and Pain Intensity Difference Scores (SPRID)
• Time-weighted Sum of Pain Relief Scores (TOTPAR)
• Percentage of Participants Achieving First Perceptible Relief Confirmed by Meaningful Relief
• Time to Meaningful Pain Relief

9. Statistical Interpretation

10. Statistical Methods Explained

The primary measure is continuous: each participant contributes a numerical SPID score, and the registry reports a mean and standard deviation for each arm. The mean describes the group’s average score. The standard deviation describes how dispersed participant scores are around that average; it is not the uncertainty in the estimated mean difference.

What does the mean difference represent?

A mean difference compares the average outcome in one arm with the average in a reference arm. For the posted primary comparisons, placebo is the reference. A positive difference is consistent with higher SPID in the active arm, and the endpoint definition says that higher positive SPID indicates improvement in pain intensity. The sponsor’s ANOVA estimates and the recalculated differences are separate estimates: the sponsor reports mean differences based on ANOVA, while recalculations use the posted group summaries and are described as unadjusted.

In general, comparing group means can be informative when the outcome is numerical and the question concerns average group-level response. It does not describe the full distribution of responses. Two groups with similar averages can still have different patterns of variability, and a mean difference does not imply that all participants’ scores lie near the mean.

What does a confidence interval communicate?

In general, a confidence interval expresses the uncertainty around an estimated effect using a range of values compatible with the analysis and its assumptions. A narrower interval indicates greater precision than a wider interval, while the interval’s location indicates which effect values are most consistent with the data and method. The sponsor reports 95% confidence intervals for the ANOVA comparisons. The recalculated bounds are presented separately and should not be mistaken for the sponsor’s ANOVA estimates.

A confidence interval is not a range containing every individual participant’s response. Nor does it, by itself, establish that an observed difference is important to patients. The registry record does not give a threshold for a clinically meaningful SPID difference, so the results cannot be classified against such a threshold from this record alone.

What does the p-value add?

A p-value describes how compatible the observed result is with a specified null hypothesis under the analysis model. The sponsor reports p <0.001 for each of the three primary comparisons with placebo. This is evidence against the relevant no-difference null under the reported analysis, but it does not measure the probability that the null hypothesis is true. It also does not measure the size, importance, or durability of an effect.

The recalculated p-values are unadjusted. The registry record does not state whether or how the sponsor adjusted for multiple comparisons. Therefore, the displayed p-values should not be interpreted as evidence that multiplicity was accounted for.

Why can summaries and analyses differ?

Recalculated results based on means, standard deviations, and group counts are simple unadjusted comparisons of posted summary statistics. The sponsor’s results are labeled ANOVA and report mean differences based on final values. Different analysis methods or data handling can produce different estimates, but the registry record does not identify the reason for the numerical differences in this study. Because the discrepancy flag is false, the posted results do not identify a discrepancy requiring the sponsor analysis to take precedence; nonetheless, the sponsor’s own reported results should be clearly distinguished from the recalculations.

General statistical methods also rely on assumptions about the outcome and analysis. The registry record names ANOVA for the sponsor comparisons but does not describe its full model, covariates, diagnostics, or missing-data procedures. It is not appropriate to infer those details. The data presented support a description of the posted estimates, intervals, and p-values, but not a reconstruction of the complete analysis plan.

Why does variability matter?

Standard deviations of 9.22, 9.35, 10.54, and 10.02 accompany the primary group means. In general, variability matters because participant outcomes differ and because greater variability can reduce the precision of a group comparison when other features are unchanged. It also cautions against treating the mean as a description of a typical individual without examining the distribution. The registry record does not post participant-level distributions for this endpoint.

11. Confidence Intervals and Precision

The sponsor’s 95% confidence intervals for the primary comparisons are 12.13 to 20.19 for roller-compaction ibuprofen versus placebo, 13.02 to 20.99 for wet-granulation ibuprofen versus placebo, and 8.33 to 16.26 for naproxen versus placebo. Each interval lies above zero, consistent with a positive mean difference under the reported ANOVA analysis. The intervals also show that the estimates are not exact: a range of positive differences is compatible with each analysis.

The intervals differ in their bounds and width, so the estimates have different degrees of precision. Precision is about how tightly an effect is estimated, not whether an effect is clinically important. The registry record does not define a clinically meaningful difference for SPID, so the intervals cannot be judged against such a threshold from the posted record.

The recalculated summary-statistic intervals have bounds of 12.63 to 21.01, 12.94 to 21.64, and 8.378 to 16.84 for the same comparisons. They are not identical to the sponsor’s reported ANOVA intervals. The registry record does not explain why the estimates and bounds differ, so the two sets should not be blended or treated as interchangeable. The sponsor’s intervals describe the sponsor-reported analysis; the recalculated intervals describe unadjusted recalculations from posted summaries.

In general, a confidence interval describes uncertainty in an estimated group difference, whereas the standard deviation describes variation among participant scores. The intervals do not show the range of individual responses and do not guarantee that future estimates will fall within their bounds. Their interpretation depends on the analysis and assumptions, some of which are not detailed in the registry record.

