Fixed-dose Safety and Efficacy Study of Asenapine for the Treatment of Acute Manic or Mixed Episode in Bipolar 1 Disorder (P05691): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Fixed-dose Safety and Efficacy Study of Asenapine for the Treatment of Acute Manic or Mixed Episode in Bipolar 1 Disorder (P05691) (NCT00764478), a randomized phase 3 study. The primary outcome is Change From Baseline in Young Mania Rating Scale (Y-MRS) Total Score at Day 21.

2. Clinical Question

3. Trial Design

This was a Phase 3, randomized, quadruple-masked, parallel-group trial with a placebo control. The registry describes a fixed-dose, three-week study of asenapine in participants with bipolar 1 disorder experiencing an acute manic or mixed episode. The trial enrolled 367 participants and is listed as completed. The recorded start date is 2012-04-06, and the primary completion date is 2014-04-30.

There were three treatment groups: asenapine 5 mg twice daily, asenapine 10 mg twice daily, and placebo twice daily. Each treatment was administered sublingually for 21 days. Random assignment and masking are recorded, but the registry record does not report the details of the randomization procedure or identify which people were masked under the quadruple-masking designation.

The primary outcome was change from baseline in Young Mania Rating Scale total score at Day 21. The recorded primary analysis population required randomization, at least one dose of trial medication, and baseline and post-baseline measurements. The registry’s arm-level primary outcome summaries list 120 participants for the 5 mg group, 113 for the 10 mg group, and 126 for placebo. The reasons these outcome counts differ from total enrollment are not reported in the registry record.

The trial also specified outcomes involving clinical global severity, response and remission, earlier symptom measurements, and depressive symptoms. The original sample-size rationale, planned interim analyses, and additional protocol details 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.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Randomized participants who received at least one dose of trial medication and had at least one baseline and post-baseline measurement.

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: Randomized participants who received at least one dose of trial medication

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline in Young Mania Rating Scale (Y-MRS) Total Score at Day 21, measured over Baseline and Day 21.

The primary endpoint is change from baseline in total score on the Young Mania Rating Scale (Y-MRS) at Day 21. The scale contains 11 items covering features such as mood, energy, sleep, speech, thought disorder, irritability, insight, and disruptive or aggressive behavior. Item scores are summed to a total from 0 to 60; higher scores indicate greater symptom severity.

The outcome is reported as a least-squares mean change, with a standard error. Negative change indicates that the score fell from baseline, which the registry defines as improvement in symptoms. The primary comparison asks whether the average modeled change in either asenapine group differed from the change in the placebo group.

General: a continuous symptom score retains information about the size of change across the scale, rather than reducing each participant’s outcome to a category such as responder or non-responder. A prespecified follow-up point also gives the comparison a common time reference. The Day 21 score is therefore the central measure for the trial’s stated primary question, while the other outcomes provide additional perspectives on symptoms and clinical ratings.

The registry identifies a mixed model repeated measures (MMRM) analysis for the primary endpoint. It does not report the model’s detailed specification, such as the covariates or covariance structure. Those details are not reported in the registry record.

7. Results Posted in the Registry

• Asenapine 5 mg BID: mean -14.40 versus -10.90 on control; difference -3.50 (95% CI -6.29 to -0.71), standardized effect d = -0.31; z-test p = 0.014.
• Asenapine 10 mg BID: mean -14.90 versus -10.90 on control; difference -4.00 (95% CI -6.81 to -1.19), standardized effect d = -0.36; z-test p = 0.005.

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 Clinical Global Impression - Bipolar Mania - Severity of Illness (CGI-BP-S) Overall Score at Day 21

• 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 errors.
• Result:
  • Asenapine 5 mg BID: mean -1.60 versus -1.10 on control; difference -0.50 (95% CI -0.82 to -0.18), standardized effect d = -0.39; z-test p = 0.002.
  • Asenapine 10 mg BID: mean -1.70 versus -1.10 on control; difference -0.60 (95% CI -0.92 to -0.28), standardized effect d = -0.48; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Asenapine 5 mg BID 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 lower for Asenapine 10 mg BID than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percentage of Participants Who Are Y-MRS Responders at Day 21

• 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:
  • Asenapine 5 mg BID: 45.0% (54/120) versus 39.7% (50/126) on control; risk difference 5.3 percentage points (95% CI -7.0 to 17.7), risk ratio 1.13 (0.85–1.52); unadjusted two-proportion z-test p = 0.399.
  • Asenapine 10 mg BID: 46.9% (53/113) versus 39.7% (50/126) on control; risk difference 7.2 percentage points (95% CI -5.3 to 19.8), risk ratio 1.18 (0.88–1.58); unadjusted two-proportion z-test p = 0.260.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Asenapine 5 mg BID and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Asenapine 10 mg BID and the control. The interval gives the range of effects that remain compatible with the data.

