Evaluation of the Safety and Efficacy of Reformulated Raltegravir (MK-0518) 1200 mg Once Daily in Combination With TRUVADA™ in Human Immunodeficiency Virus (HIV)-1 Infected, Treatment-Naive Participants (MK-0518-292): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Evaluation of the Safety and Efficacy of Reformulated Raltegravir (MK-0518) 1200 mg Once Daily in Combination With TRUVADA™ in Human Immunodeficiency Virus (HIV)-1 Infected, Treatment-Naive Participants (MK-0518-292) (NCT02131233), a randomized phase 3 study. The primary outcome is Percentage of Participants Achieving <40 Copies/mL Human Immunodeficiency Virus-1 (HIV-1) Ribonucleic Acid (RNA) at Week 48.

2. Clinical Question

The comparison concerns two raltegravir schedules and formulations within combination therapy, rather than raltegravir versus no active treatment. The registry describes the primary hypothesis as non-inferiority. It does not report the non-inferiority margin in the record summarized for this analysis, so the numerical criterion for declaring non-inferiority cannot be evaluated from the posted information alone.

The central statistical question is therefore about the comparative Week 48 response and the uncertainty around the difference, interpreted alongside the sponsor’s reported non-inferiority analysis. The result describes the analyzed trial population and endpoint; it does not, by itself, establish what would happen in populations or settings not represented in the record.

3. Trial Design

This was a Phase III, randomized, parallel-group, active-comparator-controlled trial. The registry identifies the masking as triple. Participants were assigned to reformulated raltegravir 1200 mg once daily or raltegravir 400 mg twice daily, with TRUVADA™ once daily in both groups. Placebo regimens were included alongside the active treatments, as described in the arm descriptions.

The registry lists 802 participants enrolled. For the primary endpoint, the reported arm populations are 531 for reformulated raltegravir and 266 for raltegravir. The primary population is described as all randomized participants who received at least one dose of study treatment. The registry record does not report the allocation ratio, the randomization procedure, or detailed reasons why the enrollment count and endpoint arm counts differ.

The trial is marked completed. Its recorded start date is 2014-05-23, and the primary completion date is 2015-12-21. The assigned regimens are described for 96 weeks. The primary endpoint was assessed at Week 48, while the record also lists outcomes at Week 96 and safety outcomes over specified follow-up periods.

Randomization and masking are design features intended to support a fair comparison and reduce the influence of expectations or knowledge of treatment assignment. In general, an active-comparator design asks whether the new regimen’s measured outcomes compare acceptably with an established active regimen under the trial conditions; it is not a comparison against no treatment. Detailed descriptions of concealment, masking procedures, adherence monitoring, and protocol deviations are not reported in the registry record.

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: These results stop at Week 96.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: All randomized participants who received at least one dose of study treatment

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.

Population: All Treated Participants

6. Primary Endpoint

The registry lists the primary outcome as Percentage of Participants Achieving <40 Copies/mL Human Immunodeficiency Virus-1 (HIV-1) Ribonucleic Acid (RNA) at Week 48, measured over Week 48.

The primary endpoint is the percentage of participants with HIV-1 RNA <40 copies/mL at Week 48. Blood samples collected at Week 48 were assessed using the Abbott RealTime HIV-1 Assay. The record states that the assay’s limit of reliable quantification is 40 copies/mL. The endpoint therefore classifies participants by whether their measured viral RNA is below that threshold at the specified visit.

This type of endpoint turns a laboratory measurement into a binary outcome for each participant: the threshold is either met or not met under the trial’s analysis definition. The result is then expressed as a percentage in each treatment group. In general, a threshold-based response can be easier to interpret as a proportion of participants reaching a defined state than as a change in the underlying continuous measurement. It also discards detail about values on either side of the threshold, so it does not describe the full distribution of RNA measurements.

