Efficacy and Safety of Methylphenidate HCl ER Capsules in Children and Adolescents With ADHD: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Efficacy and Safety of Methylphenidate HCl ER Capsules in Children and Adolescents With ADHD (NCT01239030), a randomized phase 3 study. The primary outcome is Change in ADHD-RS-IV Total Score From Baseline (Visit 2) to the End of the Double-Blind Phase (Visit 3).

2. Clinical Question

The study was designed to assess efficacy and safety in pediatric patients with ADHD. The registry identifies a primary outcome measure but does not report secondary outcomes. Its description characterizes the study as multicenter, randomized, parallel, and double-blind; the recorded masking classification is quadruple. Specific details about which participants or study personnel were masked are not reported in the registry record.

The central statistical comparison is not simply whether scores changed within each group. The relevant contrast is whether the average change in each methylphenidate group differed from the average change in the placebo group. The registry reports an overall ANCOVA result involving all five double-blind groups, while the posted arm summaries also support separate unadjusted dose-versus-placebo comparisons. Those are different forms of evidence and should not be treated as interchangeable.

3. Trial Design

This completed Phase 3 study was randomized and used a parallel-group design. The record lists enrollment as 230 and describes a multicenter study of fixed doses of extended-release methylphenidate compared with placebo. The double-blind phase included four dose groups—10 mg, 15 mg, 20 mg, and 40 mg—and a placebo group. The listed efficacy population for the primary outcome was N = 221.

The registry lists the study as quadruple-masked and describes the efficacy and safety study as double-blind. The exact identities of the masked parties and procedures for maintaining masking are not reported in the registry record. The arm descriptions also include an open-label phase with methylphenidate doses from 10 mg through 60 mg; the record does not describe the transition rules or the role of that phase in the primary efficacy analysis.

The registry lists the study start as 2010-11 and primary completion as 2012-02. Its status is completed. The original protocol, full schedule of assessments, randomization details, allocation concealment procedures, and the study’s own sample-size justification are not reported in the registry record.

The primary endpoint compares baseline ADHD-RS-IV total score with the score at the end of the double-blind phase. The registry description refers to Visit 2 and Visit 3, while the efficacy-population description refers to Day 0 and Day 7. The record does not explain the relationship between those labels. It lists one primary outcome measure and one posted analysis record; no secondary outcomes are posted.

In addition to the sponsor’s reported ANCOVA, the posted arm-level means and standard deviations permit simple unadjusted comparisons of each dose with placebo. These recalculations do not reproduce an adjusted model or account for design details that are not reported. Because the record flags a discrepancy between the posted results and these recalculations, the sponsor’s own analysis takes precedence when describing the sponsor-reported statistical result.

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: This study planned to randomize approximately 225 subjects to the Double-Blind phase of the study with the goal of approximately 200 subjects completing the double-blind parallel treatment

Double Blind

Reasons for not completing this period:

Dose Optimization (Open Label)

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Efficacy Population (N = 221) comprises subjects who completed ADHD-RS-IV assessments on Day 0 and Day 7.

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 in ADHD-RS-IV Total Score From Baseline (Visit 2) to the End of the Double-Blind Phase (Visit 3), measured over From baseline (visit 2) to end of of Double-Blind phase (visit 3).

The primary endpoint is change in ADHD-RS-IV total score from baseline to the end of the double-blind phase. The ADHD-RS-IV home version is an 18-item measure of ADHD symptoms. Trained clinicians administered the questionnaire to parents, who rated symptom severity for each item on a four-point scale, from 0 for never or rarely to 3 for very often. The total is the sum across the 18 items and can range from 0, indicating no impairment, to 54, indicating maximal impairment.

The registry defines the change calculation as baseline score minus end-of-phase score. Under that direction, a positive change means the score at the end was lower than at baseline, and a larger positive value represents a greater reduction in the measured symptom score. This endpoint is used to quantify change over the double-blind treatment period and to compare the average change across randomized groups.

The measure is a continuous score, so the posted arm results are expressed as means with standard deviations. A group mean describes the average change, while the standard deviation describes how much individual changes varied around that average. Neither summary alone describes every participant’s experience. The registry does not report a threshold for interpreting whether a particular amount of change is clinically important, nor does it describe a responder definition.

The endpoint description identifies Visit 2 as baseline and Visit 3 as the end of the double-blind phase. The population description instead refers to completed assessments on Day 0 and Day 7; how these labels correspond is not reported in the registry record.

