Ibuprofen/Acetaminophen Versus Nurofen Plus® and Panadeine® Extra Dental Pain Study: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Ibuprofen/Acetaminophen Versus Nurofen Plus® and Panadeine® Extra Dental Pain Study (NCT01229449), a randomized phase 3 study. The primary outcome is Change From Baseline in Area Under the Curve (AUC) of Pain Intensity and Relief Scores (SPRID).

2. Clinical Question

The clinical question concerns adults with postoperative pain after third molar extraction. The trial compared four active single-dose regimens with placebo and assessed analgesic efficacy and tolerability. The active regimens were ibuprofen 200 mg plus paracetamol 500 mg; ibuprofen 400 mg plus paracetamol 1000 mg; ibuprofen 400 mg plus codeine 25.6 mg, identified as Nurofen Plus®; and paracetamol 1000 mg plus codeine 30 mg, identified as Panadeine® Extra.

The primary question was whether the mean change from baseline in the area under the curve for pain intensity and relief scores over 0–12 hours differed among the treatment groups. The registry’s primary outcome describes the combined SPRID measure, built from pain intensity difference and pain relief assessments over follow-up. It also reports pairwise ANOVA comparisons, including comparisons of active regimens with placebo and comparisons among active regimens.

3. Trial Design

This was a phase 3, randomized, parallel-group, single-dose, placebo-controlled study described in the official title as double-blind and quadruple-masked. It was conducted at 3 sites and included 5 parallel groups: two ibuprofen/paracetamol regimens, Nurofen Plus®, Panadeine® Extra and placebo. The registry records enrollment of 678 and status as completed. The listed condition is post-operative pain.

The lower-dose combination was one tablet of ibuprofen 200 mg plus paracetamol 500 mg and one placebo tablet. The higher-dose combination was two tablets of ibuprofen 200 mg plus paracetamol 500 mg. Nurofen Plus® was two tablets of ibuprofen 200 mg plus codeine 12.8 mg, and Panadeine® Extra was two tablets of paracetamol 500 mg plus codeine 15 mg. The placebo group received two placebo tablets. These arm descriptions give the administered tablet regimens; the official title also states the corresponding dose combinations for the study comparison.

The primary outcome followed pain intensity and pain relief from baseline through 12 hours after dosing, with measurements scheduled at baseline and multiple post-dose times. The registry describes the primary analysis population as an intention-to-treat population requiring study medication, completed baseline efficacy assessments and at least one post-baseline assessment. It further states that subjects with treatment administration errors were analyzed according to treatment assignment, but the wording of that population description ends before the sentence is complete. Further details are not reported in the registry record.

The trial’s original sample-size justification, allocation ratio, detailed randomization procedure, and any interim-analysis plan are not reported in the registry record. The posted arm-level counts describe outcome data and should not be read as a substitute for those unreported design details.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Before assignment: A total of 678 subjects were randomised into the study.173 subjects received ibuprofen 200 mg + paracetamol 500 mg, 169 subjects received Nurofen Plus®, 168 subjects received ibuprofen 400 mg + paracetamol 1000 mg, 113 subjects received Panadeine® Extra and 55 subjects received placebo.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Intention-to-treat (ITT) population includes all randomized subjects who took the study medication, completed the baseline efficacy assessments and had at least one post-baseline assessment. Any subjects with treatment administration errors were analyzed according to the treatment to which they were randomized.

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 Change From Baseline in Area Under the Curve (AUC) of Pain Intensity and Relief Scores (SPRID), measured over 0 (baseline), 0.25, 0.5, 0.75, 1, 1.5, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11 and 12 hours post-dose.

The primary endpoint is change from baseline in the area under the curve of pain intensity and relief scores, abbreviated SPRID, over 0–12 hours. An area under the curve combines assessments taken across follow-up into a measure that reflects both the size and timing of recorded scores. The registry says the calculation used linear trapezoids and assumed that the baseline assessment occurred at time zero. It reports the outcome in units on a scale multiplied by hours.