The primary analysis used the NC=F approach as defined by the FDA “snapshot” approach. The registry says missing data were treated as failures regardless of the reason. Thus, the reported response proportions reflect both the measured threshold status and this missing-data rule. The primary endpoint is clinically interpretable as a response proportion at a fixed time, but its meaning depends on the assay threshold, visit timing, analysis population, and treatment of missing observations.

The record identifies this as the endpoint for the primary non-inferiority hypothesis. It does not report the planned non-inferiority margin or the details needed to independently assess how that margin was chosen.

7. Results Posted in the Registry

• Raltegravir: 88.3% (235/266) versus 88.9% (472/531) on control; risk difference -0.5 percentage points (95% CI -5.2 to 4.1), risk ratio 0.99 (0.94–1.05); unadjusted two-proportion z-test p = 0.819.

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.

Percentage of Participants Achieving <40 Copies/mL Human Immunodeficiency Virus-1 (HIV-1) Ribonucleic Acid (RNA) at Week 96

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Raltegravir: 80.1% (213/266) versus 81.5% (433/531) on control; risk difference -1.5 percentage points (95% CI -7.3 to 4.4), risk ratio 0.98 (0.91–1.06); unadjusted two-proportion z-test p = 0.618.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Raltegravir and the control. The interval gives the range of effects that remain compatible with the data.

Percentage of Participants With an AE After 96 Weeks of Treatment

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Raltegravir: 94.0% (250/266) versus 90.8% (482/531) on control; risk difference 3.2 percentage points (95% CI -0.6 to 7.0), risk ratio 1.04 (0.99–1.08); unadjusted two-proportion z-test p = 0.118.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Raltegravir and the control. The interval gives the range of effects that remain compatible with the data.

Percentage of Participants With a Drug-Related AE at Week 48

• Endpoint type: Binary: the percentage of participants with the event (counts rebuilt from the posted percentages and group sizes).
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Raltegravir: 27.1% (72/266) versus 25.0% (133/531) on control; risk difference 2.0 percentage points (95% CI -4.5 to 8.5), risk ratio 1.08 (0.84–1.38); unadjusted two-proportion z-test p = 0.538.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Raltegravir and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes extend the Week 48 primary question to later response, immune-cell measures, and safety outcomes. The registry lists Week 96 HIV-1 RNA response, change in CD4 cell count, adverse events, drug-related adverse events, and serious adverse events among the secondary measures. The secondary results described in the record include a Week 96 response comparison, adverse events after 96 weeks of treatment, and drug-related adverse events at Week 48.

At a broad level, the posted Week 96 response percentages are close to the primary Week 48 percentages, and the unadjusted comparison is not strongly differentiated by its p-value. The additional safety comparisons are descriptive secondary findings. They provide context beyond the primary endpoint, but do not change what the primary Week 48 analysis measured or resolve the missing non-inferiority margin.

These secondary results should carry less confirmatory weight than the primary result. General explanation: when several outcomes are tested, the chance of observing at least one apparently notable finding can increase if no adjustment or testing hierarchy is used. The registry record does not report a multiplicity adjustment, a gatekeeping sequence, or a prespecified hierarchy for interpreting the secondary outcomes. Unadjusted p-values should therefore be treated as exploratory descriptions rather than as independent proof of treatment differences.

Secondary outcomes also differ in their definitions, follow-up periods, and data requirements. A response proportion, a change in CD4 count, and an adverse-event proportion do not measure the same construct. The posted findings should be interpreted outcome by outcome, with attention to endpoint-specific analysis and missing-data handling; those details are not reported in the registry record for all secondary measures.