7. Results Posted in the Registry

• 10 mg: mean 9.30 versus 5.10 on control; difference 4.20 (95% CI 0.31 to 8.09), standardized effect d = 0.44; z-test p = 0.034.
• 15 mg: mean 11.20 versus 5.10 on control; difference 6.10 (95% CI 1.32 to 10.88), standardized effect d = 0.55; z-test p = 0.012.
• 20 mg: mean 12.30 versus 5.10 on control; difference 7.20 (95% CI 3.04 to 11.36), standardized effect d = 0.71; z-test p = <0.001.
• 40 mg: mean 13.20 versus 5.10 on control; difference 8.10 (95% CI 3.82 to 12.38), standardized effect d = 0.79; z-test p = <0.001.

8. Statistical Interpretation

9. Statistical Methods Explained

What does the mean change represent?

The endpoint is continuous, so each arm is summarized by a mean change and standard deviation. The mean is the arithmetic average of participants’ baseline-minus-end score changes. Because the subtraction is baseline minus end, positive values indicate lower scores at the end of the phase. The standard deviation describes the spread of participant-level changes around the group mean; it is not the uncertainty in the mean itself.

For example, the posted mean change was 13.2 in the 40 mg arm and 5.1 in the placebo arm. The unadjusted mean difference is reported as 8.1. This contrast compares the group averages; it does not mean that every participant in the active-treatment group changed by that amount relative to a placebo participant. Individual changes can vary, as reflected in the arm standard deviations.

What does an unadjusted comparison do?

The recalculated comparisons use each arm’s posted mean, standard deviation, and sample size to estimate a difference in average change between one dose group and placebo. “Unadjusted” means that the calculation does not account for baseline score or other covariates in a regression model. The calculations are simple comparisons of the posted summaries, not a recreation of the sponsor’s analysis. They also do not use participant-level data, which are not reported in the registry record.

A confidence interval around a mean difference represents a range of values compatible with the estimate under the calculation’s assumptions. If an interval excludes zero, that is evidence against no difference for that particular unadjusted contrast at the interval’s confidence level. It does not account for the fact that several dose groups are being compared with placebo unless an appropriate multiplicity procedure is used. Such a procedure is not reported for these recalculations.

What is ANCOVA doing?

ANCOVA, or analysis of covariance, compares groups while adjusting for one or more covariates. In a baseline-to-endpoint trial analysis, baseline outcome score is commonly a relevant covariate, but the exact covariates and model specification used in this trial are not reported in the registry record. Adjustment can improve precision when the covariates are related to the outcome and can address baseline differences under the model’s assumptions. The sponsor’s record lists an ANCOVA result with p = 0.005, but it does not post the adjusted group estimates, confidence intervals, model details, or the precise contrast tested.

The sponsor’s analysis includes all five double-blind groups according to the posted analysis record. A single overall analysis result is not the same thing as four separately reported adjusted comparisons against placebo. Without estimates and contrast details, the overall p-value cannot show the size or precision of each dose-specific adjusted difference. Because the registry flags a discrepancy with the recalculations, the sponsor’s own analysis takes precedence when describing the trial’s reported analysis.

Why do the p-values need context?

A p-value describes how incompatible the observed data are with a specified statistical null hypothesis, conditional on the model and assumptions. 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 recalculated p-values are unadjusted and pertain to individual comparisons; the sponsor’s p-value comes from ANCOVA and is reported separately. Their different methods and levels of detail mean they should not be treated as if they were estimates from one identical analysis.

When several doses are each compared with one control, the number of statistical opportunities to observe a small p-value increases. General statistical practice therefore considers whether the testing plan controls the chance of false-positive findings across comparisons. The registry does not report a multiplicity procedure or the planned hierarchy of comparisons, so the status of the separate comparisons within an overall testing strategy is unclear.

How should variation and sample size be understood?

The standard deviations differ across arms, indicating that the observed participant-level changes were not equally dispersed in every group. General statistical reasoning matters because a method that assumes a particular variance structure may perform differently when variability differs across groups. The recalculated comparisons use pooled standard deviations as part of the unadjusted calculation, while the sponsor analysis is identified as ANCOVA. The record does not report diagnostic checks or details that would allow assessment of model assumptions.