SPRID combines pain intensity difference, or PID, and pain relief, or PR. Pain intensity was recorded using a 4-point ordinal scale from 0 for no pain to 3 for severe pain. Total pain relief was recorded on a 5-point ordinal rating scale from 0 for none to 4 for complete relief. The description also gives a 0mm-to-100mm range for the pain score, with 0mm for no pain and 100mm for worst pain. These different scale descriptions should be interpreted as part of the registry’s operational definition, rather than as interchangeable units.

A repeated-assessment summary is used because pain can change during the post-dose follow-up, and a single reading would not capture that time course. AUC condenses the sequence into one endpoint for comparing group means. Its interpretation depends on the construction and direction of the component scores: in the posted summaries, the active-group means are higher than the placebo mean. The endpoint is a study measure, not a direct account of each participant’s experience or a complete measure of tolerability.

7. Results Posted in the Registry

• Ibuprofen 200mg + Paracetamol 500mg (Lower Dose): mean 2.68 versus 0.54 on control; difference 2.14 (95% CI 1.71 to 2.57), standardized effect d = 1.39; z-test p = <0.001.
• Ibuprofen 400mg + Paracetamol 1000mg (Higher Dose): mean 3.30 versus 0.54 on control; difference 2.76 (95% CI 2.32 to 3.20), standardized effect d = 1.72; z-test p = <0.001.
• Nurofen Plus®: mean 2.62 versus 0.54 on control; difference 2.08 (95% CI 1.63 to 2.53), standardized effect d = 1.26; z-test p = <0.001.
• Panadeine® Extra: mean 1.93 versus 0.54 on control; difference 1.39 (95% CI 0.93 to 1.85), standardized effect d = 0.95; 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.

Change From Baseline in Peak Pain Intensity Difference (Peak PID - Ordinal)

• 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 200mg + Paracetamol 500mg (Lower Dose): mean 1.78 versus 0.60 on control; difference 1.18 (95% CI 0.92 to 1.44), standardized effect d = 1.41; z-test p = <0.001.
  • Ibuprofen 400mg + Paracetamol 1000mg (Higher Dose): mean 1.93 versus 0.60 on control; difference 1.33 (95% CI 1.07 to 1.59), standardized effect d = 1.61; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Ibuprofen 200mg + Paracetamol 500mg (Lower Dose) 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 400mg + Paracetamol 1000mg (Higher Dose) than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline in Peak Pain Relief (PR)

• 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 200mg + Paracetamol 500mg (Lower Dose): mean 3.06 versus 0.96 on control; difference 2.10 (95% CI 1.76 to 2.44), standardized effect d = 2.02; z-test p = <0.001.
  • Ibuprofen 400mg + Paracetamol 1000mg (Higher Dose): mean 3.25 versus 0.96 on control; difference 2.29 (95% CI 1.96 to 2.62), standardized effect d = 2.39; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Ibuprofen 200mg + Paracetamol 500mg (Lower Dose) 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 400mg + Paracetamol 1000mg (Higher Dose) than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The registry lists secondary outcomes covering pain intensity difference, pain relief, additional AUC summaries, individual pain readings and peak measures. The available numeric summaries for the posted peak pain intensity difference and peak pain relief outcomes show higher group means for the active regimens than for placebo. This overall direction is consistent with the primary outcome summaries, which also have higher active-group means than the placebo mean.

These related endpoints provide a broader view of pain ratings over follow-up and at peak response, but they do not independently establish the primary finding. Several measures share underlying pain assessments and may therefore be correlated rather than fully independent confirmations. The registry record lists 9 posted secondary outcomes, while detailed numeric summaries and recalculated contrasts are not present for every listed secondary measure. Where values or analyses are not reported in the registry record, no conclusion about those outcomes can be drawn from their titles alone.

Unadjusted secondary results carry less weight when many outcomes or comparisons are examined because the chance of at least one apparently notable result can increase across a collection of tests. The registry does not report a multiplicity procedure for these analyses. That does not establish that no adjustment was used in the underlying trial analysis; it means the procedure is not reported in the registry record. Secondary results are best read as supportive descriptions of the outcome pattern, with priority given to the prespecified primary endpoint and the sponsor’s reported analysis.