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

• Percentage of Participants Achieving <40 Copies/mL Human Immunodeficiency Virus-1 (HIV-1) Ribonucleic Acid (RNA) at Week 96
• Change From Baseline in Cluster of Differentiation 4 (CD4) Cell Count at Week 48
• Change From Baseline in CD4 Cell Count at Week 96
• Percentage of Participants With an Adverse Event (AE) at Week 48
• Percentage of Participants With an AE After 96 Weeks of Treatment
• Percentage of Participants With a Drug-Related AE at Week 48
• Percentage of Participants With a Drug-Related AE After 96 Weeks of Treatment
• Percentage of Participants With a Serious Adverse Event (SAE) at Week 48

9. Statistical Interpretation

10. Statistical Methods Explained

For a binary endpoint, each participant is classified as having or not having the event of interest. Here the event is achieving HIV-1 RNA <40 copies/mL at Week 48. The arm-level percentage is the reported proportion meeting that definition. General explanation: the uncertainty around a proportion depends on both the observed proportion and the number of participants contributing to it; a confidence interval communicates a range of values compatible with the data and the method’s assumptions.

What the confidence intervals describe

The arm-specific 95% confidence intervals describe uncertainty in each response percentage. A confidence interval is not a guarantee that the true value lies in the displayed range, nor is it a probability statement about this particular trial result. In general, intervals are more useful when read with the point estimate and the comparison interval, rather than as a binary test of whether two separate arm intervals overlap.

The recalculated comparison is expressed as a risk difference. General explanation: a risk difference subtracts one group’s event proportion from the other group’s event proportion, so zero represents no difference. Its confidence interval describes uncertainty in that contrast. The primary recalculated interval spans zero; the unadjusted p-value is 0.819. These calculations are not adjusted for any factors and should not be confused with the sponsor’s reported non-inferiority analysis.

What non-inferiority means

General explanation: a non-inferiority trial asks whether the new regimen’s outcome is not unacceptably worse than the comparator, according to a prespecified margin. It is not enough that a conventional test fails to find a difference. The margin and the direction in which the difference is defined are essential to interpreting the confidence interval against the trial’s criterion. The registry describes a non-inferiority hypothesis and posts a sponsor analysis, but the margin and the method used for that analysis are not reported in the registry record. Accordingly, the available information does not allow independent verification of the decision rule.

How missing outcomes are handled

The primary analysis used NC=F under the FDA “snapshot” approach and treated all missing data as failures regardless of reason. This defines how missing Week 48 observations enter the binary response outcome. General explanation: treating missing observations as failures is one way to avoid counting an unobserved response as a success, but it can affect the estimated response proportions and can be sensitive to patterns of missingness. The record does not provide the number of missing observations, their reasons, or a sensitivity analysis for alternative assumptions.

The listed primary population includes randomized participants who received at least one dose. The registry does not report a separate intention-to-treat analysis, a per-protocol analysis, or details on exclusions from each analysis. Such details matter particularly for non-inferiority designs because analysis-population choices can affect the interpretation of the comparison.

How to interpret the unadjusted p-values

General explanation: a p-value summarizes how unusual data at least as extreme as those observed would be if the tested null hypothesis and model assumptions held. It is not the probability that the null hypothesis is true, and it does not measure the size or clinical importance of an effect. The posted unadjusted p-values are descriptive of the recalculated comparisons; the record does not report whether these tests were prespecified or how they relate to the sponsor’s primary non-inferiority procedure.

For the Week 48 primary comparison, the recalculated p-value is 0.819. The sponsor’s reported analysis does not include a p-value in the record. The sponsor analysis is presented as an estimated difference with a 95% confidence interval, which is the information relevant to assessing a margin-based non-inferiority claim when the margin is known.

Why binary outcomes may need careful interpretation

General explanation: converting a measurement into a threshold outcome makes the result easier to express as a response proportion, but participants just below and just above the threshold are classified differently even if their underlying measurements are close. The endpoint therefore answers a specific threshold question; it does not describe the magnitude of RNA reduction or the distribution of values among participants who did not meet the threshold.

The primary result is based on the posted endpoint definition and analysis population. Assay details are limited to the stated method and limit of reliable quantification. Further analysis choices, including the statistical method underlying the sponsor’s reported difference, are not reported in the registry record.

11. Confidence Intervals and Precision

The Week 48 response estimates are 88.9% for reformulated raltegravir and 88.3% for raltegravir. Their 95% confidence intervals are 85.9% to 91.4% and 83.9% to 91.9%, respectively. These intervals convey uncertainty around each arm’s response percentage; they are not intervals for the between-arm difference.