Percentage of Participants Who Are Y-MRS Remitters at Day 21

• 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:
  • Asenapine 5 mg BID: 34.2% (41/120) versus 30.2% (38/126) on control; risk difference 4.0 percentage points (95% CI -7.7 to 15.7), risk ratio 1.13 (0.79–1.63); unadjusted two-proportion z-test p = 0.501.
  • Asenapine 10 mg BID: 38.1% (43/113) versus 30.2% (38/126) on control; risk difference 7.9 percentage points (95% CI -4.1 to 19.9), risk ratio 1.26 (0.88–1.80); unadjusted two-proportion z-test p = 0.198.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Asenapine 5 mg BID and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Asenapine 10 mg BID and the control. The interval gives the range of effects that remain compatible with the data.

The registry lists a range of secondary outcomes covering clinical global severity, responder and remitter classifications, earlier Y-MRS measurements, and depressive symptoms. Taken together, the posted Day 21 summaries tend to have score changes or percentages in a direction more favorable to the asenapine groups than to placebo. The pattern is not uniformly precise across outcome types: recalculated intervals for the binary responder and remitter comparisons include no difference.

These outcomes complement the primary Y-MRS comparison but do not replace it. A clinical global severity rating offers another measure of illness severity, while responder and remitter categories summarize whether participants meet outcome definitions. Earlier measurements provide information at other points during the three-week treatment period, and the depressive-symptom measure addresses a different symptom domain. The registry record does not include all analysis details or operational definitions needed to evaluate every secondary endpoint fully.

General: secondary endpoints can help describe whether findings are consistent across measures, but each additional comparison creates another opportunity for a result to appear notable by chance. The registry does not report a multiplicity adjustment or a complete testing hierarchy. Consequently, unadjusted secondary results carry less weight than the prespecified primary comparison and should be considered supportive or exploratory rather than independent confirmation.

The secondary summaries should be interpreted in light of the primary analysis population and the short follow-up. Counts and percentages can vary by endpoint, and the registry does not report a common analysis population for every secondary measure in the record. The overall direction is informative, but it is not a substitute for uncertainty estimates, definitions, and multiplicity procedures that are not reported.

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

• Change From Baseline in Clinical Global Impression - Bipolar Mania - Severity of Illness (CGI-BP-S) Overall Score at Day 21
• Percentage of Participants Who Are Y-MRS Responders at Day 21
• Change From Baseline in Y-MRS Total Score at Day 2, Day 4, Day 7 and Day 14
• Percentage of Participants Who Are Y-MRS Responders at Day 2, Day 4, Day 7, Day 14
• Percentage of Participants Who Are Y-MRS Remitters at Day 21
• Percentage of Participants Who Are Y-MRS Remitters at Day 2, Day 4, Day 7, Day 14, Day 21
• Change From Baseline in Montgomery Asberg Depression Rating Scale (MADRS) Total Score
• Change From Baseline in CGI-BP-S Overall Score at Day 2, Day 4, Day 7, Day 14

9. Statistical Interpretation

10. Statistical Methods Explained

The registry identifies the primary analysis as a mixed model repeated measures analysis, or MMRM, and reports least-squares means and their standard errors. It also posts sponsor-reported MMRM comparisons and simple recalculations based on the arm-level summary statistics. These are related analyses, but they are not identical calculations.

What a least-squares mean represents

General: a least-squares mean is a model-based estimate of an arm’s mean outcome. Unlike a raw arithmetic average, it can reflect the structure and terms of the statistical model. The registry does not give enough detail to describe which adjustments were included in this MMRM, so the reported estimates should be interpreted as model-based means without assuming specific covariates or other design features.

The primary endpoint is measured repeatedly, and the registry states that the analysis used MMRM. General: repeated-measures models are designed to analyze measurements taken at multiple times while accounting for their relationship within a participant. That broad description does not establish which time points or model terms were included in this trial’s particular analysis. Those specifications are not reported in the registry record.

Standard errors and confidence intervals

The standard error describes uncertainty in an estimated mean. General: it reflects how precisely an estimate is determined, rather than the spread of individual participants’ measurements. A confidence interval combines the estimate with its uncertainty to express a range of values compatible with the data under the model assumptions. A narrower interval indicates more precision; a wider interval indicates less.

The registry reports 95% confidence intervals for the sponsor’s primary MMRM comparisons. The recalculated intervals are unadjusted intervals for simple mean differences. The two sets of intervals have similar directions and broadly similar ranges, but they arise from different analytical procedures and should not be treated as duplicate model outputs.

What the recalculated comparison uses

The recalculated primary comparisons subtract the posted placebo change from the posted change for each asenapine dose. The calculations use pooled standard deviations estimated approximately from the posted standard errors and sample sizes. Because the standard deviations are approximations and the calculations are unadjusted, these estimates do not reproduce all features of the trial’s MMRM analysis. The recalculated p-values are therefore best read as a supplementary check based on the summaries, not as replacements for the sponsor’s model-based results.

General: a p-value describes how incompatible the observed data are with a specified null model, under the assumptions of the analysis. It is not the probability that the null hypothesis is true, and it does not measure clinical importance. A smaller p-value does not, on its own, tell how large or meaningful an effect is; the estimated difference and its uncertainty are also relevant.