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

• Change From Baseline in AUC (0-8h) of SPRID
• Change From Baseline in AUC for Pain Intensity Difference Scores (SPID)
• Change From Baseline in AUC of Pain Relief Scores (TOTPAR)
• Change From Baseline in AUC of Individual Reading Pain Intensity and Relief Scores (SPRID)
• Individual Pain Intensity Differences (Ordinal)
• Individual Pain Intensity Differences Visual Analogue Scale (VAS)
• Change From Baseline in Peak Pain Intensity Difference (Peak PID - Ordinal)
• Change From Baseline in Peak Pain Relief (PR)

9. Statistical Interpretation

10. Statistical Methods Explained

The registry describes the primary endpoint as a continuous measure summarized by a mean and standard deviation. A mean gives the group’s average recorded outcome, while the standard deviation describes how dispersed individual observations are around that average. A mean difference compares the averages in two groups. It is expressed in the outcome’s units, which for the primary endpoint are units on a scale multiplied by hours.

What does the AUC measure?

Area under the curve summarizes measurements across time rather than treating each scheduled reading as an unrelated endpoint. The registry says the SPRID AUC was calculated with the linear trapezoid method, which connects successive observations with straight lines and estimates the area between them. The baseline assessment was assumed to be at time zero. The resulting value reflects both the scores and their timing during the 0–12-hour follow-up. It does not retain every detail of the sequence, so two individuals with different score patterns could in principle have similar summary values.

How should a mean difference be read?

For each recalculated active-versus-placebo comparison, the estimate is the active-group mean minus the placebo-group mean. A positive estimate therefore means the posted active-group average is numerically higher on this recorded outcome. For example, the recalculated mean difference for the lower-dose combination is 2.14, with a 95% confidence interval from 1.707 to 2.573. The higher-dose combination estimate is 2.76, with a 95% confidence interval from 2.319 to 3.201. The registry’s recorded primary outcome and scale descriptions should guide interpretation of direction; the positive sign alone is not a universal definition of benefit.

The recalculated confidence intervals use the posted summary data and are unadjusted. In general, a confidence interval describes a range of values compatible with the data and the calculation’s assumptions. It conveys precision as well as direction. A narrow interval indicates a more precise estimate under that calculation; a broad interval indicates greater uncertainty. It does not mean that the true value has a stated probability of lying within that particular interval.

Why distinguish the recalculation from ANOVA?

The registry reports pairwise analyses using ANOVA, including p-values and superiority labels. The posted recalculations instead use a simple, unadjusted comparison of the two group means and their summary variability. These approaches need not produce identical inferential results. A trial analysis can use model structure, adjustments or other choices that are not recoverable from arm means and standard deviations alone. The registry record does not report enough detail to reconstruct all those choices. Because the record flags a discrepancy, the sponsor’s own reported analysis takes precedence over the recalculated comparison.

A p-value describes how compatible the data are with a specified null hypothesis under the analysis assumptions; it is not the probability that the null hypothesis is true, nor a measure of the size or importance of an effect. The sponsor-reported p-values should therefore be considered alongside the means, uncertainty and endpoint definition. The unadjusted p-values in the recalculated comparisons answer a narrower question and do not account for the set of comparisons made across treatment groups and outcomes.

Why can outcome variability matter?

Standard deviations describe variation among recorded outcomes. When variation is substantial relative to a mean difference, the group means can be estimated less precisely. The posted primary summaries give standard deviations for every arm, and the recalculation uses pooled variability for each two-group contrast. In general, pooling assumes a common variability for the two groups being compared. If group variances differ materially, a pooled approach may not represent the uncertainty as well as a method that allows separate variances. The record’s recalculated values are explicitly unadjusted summaries, not a substitute for assessment of model assumptions in the trial analysis.

The primary measure combines components based on ordinal pain intensity and relief ratings and integrates them over time. Treating the resulting AUC as a continuous outcome supports mean-based comparisons, as used in the record, but the construction does not make the original component ratings continuous or erase their scale properties. The record does not report a detailed distributional assessment, residual diagnostics, or sensitivity analyses for the endpoint.