The recalculated difference interval includes values on both sides of no difference. This means the observed summary data do not pin down the direction of the underlying difference at the interval’s stated confidence level. The sponsor analysis reports an estimated difference of 0.510 with a 95% confidence interval from -4.204 to 5.223. The sponsor interval also covers zero, but non-inferiority is assessed against a prespecified margin rather than against zero alone. That margin is not reported in the registry record.

Confidence intervals are most informative when considered with the endpoint definition, the analysis population, and the decision threshold. For a non-inferiority question, the interval’s relation to the margin is central. Without the margin, the sponsor interval cannot be classified against the trial’s non-inferiority criterion based solely on the posted information.

The Week 96 arm values are reported as 81.5% and 80.1%, but their displayed arm confidence limits repeat the Week 48 limits. Those limits therefore do not provide reliable Week 96-specific precision information in the registry record. More generally, estimates from later follow-up can be affected by the number of participants with evaluable data and by missing-data handling; those details for Week 96 are not reported 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 illustrations based on the observed effect, not the trial’s original design calculation. For these binary outcomes, the entries are participants per arm, not total events. The stated assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each planning row uses the stated fraction of the observed effect as the effect to detect.

The 80% power column gives the estimated participants per arm for a design that would have an 80% probability of detecting the specified effect under those assumptions, if the assumed effect and analysis conditions held. The 90% power column gives the corresponding planning count for 90% power. These are design-planning quantities, not evidence that the completed trial had a particular probability of detecting its result.

Rows for 100%, 75%, and 50% of the observed effect illustrate how changing the target effect changes the planning count. Smaller effects require more participants to detect, all else held fixed, which is why the smaller-effect rows have larger counts. For the primary endpoint, the planning entries are 53,698 and 71,885 participants per arm for 100% of the observed effect; 94,966 and 127,132 for 75%; and 212,556 and 284,551 for 50%, for 80% and 90% power respectively.

The curve should be read as a visual representation of how the planning requirement varies with the target effect under the same assumptions. These calculations are not observed power. The registry record does not report the assumptions used in the trial’s original sample-size justification, so the illustration should not be read as a reconstruction of that design decision.

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, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.889; treatment proportion p₁ = 0.883; average p̄ = 0.886.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.4492 = 0.8803.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.4491 = 0.3780.
4. n = (0.8803 + 0.3780)² / (-0.0054)² = 53,697.1, rounded up to 53,698 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
p0 <- 0.888888888888889                          # control proportion
p1 <- 0.883458646616541                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^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 (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(2131233)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 53,698 (80% power), 71,885 (90% power)
 75% of observed effect: n per arm = 94,966 (80% power), 127,132 (90% power)
 50% of observed effect: n per arm = 212,556 (80% power), 284,551 (90% power)
power.prop.test: 53697.1 
Simulated power at n = 53,698 per arm: 0.798 (20000 replicates)

The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-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 analysis is reported as a non-inferiority or equivalence analysis, with an estimated difference of 0.510 and a 95% confidence interval from -4.204 to 5.223. The registry does not report a p-value for this analysis, its specific method, or the non-inferiority margin. Those omissions limit independent interpretation of whether the confidence interval met the trial’s planned criterion.

The recalculated comparison uses posted arm summary statistics to produce a simple, unadjusted risk-difference analysis. Its p-value is 0.819, and its interval spans zero. This calculation is not the sponsor’s model or formal non-inferiority procedure, and it should not be substituted for it. The reported sponsor estimate and the recalculated estimate are on differently presented scales in the record, so they should not be compared as though they were identical quantities.

The discrepancy indicator is false, so no discrepancy between the sponsor analysis and the recalculation is flagged in the record. Even so, they answer related but not necessarily identical statistical questions: the sponsor analysis is identified as non-inferiority or equivalence, while the recalculation is an unadjusted comparison of proportions. The sponsor analysis is the relevant posted analysis for the trial’s stated hypothesis; full assessment still depends on the unreported margin and analysis details.