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 for the continuous outcomes in this study, not total events. The sample-size assumptions listed for the planning illustration are a two-sided significance level of 0.05, equal allocation between the two arms, a normal approximation, and an effect to detect set to the stated fraction of the observed effect. The planning rows therefore consider 100%, 75%, and 50% of the observed effect. The original trial’s own design assumptions and sample-size justification are not reported in the registry record.

The 80% power column gives the illustrative number of participants per arm for a design with an 80% chance of detecting the specified effect under the stated assumptions. The 90% power column gives the corresponding illustrative number per arm for a 90% chance. These are design-planning quantities under assumptions, not descriptions of the power achieved in this completed trial.

Smaller effects require more participants to detect under otherwise comparable assumptions. Thus the rows based on a smaller fraction of the observed effect generally call for larger per-arm planning values. The displayed calculations use effects estimated in this study, which may not be a reliable expectation for a future study. This is not observed power. For time-to-event outcomes, the planning convention differs: those figures refer to the total number of events, whereas the continuous-outcome figures refer to participants per arm.

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 = 16.820; pooled standard deviation σ = 9.305.
2. n = 2 × (1.96 + 0.842)² × 9.305² / 16.820² = 4.8, rounded up to 5 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 <- 16.82                      # observed difference in means
sigma <- 9.3047066047243                     # 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(913627)
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 (80% power), 7 (90% power)
 75% of observed effect: n per arm = 9 (80% power), 12 (90% power)
 50% of observed effect: n per arm = 20 (80% power), 26 (90% power)
power.t.test: 5.9 
Simulated power at n = 5 per arm: 0.708 (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. Analyses Reported by the Sponsor

The sponsor’s primary-outcome analyses are reported as ANOVA comparisons of each active-treatment group with placebo. The reported mean differences are 16.16 for roller-compaction ibuprofen, 17.00 for wet-granulation ibuprofen, and 12.30 for naproxen. The respective 95% confidence intervals are 12.13 to 20.19, 13.02 to 20.99, and 8.33 to 16.26; the reported p-value for each is <0.001.

The unadjusted recalculations from the posted means, standard deviations, and group counts give mean differences of 16.82, 17.29, and 12.61, respectively. Their interval bounds and estimates differ from the sponsor’s ANOVA results. These recalculations are not replacements for the sponsor’s analysis. The discrepancy flag is false, and the registry record does not explain the numerical differences or provide enough detail to reconstruct the sponsor’s full model.

The sponsor’s analysis should therefore be read as the registry’s reported inferential analysis, with recalculations serving as a separate check based on the posted summaries. The record does not report the full statistical analysis plan, so any unreported modeling choices or adjustments should not be inferred.

15. Multiplicity, Missing Data and Analysis Populations

The registry record reports a primary outcome, multiple secondary outcomes, and 301 analyses. It does not report a complete statistical analysis plan or state whether the sponsor adjusted for multiple outcomes, comparisons, or analyses. The primary sponsor-reported p-values are listed for the three active-versus-placebo comparisons, but the record does not describe whether these comparisons were treated as one family or how any family-wise error was controlled. The recalculated p-values are explicitly unadjusted.

As a general statistical issue, multiplicity arises when many hypotheses are tested. Repeated testing can make small p-values more likely even if no true effect exists across the tested family. Adjustments or a prespecified testing hierarchy can address this, but their interpretation depends on the planned family of hypotheses. Since that plan is not reported in the registry record, the posted individual p-values should not be treated as if an adjustment had necessarily been made.

The primary population is defined as randomized participants who dosed with study product and provided a baseline pain-severity assessment. The record does not report how many randomized participants failed to meet that definition, how missing endpoint observations were handled, or whether any sensitivity analyses assessed missing-data assumptions. It also does not detail whether all randomized participants were included in the sponsor’s analysis or how deviations from the intended analysis population were managed.

These omissions matter because exclusions and missing data can affect group comparisons, particularly when the reasons for missingness differ between groups or relate to outcomes. This is a general concern, not evidence that such bias occurred in this trial. Without the analysis plan and missing-data details, the robustness of the estimates to alternative analysis choices cannot be assessed from the registry record alone.

16. 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 0% reporting threshold.

Most frequent non-serious adverse event terms

The posted serious-adverse-event figures show 0 affected participants in each of the four arms. The numbers at risk were 29 for placebo, 53 for roller-compaction ibuprofen, 56 for wet-granulation ibuprofen, and 58 for naproxen. These are group-level registry counts for the safety summary and should be read as counts reported for the listed groups, not as proof that no adverse events of any kind occurred.

The adverse-event record lists other, non-serious adverse events for 8 participants in placebo, 3 in roller-compaction ibuprofen, 8 in wet-granulation ibuprofen, and 6 in naproxen. Those counts are distinct from the serious-adverse-event figures and should not be conflated with them. No serious adverse-event terms are listed. Death counts are not reported in the registry record.

Safety counts are descriptive. They do not establish that risks are absent, and they should be interpreted in light of the group sizes, duration, and completeness of adverse-event reporting. The registry record does not provide enough detail to assess event definitions, severity grading, or the timing of events.