What limits reconstruction?

Arm-level means, standard deviations and counts allow a basic two-group comparison, but they do not reveal participant-level trajectories, the covariance among repeated readings, or how missing post-dose observations were handled. Nor do they show whether the sponsor’s ANOVA used adjustment for site or other variables. Such analysis details are not reported in the registry record. The recalculation is therefore an aid to reading the posted summary statistics, not a reconstruction of the full trial analysis.

11. Confidence Intervals and Precision

Precision is reflected by the width of the confidence interval around an estimate. The recalculated active-versus-placebo intervals for the primary mean differences are entirely above zero. For the lower-dose combination, the estimate is 2.14 and the 95% confidence interval is 1.707 to 2.573. For the higher-dose combination, the estimate is 2.76 and the interval is 2.319 to 3.201. Nurofen Plus® has an estimate of 2.08 with an interval from 1.634 to 2.526, while Panadeine® Extra has an estimate of 1.39 with an interval from 0.933 to 1.847.

These intervals arise from unadjusted recalculations of the posted group summaries. They describe uncertainty for each pairwise mean difference under that calculation. They do not represent the sponsor’s full ANOVA analysis, and the registry’s recorded comparisons do not provide confidence limits. The record flags a discrepancy, so the sponsor’s own analysis takes precedence for interpreting the trial’s formal reported comparisons.

Intervals that exclude zero are consistent with a positive mean difference under the recalculation, but interval exclusion is not a measure of clinical importance. The endpoint’s scale and meaning matter, and the available record does not define a threshold for a clinically important difference. The interval also does not address all sources of uncertainty, including multiplicity across comparisons, unreported model choices, or missing outcome data. Thus, the intervals convey statistical precision conditional on the posted summary statistics and calculation, rather than complete certainty about the treatment contrast.

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 sample-size figures are planning illustrations based on the observed effect, not the original trial’s design calculation. For these continuous outcomes, the figures are participants per arm, not total events. The illustration assumes a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. It considers detecting the observed effect or a stated fraction of that effect. The original design assumptions and sample-size justification are not reported in the registry record.

The 80% power column gives the number of participants per arm estimated to be needed for an 80% chance of detecting the specified effect under the planning assumptions, if that effect is the true one and the assumptions hold. The 90% power column expresses the corresponding planning target for a 90% chance. These are design-planning quantities, not evidence that the completed trial had that probability of finding a result.

Rows for planning at a smaller fraction of the observed effect require more participants per arm than rows based on the full observed effect. This follows because a smaller difference is harder to distinguish from random variation when other assumptions are held constant. The figures are therefore useful for illustrating how planning needs respond to the assumed effect size, but should not be treated as a recommendation or as a reconstruction of the trial’s original design. The values are not observed power.

13. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = 2.140; pooled standard deviation σ = 1.540.
2. n = 2 × (1.96 + 0.842)² × 1.540² / 2.140² = 8.1, rounded up to 9 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 <- 2.14                      # observed difference in means
sigma <- 1.54029332914968                     # 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(1229449)
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 = 9 (80% power), 11 (90% power)
 75% of observed effect: n per arm = 15 (80% power), 20 (90% power)
 50% of observed effect: n per arm = 33 (80% power), 44 (90% power)
power.t.test: 9.2 
Simulated power at n = 9 per arm: 0.790 (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 registry’s own primary analyses are reported as pairwise ANOVA tests with superiority labels and p-values. For example, the higher-dose ibuprofen/paracetamol group is reported as superior to placebo with p < 0.001, and its comparison with the lower-dose combination has p < 0.001. The record also reports p = 0.72 for the lower-dose combination versus Nurofen Plus®. These are the sponsor’s recorded inferential results; the registry does not provide estimates or confidence intervals for those ANOVA comparisons.