15. Multiplicity, Missing Data and Analysis Populations

The primary endpoint is clearly identified as Week 48 HIV-1 RNA <40 copies/mL, and the record describes the primary hypothesis as non-inferiority. However, the registry record does not report a multiplicity strategy for the secondary outcomes, including whether outcomes were ordered in a testing hierarchy or whether statistical significance was adjusted for multiple comparisons. The secondary p-values that are posted are unadjusted.

General explanation: testing many outcomes can increase the chance of a nominally unusual result appearing by chance. Multiplicity procedures can control that risk, while a prespecified hierarchy can define which outcomes are confirmatory and how later tests depend on earlier ones. Without those details, secondary results are best understood as descriptive and should not be treated as if each were a separately confirmatory finding.

Missing-data handling is specified for the primary endpoint: the NC=F approach treated all missing data as failures regardless of reason. The number of missing Week 48 observations, the reasons for missingness, and sensitivity analyses are not reported in the registry record. The handling of missing values for the secondary endpoints is also not reported in the registry record.

The primary population is described as all randomized participants who received at least one dose of study treatment. The registry record does not report detailed counts for other analysis populations, exclusions, protocol deviations, or adherence-based analyses. It also does not report a separate per-protocol analysis. These details are relevant to interpreting a non-inferiority study because the definition of the analyzed population and the treatment of missing outcomes can influence the estimated difference.

The record identifies the sponsor analysis as non-inferiority or equivalence but does not report its method or margin. The original sample-size justification, interim analyses, and detailed statistical analysis plan are not reported in the registry record. Without those elements, the displayed analysis can be described, but its full prespecified decision framework cannot be reconstructed.

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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: depression (0.8%), gastritis (0.8%), appendicitis (0.8%), proctitis (0.4%), mental status changes (0.4%).

The registry records serious adverse events for 51 of 531 participants in the reformulated raltegravir group and 42 of 266 participants in the raltegravir group. These are counts with the listed numbers at risk, not adjusted comparisons. A serious adverse event is not necessarily caused by study treatment; the posted counts alone do not establish causation.

The record lists depression, gastritis, and appendicitis at 0.8% each among the top serious-event terms, and proctitis, mental status changes, and vomiting at 0.4% each. The timeframe associated with the serious-event summary is not reported in the registry record. Death counts are not reported in the record.

These figures should be read as a safety description rather than as a definitive comparison of risk. General explanation: differences in event counts can reflect the number of participants observed, follow-up duration, event definitions, and chance variation. The registry does not provide a formal comparative analysis for the serious adverse event counts in the information. The separate secondary outcomes include adverse-event measures at Week 48 and after 96 weeks, but their definitions and analyses should not be conflated with the serious-event summary.

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

The posted primary result shows similar observed Week 48 response percentages in the two treatment groups: 88.9% with reformulated raltegravir and 88.3% with raltegravir. The arm-specific confidence intervals indicate uncertainty around those estimates, and the unadjusted recalculated comparison does not isolate a difference from no difference. These findings describe the trial’s measured endpoint under its stated analysis rule.

They do not, on their own, prove that the regimens are equivalent, nor do they independently establish non-inferiority. A failure to find a conventional difference is not the same as showing that any difference is smaller than an acceptable margin. The registry describes a non-inferiority hypothesis and posts a sponsor confidence interval, but the non-inferiority margin is not reported in the registry record. Without it, the margin-based conclusion cannot be independently assessed.

The result also does not describe every dimension of treatment response. The endpoint is a binary threshold at Week 48, based on HIV-1 RNA below 40 copies/mL. It does not reveal the distribution of RNA measurements or the size of changes among participants. The missing-data rule counts missing primary observations as failures, so the response estimate includes that analysis choice.