The sample-size illustrations are planning calculations based on observed effects and stated assumptions, not a report of the original design calculation. They indicate how many participants per arm would be needed under those assumptions to target a chosen power for an effect set as a stated fraction of the observed effect. Smaller target effects generally require more participants because they are harder to distinguish from random variation. These illustrations are not observed power.

Information about missing-data methods, analysis sets beyond the described efficacy population, and the original sample-size rationale is not reported in the registry record. The available summary therefore supports interpretation of the posted endpoint summaries and analyses, but not a full audit of the prespecified statistical plan or its implementation.

10. Confidence Intervals and Precision

The recalculated mean differences are estimates, and their confidence intervals convey uncertainty around those estimates. For 10 mg versus placebo, the mean difference was 4.2 with a 95% confidence interval from 0.311 to 8.089. For 15 mg, it was 6.1 with a 95% confidence interval from 1.324 to 10.88. For 20 mg, it was 7.2 with a 95% confidence interval from 3.041 to 11.36. For 40 mg, it was 8.1 with a 95% confidence interval from 3.822 to 12.38.

Each interval has a lower limit above zero, so these simple unadjusted estimates are compatible with positive average differences under the calculation used. The intervals also show that the precise size of each difference is uncertain: a range of values remains compatible with the posted summary statistics. The intervals for the dose comparisons overlap, so the numerical ordering of the point estimates should not be taken as evidence that one active dose differs from another. Direct active-dose comparisons and their uncertainty are not reported.

A confidence interval is not a guarantee that the true effect lies within its limits. In general, it reflects the uncertainty expected from repeated use of a specified method under its assumptions. These intervals are recalculated from posted summary statistics and are unadjusted; they are not the intervals from the sponsor’s ANCOVA. The sponsor-adjusted estimates and intervals are not reported in the registry record.

Precision is influenced by sample size and variability. The posted arm sizes range from 40 to 48 for the efficacy summaries, and the standard deviations indicate appreciable variation in change scores. The record does not provide a prespecified clinically important difference, so statistical precision cannot by itself determine whether a particular interval represents a clinically meaningful difference. Interpretation should also account for the discrepancy noted between the recalculations and sponsor analysis, and for the lack of reported multiplicity details.

11. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The planning figures are participants per arm for the continuous-outcome comparisons; they are not total event counts. They are illustrations based on the observed effect, rather than the trial’s original design calculation. The listed assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each scenario targets an effect set at 100%, 75%, or 50% of the observed effect.

The 80% power column gives the number of participants per arm that the planning calculation estimates would be needed to have an 80% chance of detecting the specified effect under the stated assumptions. The 90% power column gives the corresponding per-arm planning figure for a 90% chance. These are design targets: higher target power generally requires more participants when the other assumptions are held constant. The original sample-size justification for this trial is not reported in the registry record.

For each dose-versus-placebo illustration, the required per-arm figures increase as the assumed effect is reduced from the full observed effect to 75% or 50% of it. This follows a general statistical principle: smaller differences are harder to distinguish from random variation, so detecting them with the same target power generally requires more participants. The figures depend on the observed effects and assumptions used in the illustration, and should not be read as a recommendation or as a description of enrollment in the trial.

This is not observed power. The calculations do not state the probability that the completed trial succeeded, and they do not replace the observed estimates, confidence intervals, or sponsor analysis.

12. How the Sample Size Is Derived

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

Formula

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

Worked calculation for this trial

1. Observed difference Δ = 4.200; pooled standard deviation σ = 9.586.
2. n = 2 × (1.96 + 0.842)² × 9.586² / 4.200² = 81.8, rounded up to 82 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 <- 4.2                      # observed difference in means
sigma <- 9.5861458569805                     # 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(1239030)
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 = 82 (80% power), 110 (90% power)
 75% of observed effect: n per arm = 146 (80% power), 195 (90% power)
 50% of observed effect: n per arm = 328 (80% power), 438 (90% power)
power.t.test: 82.7 
Simulated power at n = 82 per arm: 0.797 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

13. Analyses Reported by the Sponsor

The sponsor’s posted result is an ANCOVA analysis across the five double-blind groups, with p = 0.005. The registry does not report an adjusted effect estimate, confidence interval, covariates, or the exact contrast represented by this p-value. It therefore supports reporting that the sponsor’s analysis found an overall statistical result, but not reconstructing dose-specific adjusted effects from the information posted.