The recalculated comparisons use the posted arm means and standard deviations to produce simple, unadjusted mean differences, confidence intervals and p-values. They are a separate statistical reading of summary data and do not reproduce all possible features of the sponsor’s analysis. The record flags a discrepancy between the two, so the sponsor’s own analysis takes precedence. Recalculated estimates can still help readers understand the scale and precision of a basic contrast, but they should not be presented as the trial’s formal analysis or used to override its reported results.

The registry does not report enough detail about the ANOVA specification, adjustment variables, or multiplicity handling to explain the discrepancy. Any explanation beyond the distinction between the reported analysis and the unadjusted recalculation would be speculative.

15. Multiplicity, Missing Data and Analysis Populations

The study compares 5 treatment groups, and the registry reports multiple pairwise primary-outcome analyses as well as a range of secondary outcomes. Testing many contrasts can increase the chance of obtaining at least one small p-value even when there is no underlying difference for some comparisons. A multiplicity procedure can address this by controlling the interpretation of a family of tests. The registry record does not report whether or how the primary pairwise comparisons or secondary analyses were adjusted for multiplicity. Accordingly, the reported p-values should be interpreted in light of that missing information rather than assumed to be adjusted or unadjusted beyond what is explicitly stated.

The primary analysis population is described as randomized subjects who took the study medication, completed baseline efficacy assessments and had at least one post-baseline assessment. This is a defined analysis population, not necessarily all randomized participants. The record further says subjects with treatment administration errors were analyzed according to treatment assignment, but its description of that rule is incomplete. The registry does not report the number excluded from the primary analysis population, reasons for exclusion, or a detailed accounting of missing outcome assessments.

Missing data can affect a repeated-measure endpoint because the AUC relies on observations across follow-up. The registry describes the scheduled assessments and the trapezoidal calculation but does not report how unobserved readings were handled, whether any imputation was performed, or whether sensitivity analyses assessed alternative missing-data assumptions. These omissions limit independent evaluation of how incomplete follow-up might affect the outcome summaries.

The detailed statistical plan, including any interim analyses, covariate adjustments, model diagnostics and analysis hierarchy, is not reported in the registry record. Their absence from the record does not show that the study lacked such procedures; it restricts what can be inferred about them.

16. 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 5% reporting threshold.

Most frequent non-serious adverse event terms

The registry reports zero serious adverse events in every group and zero deaths in every group. The number at risk for serious events is listed separately for each treatment arm, and the serious-event count is zero for each. These figures indicate what was recorded in the registry’s serious adverse event summary; they do not establish that no adverse effects of any kind occurred.

Other adverse events were reported in all groups. The recorded affected counts are 88 for the lower-dose ibuprofen/paracetamol group, 87 for the higher-dose combination, 97 for Nurofen Plus®, 72 for Panadeine® Extra and 35 for placebo. The registry does not provide serious adverse event terms because the serious-term list is empty. The figures alone do not describe event type, duration, severity, timing, or whether events were judged related to study medication. They also do not support a full comparative safety assessment. These are descriptive registry counts, not individualized risk estimates or medical advice.

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

The record documents a randomized, masked comparison of single-dose regimens in adults with postoperative pain after third molar extraction. For the primary 0–12-hour SPRID outcome, the posted mean values are higher in every active-treatment group than in the placebo group. The sponsor’s recorded ANOVA analyses label the active-versus-placebo comparisons as superiority results, with p-values below < 0.001. The registry also reports differences among some active groups and no clear statistical difference for the lower-dose combination compared with Nurofen Plus® in its pairwise analysis.

Those findings describe average scores on a defined, composite study endpoint over a limited follow-up period. They do not show how every participant responded, establish a clinically important threshold, or answer questions about use beyond the single dose and 12-hour observation window. Group means and p-values do not by themselves determine the importance of a difference to patients. The registry does not report a threshold for clinical importance.

The recalculated mean differences and confidence intervals are unadjusted checks based on posted summary statistics. Because the registry flags a discrepancy, the sponsor’s own analysis takes precedence. The recalculation should not be mistaken for a replacement analysis, and statistical significance should not be equated with certainty about all relevant effects.