The Week 96 response and safety outcomes add context, but they are secondary findings and the record does not report a multiplicity plan. Serious adverse event counts do not establish whether events were caused by treatment. These results should be understood as registry-record evidence from the stated randomized comparison, not as medical advice or as a substitute for a complete assessment of the trial protocol and analysis plan.

18. Why This Trial Matters Statistically

This trial illustrates why a non-inferiority question cannot be answered by looking only at whether two observed percentages are close or whether a conventional p-value is large. The primary response estimates are similar, but a non-inferiority conclusion depends on a prespecified margin and on the confidence interval’s relation to that margin. The margin is not reported in the registry record, making this an important limitation of the available statistical account.

It also illustrates the distinction between the sponsor’s formal analysis and an unadjusted recalculation from arm summaries. The sponsor analysis is identified as non-inferiority or equivalence, whereas the recalculation is a simple risk-difference comparison. The recalculation is useful for describing the posted proportions and their uncertainty, but it cannot reproduce an unreported model or decision rule.

The endpoint highlights how analytical definitions affect interpretation. HIV-1 RNA <40 copies/mL at a specific visit is a clear threshold outcome, and the NC=F approach assigns missing primary outcomes as failures. That choice should be considered alongside the observed percentages, because missing-data assumptions form part of the estimand being described.

Finally, the record provides secondary response and safety information but does not report a multiplicity strategy or full details for all analyses. Together, these features make the study a useful example of reading effect estimates, confidence intervals, endpoint rules, and registry reporting gaps as parts of one statistical interpretation rather than treating a single p-value as the whole result.

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.
• Participant counts were reconstructed from posted percentages and arm sizes, so small rounding differences are possible.

The registry record does not report the non-inferiority margin, even though the primary hypothesis is described as non-inferiority. The sponsor’s reported estimated difference and confidence interval therefore cannot be compared with the planned boundary using the information available in the record. The sponsor method is also not reported.

The record does not report the original sample-size justification, detailed statistical analysis plan, interim analyses, or a multiplicity strategy. It does not give the number or reasons for missing primary observations, or sensitivity analyses for the NC=F rule. Handling of missing data for secondary outcomes is not reported in the registry record.

The Week 96 arm estimates are accompanied by confidence limits that repeat the Week 48 limits. Those limits should not be interpreted as Week 96-specific precision estimates. The time period for the serious adverse event summary is not reported, and death counts are not reported. The record also does not provide a formal comparative analysis for those serious-event counts.

The primary arm populations are reported as 531 and 266, while overall enrollment is 802. Detailed accounting of the analysis populations and participant disposition is not reported in the registry record. The registry identifies the primary population as randomized participants who received at least one dose, but does not report further population-specific analyses or the impact of protocol deviations.

Finally, the recalculated comparison is unadjusted and based on posted summary statistics. It cannot substitute for the sponsor’s formal non-inferiority analysis or recover unreported design and analysis choices.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Evaluation of the Safety and Efficacy of Reformulated Raltegravir (MK-0518) 1200 mg Once Daily in Combination With TRUVADA™ in Human Immunodeficiency Virus (HIV)-1 Infected, Treatment-Naive Participants (MK-0518-292) — NCT02131233.
• Registry record last updated 2019-01-30; status last verified 2019-01.
• Results first posted 2016-10-31.
• 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

NCT02131233 is a completed Phase III randomized, triple-masked, parallel-group, active-comparator trial sponsored by Merck Sharp & Dohme LLC. It enrolled 802 treatment-naive participants with HIV-1 infection.

The trial compared reformulated raltegravir 1200 mg once daily with raltegravir 400 mg twice daily, each combined with TRUVADA™ once daily. The primary endpoint was the percentage with HIV-1 RNA <40 copies/mL at Week 48, analyzed using an NC=F snapshot approach in which missing data were treated as failures.

Week 48 response estimates were 88.9% and 88.3%, respectively. The registry also posts a sponsor non-inferiority or equivalence estimate and confidence interval, but the margin needed to interpret that analysis is not reported in the registry record.