The separate dose-versus-placebo estimates are simple unadjusted recalculations from arm-level means, standard deviations, and sample sizes. They are useful for describing the posted summaries, but they are not the sponsor’s model-based results. The registry flags a discrepancy between the sponsor analysis and these recalculations. Under that circumstance, the sponsor’s own analysis takes precedence when stating the trial’s reported inferential result.

The sponsor’s overall p-value should not be presented as a p-value for every dose comparison. Conversely, the unadjusted p-values should not be presented as the sponsor’s ANCOVA results. The record does not supply enough model detail to reconcile the difference, so the reason for it is not reported in the registry record.

14. Multiplicity, Missing Data and Analysis Populations

The registry posts one primary outcome measure and one analysis record. The reported ANCOVA is identified as including the five double-blind groups, but the record does not describe the planned testing hierarchy, whether the overall analysis was an omnibus test, or how any dose-specific contrasts were to be handled. It also does not report a multiplicity adjustment for the separate unadjusted dose-versus-placebo recalculations. When multiple comparisons are made, multiplicity procedures can help control the overall risk of false-positive conclusions; without the plan, the inferential status of the separate comparisons cannot be fully assessed.

The registry identifies an efficacy population of N = 221, comprising participants who completed ADHD-RS-IV assessments on Day 0 and Day 7. It does not report how many randomized participants were excluded from that population, how missing assessments were handled, or whether other analysis populations were used for the primary outcome. The arm-level efficacy sample sizes are posted, but the reasons for differences among those counts and the listed enrollment are not explained in the registry record.

Missing-data methods can affect estimates if outcome availability is related to treatment assignment or participant outcomes. General statistical practice considers the amount and pattern of missing data, the assumptions behind the method used, and sensitivity analyses. None of these details is reported for the primary endpoint. It is therefore not possible to determine from the registry record whether the primary analysis used imputation, a model-based approach, complete cases alone, or another method.

The record also does not report the original statistical analysis plan, any prespecified interim analyses, stopping rules, or the trial’s own sample-size justification. These omissions do not negate the posted results, but they limit assessment of whether the reported analyses follow a fully specified plan and how robust conclusions are to missingness or multiple testing.

15. Safety Results

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

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: adjustment disorder with mixed disturbance or emotion and conduct (2.3%), migraine (0.5%).

The registry lists serious adverse events and other adverse events separately for the double-blind groups and the open-label phase. In the double-blind phase, the serious adverse event counts were 0 among 49 at risk in the 10 mg group, 1 among 44 at risk in the 15 mg group, 0 among 45 at risk in the 20 mg group, 0 among 45 at risk in the 40 mg group, and 0 among 47 at risk in the placebo group. The record lists zero deaths in each of these groups.

These are counts of participants affected relative to the listed numbers at risk, not comparisons adjusted for exposure time or other factors. The record also lists serious-event terms with their percentages: Adjustment disorder with mixed disturbance or emotion and conduct at 2.3%, and Migraine at 0.5%. The registry does not provide further context about these terms in the posted summary.

The open-label phase is listed separately, with 1 serious adverse event among 221 at risk and 0 deaths. Its other adverse event count is also reported separately from the double-blind groups. Because the phases and denominators differ, these figures should not be combined into a single double-blind comparison. Adverse-event counts alone do not establish causation, and the registry summary does not provide enough detail to compare event timing, duration, or severity beyond the serious-event classification.

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

The posted results describe average change in ADHD-RS-IV total score during the double-blind phase. Under the registry’s baseline-minus-end definition, the average change was positive in all listed groups, including placebo. The unadjusted dose-versus-placebo estimates were positive, and their confidence intervals were above zero. The sponsor also reported an ANCOVA result with p = 0.005 across the five groups.

These findings describe group averages on a symptom-rating scale. They do not mean that every participant experienced the average change, and they do not establish how a particular participant would respond. The standard deviations show that individual changes varied. The record does not report a clinical-importance threshold or responder definition, so the statistical differences cannot be translated from this information alone into a claim about clinical importance.

The unadjusted calculations and sponsor-reported ANCOVA are not identical analyses. The registry flags a discrepancy, and the sponsor’s own analysis takes precedence as the trial’s reported analysis. Because adjusted estimates, confidence intervals, exact model details, and multiplicity procedures are not reported, the sponsor’s overall p-value cannot establish the size or precision of each dose-specific adjusted comparison.