The safety record reports no serious adverse events or deaths in any group, while other adverse events were recorded in each group. These summaries do not provide detailed event descriptions or establish comparative safety. The registry also does not report enough information to assess multiplicity handling, missing-data procedures, or all elements of the statistical analysis plan. Taken together, the record supports a description of the posted outcome patterns and their statistical uncertainty, but it does not settle questions beyond the trial’s population, regimens, endpoint and recorded follow-up.

18. Why This Trial Matters Statistically

This trial illustrates how a multi-arm design can address several related treatment questions within a common study: comparisons with placebo, comparisons between dose levels, and comparisons with active regimens containing codeine. Those contrasts are not interchangeable. A placebo comparison asks whether an active group differs from placebo on the recorded endpoint; a comparison among active groups addresses a different question. The registry reports both kinds of pairwise analyses.

The primary endpoint also demonstrates the trade-off involved in summarizing repeated assessments. SPRID AUC condenses pain intensity difference and relief scores across follow-up into a single mean outcome. This makes a group comparison possible without treating every time point as a separate primary result, while also hiding some detail about the timing and shape of each participant’s trajectory.

The record is useful for illustrating why statistical interpretation should distinguish a sponsor-reported model analysis from an unadjusted recalculation. Arm means and standard deviations allow a transparent basic comparison, but cannot recover every aspect of an ANOVA or missing-data strategy. Here, the discrepancy flag makes that distinction especially important, and the sponsor’s analysis takes precedence.

Finally, the design presents a multiplicity question: several groups, pairwise comparisons and secondary endpoints appear in the record. Without a reported adjustment strategy, isolated p-values should not be treated as a complete account of the evidence. The case highlights the need to read effect estimates, intervals, analysis populations and outcome definitions alongside significance labels, while avoiding conclusions that extend beyond the registered study context.

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 primary endpoint is a combined AUC measure built from pain intensity difference and pain relief ratings. Its interpretation depends on the registry’s scoring and calculation definitions, including the description of the score range and the use of a linear trapezoid method. The composite may make comparisons concise, but it does not reveal the full time course of pain assessments or each component’s contribution to the summary.

The study was single dose and followed the primary endpoint through 12 hours after dosing. The record therefore does not address repeated dosing or outcomes beyond that follow-up. Participants were adults with postoperative dental pain after third molar extraction, so the registry record does not establish how results apply to other populations or pain settings.

The record does not report the original sample-size justification, detailed allocation procedure, analysis plan, multiplicity approach, or handling of missing readings. The ITT population wording is incomplete, and the number and reasons for any exclusions from the primary analysis are not stated. These gaps restrict assessment of analysis choices and potential bias.

The recalculated contrasts are unadjusted and differ from the sponsor’s reported analysis, a discrepancy explicitly flagged in the record. The sponsor’s analysis takes precedence, but the registry does not provide enough model detail to explain the difference. Confidence intervals from the recalculations consequently should not be treated as intervals for the sponsor’s ANOVA estimates.

Finally, the safety summary provides counts of serious and other adverse events without event terms, timing, severity or attribution details. It is descriptive and cannot fully characterize comparative tolerability.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Ibuprofen/Acetaminophen Versus Nurofen Plus® and Panadeine® Extra Dental Pain Study — NCT01229449.
• Registry record last updated 2018-09-17; status last verified 2018-08.
• Results first posted 2018-09-17.
• 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

The registry describes a completed phase 3 randomized, quadruple-masked, parallel-group, single-dose study conducted at 3 sites, with enrollment of 678. Five groups received two ibuprofen/paracetamol combinations, Nurofen Plus®, Panadeine® Extra or placebo. The primary outcome was change from baseline in the 0–12-hour AUC of pain intensity and relief scores.

The posted primary means are higher in each active group than in the placebo group, and the registry reports ANOVA superiority results for active-treatment comparisons with placebo. The unadjusted recalculations give positive mean differences with confidence intervals above zero, but the record flags a discrepancy, so the sponsor’s own analysis takes precedence. Serious adverse events and deaths are reported as zero in every group; other adverse events were recorded in all groups. Multiplicity handling, detailed missing-data procedures and several trial-design assumptions are not reported in the registry record.