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

The posted primary results show higher mean SPID scores in the ibuprofen and naproxen arms than in placebo over baseline to 12 hours. The sponsor-reported ANOVA comparisons have positive mean differences, 95% confidence intervals above zero, and p-values <0.001. The endpoint definition identifies higher positive SPID values with improvement in pain intensity. These registry entries describe the reported group-level results for this trial and its specified outcome.

They do not establish that every participant experienced improvement, that the observed group averages apply to other settings, or that differences persist beyond the measured interval. The registry record concerns a single dose for post-operative dental pain; conclusions should remain bounded by that population, treatment context, and follow-up period. It does not provide a threshold for a clinically meaningful difference, so statistical evidence alone cannot establish the practical importance of the estimated differences.

The study includes two ibuprofen formulations manufactured by different processes, but the listed primary sponsor analyses compare each active arm with placebo. The posted summaries do not include a sponsor-reported primary-outcome comparison directly between the two ibuprofen formulations. Similar-looking group means are not a formal test of equivalence or non-inferiority, and the record does not report such a design or analysis.

The findings also do not settle broader safety questions. The reported serious-adverse-event counts are zero in each arm, but the registry’s safety summary is not a guarantee of no risk and does not establish safety for other populations, doses, or durations. In general, statistical significance, clinical importance, and safety are separate questions requiring different evidence. The registry results address only part of that broader assessment.

18. Why This Trial Matters Statistically

Statistically, the study is notable for separating two manufacturing processes for the same stated 600 mg ibuprofen IR/ER formulation. That design reflects the registry’s stated concern that manufacturing could affect prototype performance. The four-arm comparison also includes placebo and naproxen, permitting the posted primary summaries to be read in a broader randomized-group context.

The primary endpoint combines repeated pain-intensity ratings into a time-weighted summary over baseline to 12 hours. That choice illustrates how longitudinal observations can be condensed into a continuous outcome for group comparison. It also highlights why the endpoint definition matters: score direction, scale, time window, and weighting determine what the resulting mean represents.

The record offers a useful contrast between the sponsor’s ANOVA estimates and simple unadjusted recalculations from group summaries. The values are not identical, underscoring that a mean difference depends on the analysis used and that summary data cannot reproduce every feature of a full model. The record does not explain the difference, making transparent separation of sponsor analyses and recalculations important.

Finally, the number of posted analyses and secondary measures makes multiplicity and selective reporting relevant interpretive issues. The record does not state the sponsor’s multiplicity strategy or full analysis plan. This limits how confidently individual secondary p-values can be interpreted and shows why prespecified analysis details are important alongside outcome estimates.

19. 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 gives a defined primary analysis population but does not report the complete statistical analysis plan, the original sample-size justification, or the assumptions used when the trial was designed. The planning illustrations based on observed effects are not substitutes for those original design details. The record also does not explain why the sponsor-reported ANOVA estimates differ from the unadjusted recalculations.

Although the study description says the two ibuprofen formulations were to be compared with placebo and each other, the posted sponsor analyses for the primary endpoint list comparisons with placebo and do not list a direct comparison between formulations. The available summaries therefore do not support a formal conclusion about whether the manufacturing processes yield equivalent or different primary outcomes.

The primary endpoint is limited to a time-weighted measure through 12 hours after a single dose in post-operative dental pain. The record does not establish whether these results generalize to other pain settings, dosing schedules, or follow-up periods. It also does not report a threshold for clinically meaningful change, limiting interpretation of the practical importance of the numerical differences.

Details of missing-data handling, participant flow, and sensitivity analyses are not reported in the registry record. Nor does the record state how multiplicity across the many posted analyses was addressed. These are reporting limitations; they do not establish that the trial’s conduct or analyses were deficient, but they constrain independent evaluation of robustness.

The safety summary gives group counts for serious and other adverse events, but does not provide further details of event timing, severity grading, or ascertainment. Zero reported serious adverse events in each arm should therefore be interpreted as a registry summary, not as proof that risk is absent.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Study Evaluating Ibuprofen 600 mg Extended Release (ER) For Dental Pain — NCT00913627.
• Registry record last updated 2018-03-22; status last verified 2018-02.
• Results first posted 2018-03-22.
• 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.

23. Record Summary

This completed randomized, double-masked, parallel-group Phase 2 study evaluated single-dose ibuprofen 600 mg IR/ER formulations made by roller compaction and wet granulation for post-operative dental pain. Placebo and naproxen arms were also included. The primary outcome was mean time-weighted sum of pain intensity difference from baseline to 12 hours in the defined ITT population.

The sponsor reported ANOVA mean differences versus placebo of 16.16, 17.00, and 12.30 for roller-compaction ibuprofen, wet-granulation ibuprofen, and naproxen, respectively, with each p-value <0.001. The group summaries and unadjusted recalculations show the same positive direction but differ numerically from the sponsor estimates. The registry record does not report the full analysis plan, multiplicity handling, missing-data procedures, or the original sample-size justification.