The findings are limited to the recorded endpoint and study phase. They do not establish long-term outcomes, outcomes beyond the ADHD-RS-IV measure, or effects in populations not described by the trial. Secondary outcomes are not posted. Safety information is also limited to the listed event counts and does not by itself determine whether an event was caused by an intervention.

Accordingly, the results should be read as evidence about the posted group-level score changes and the analyses recorded for this trial, with uncertainty about adjusted dose-specific effects and analysis details. They do not warrant medical advice or a conclusion about what treatment is appropriate for an individual.

17. Why This Trial Matters Statistically

This trial illustrates why a registry’s arm summaries and its sponsor-reported analysis answer related but distinct statistical questions. Means and standard deviations show the observed distribution of change within each group. Simple unadjusted differences compare those averages, while ANCOVA may account for covariates and can yield different estimates or uncertainty. Here, the registry posts the ANCOVA p-value but not its adjusted estimates or model specification, alongside summaries from which unadjusted comparisons can be recalculated.

The discrepancy flag makes that distinction particularly important. The unadjusted comparisons can help readers understand the direction and approximate scale of the posted summary differences, but they cannot replace the sponsor’s analysis. At the same time, the reported overall p-value does not supply the dose-specific adjusted effects needed to assess their size and precision. Clear reporting of estimates, intervals, model details, and planned contrasts would make these results easier to interpret.

The study also raises standard questions about multiple comparisons, missing data, and analysis populations. Four dose-versus-placebo contrasts are available as simple recalculations, yet the registry does not state a multiplicity strategy. The efficacy population is defined by completed assessments, but missing-data handling and the relationship between that population and all randomized participants are not explained. These details matter because they affect how confidently an analysis can be interpreted as addressing the trial’s intended question.

Finally, the endpoint is a continuous rating-scale change, and the registry does not post a clinically important threshold. Statistical evidence and clinical interpretation are related but not interchangeable. Readers need both a clear effect estimate with uncertainty and context for what size of score change matters. The posted information is useful for examining the trial’s statistical results, while these reporting gaps limit a complete appraisal.

18. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

Several trial-specific details needed to fully interpret the results are not reported in the registry record. The sponsor’s ANCOVA is named, but its covariates, model form, adjusted estimates, confidence intervals, and precise tested contrast are absent. That prevents a direct comparison between the adjusted sponsor result and the unadjusted recalculations beyond noting the reported discrepancy.

The record does not provide the original statistical analysis plan, sample-size justification, or a multiplicity strategy for dose comparisons. It also does not report how missing primary-outcome assessments were handled, whether sensitivity analyses were performed, or how participants outside the stated efficacy population were treated. The efficacy population is defined as participants with Day 0 and Day 7 assessments, while the endpoint description uses Visit 2 and Visit 3; their correspondence is not explained.

The registry posts no secondary outcomes. It does not report a threshold for clinically important ADHD-RS-IV change, a responder definition, or follow-up results beyond the double-blind endpoint. Therefore, the posted mean changes cannot establish the clinical importance or durability of the observed differences.

The study includes an open-label phase, but the registry summary does not describe its role in the primary efficacy analysis or how participants entered it. Safety counts are listed by phase and group, but further details such as event timing and duration are not present in the posted summary. The record’s masking classification is quadruple and the study description says double-blind, but the identities of masked parties and the procedures are not reported. These limitations constrain assessment of the analysis and design without changing the values reported for the posted results.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Efficacy and Safety of Methylphenidate HCl ER Capsules in Children and Adolescents With ADHD — NCT01239030.
• Registry record last updated 2023-02-22; status last verified 2023-01.
• Results first posted 2023-02-22.
• 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.

22. Record Summary

NCT01239030 is a completed Phase 3 randomized, parallel study of extended-release methylphenidate in children and adolescents aged 6 to 18 years with ADHD. The double-blind groups received 10 mg, 15 mg, 20 mg, or 40 mg, or placebo. The primary outcome was change in ADHD-RS-IV total score from baseline to the end of the double-blind phase, with positive changes defined as better outcomes in the registry description.

The sponsor reported an ANCOVA result of p = 0.005 across the five groups. Separate recalculated unadjusted dose-versus-placebo mean differences were positive, with confidence intervals above zero; the record flags a discrepancy, so the sponsor’s analysis takes precedence. Adjusted dose-specific estimates, multiplicity details, and missing-data methods are not reported in the registry record.