Continuous and binary outcomes

The primary outcome and the clinical global severity outcome are continuous measures, reported as changes in scores. By contrast, responder and remitter outcomes classify participants into categories and are reported as percentages. The recalculated comparisons for those binary outcomes are risk differences: the estimated percentage-point difference between an asenapine group and placebo, expressed on the proportion scale in the calculation. Their confidence intervals describe uncertainty around that difference.

General: continuous and binary analyses answer related but distinct questions. A mean change compares average score changes, whereas a responder analysis compares the frequency of meeting a response definition. Categorization can be useful for interpretation, but it discards information about differences among participants within each category. The registry lists the response outcomes but does not provide their operational definitions in the record summarized for these results.

Unadjusted comparisons and multiple outcomes

The recalculated p-values are explicitly unadjusted. The trial record includes multiple outcomes and more than one treatment-versus-placebo comparison. General: when many hypotheses are assessed, the chance of at least one apparently notable result can increase if no adjustment or hierarchy is used. An adjustment can address this issue, but it may also change how evidence is evaluated. Whether the trial used a multiplicity procedure for its outcome family is not reported in the registry record, so the secondary findings should be treated as less conclusive than a single prespecified primary result.

The registry reports the sponsor’s MMRM results for the primary endpoint and several secondary outcomes. It does not report detailed model assumptions, diagnostic checks, missing-data procedures, or sensitivity analyses for the primary model. Those omissions limit the degree to which an outside reader can independently evaluate the model’s implementation or robustness.

11. Confidence Intervals and Precision

The primary recalculated mean difference for asenapine 5 mg versus placebo was -3.5 Y-MRS points, with a 95% confidence interval from -6.286 to -0.714. For asenapine 10 mg versus placebo, the difference was -4.0 points, with a 95% confidence interval from -6.814 to -1.186. Both ranges are entirely on the negative side, consistent with a greater mean decrease in the asenapine group than in placebo under these unadjusted calculations.

The registry’s MMRM estimates have the same direction. For the 5 mg comparison, the sponsor-reported difference was -3.5, with a 95% confidence interval from -6.3 to -0.7. For 10 mg, it was -4.0, with a 95% confidence interval from -6.9 to -1.2. These are model-based results, whereas the recalculated intervals rely on approximate standard deviations reconstructed from summary standard errors and sample sizes.

General: a confidence interval is not a guarantee that the true effect lies within the interval, nor does it show the range of individual participant outcomes. It conveys uncertainty about an estimated group-level effect under the chosen method and its assumptions. The intervals do not include zero, but they still span a range of possible differences. Precision should therefore be considered alongside the point estimates and the model that produced them.

The registry does not report an established threshold for a clinically important difference on this endpoint. The statistical intervals alone cannot determine whether the size of a difference is important to participants. The short follow-up and the unreported details of model specification and missing-data handling also limit interpretation of precision beyond the recorded analysis.

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 a description of the trial’s original design calculation. For these continuous-outcome comparisons, the listed figures are participants per arm, not totals across both arms. The planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set at 100%, 75%, or 50% of the observed effect.

The 80% power column gives the illustrative number of participants per arm associated with an 80% chance of detecting the assumed effect under those planning assumptions, if the assumptions hold. The 90% power column gives the corresponding planning number for a 90% chance. Greater target power generally requires a larger planned sample, all else held constant. Planning for a smaller effect also requires more participants, because a smaller difference is harder to distinguish from random variation.

These figures are not observed power. They do not describe the probability that the completed trial detected its effect, and they should not be read as a retrospective test of whether the trial was adequately designed. The original sample-size assumptions and justification are not reported in the registry record. The planning numbers are hypothetical illustrations based on the observed estimates, which themselves are uncertain and may not match the effect expected when a future study is designed.

For binary outcomes, the corresponding planning figures also refer to participants per arm. The underlying outcome and effect assumptions differ from those for a continuous score, so figures for distinct endpoints should not be compared without considering what each endpoint measures and how its observed effect was estimated.

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 = -3.500; pooled standard deviation σ = 11.142.
2. n = 2 × (1.96 + 0.842)² × 11.142² / -3.500² = 159.1, rounded up to 160 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 <- -3.5                      # observed difference in means
sigma <- 11.1424250163913                     # 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(764478)
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 = 160 (80% power), 213 (90% power)
 75% of observed effect: n per arm = 283 (80% power), 379 (90% power)
 50% of observed effect: n per arm = 637 (80% power), 852 (90% power)
power.t.test: 160.1 
Simulated power at n = 160 per arm: 0.798 (20000 replicates)

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

14. Analyses Reported by the Sponsor

The sponsor’s reported primary analyses use MMRM and compare least-squares mean changes. For asenapine 5 mg versus placebo, the registry reports an estimated difference of -3.5, with a 95% confidence interval from -6.3 to -0.7. For asenapine 10 mg versus placebo, it reports -4.0, with a 95% confidence interval from -6.9 to -1.2. Both sponsor-reported comparisons are in the same direction as the recalculated comparisons.

The simple recalculations are derived from posted arm-level summaries and approximate standard deviations estimated from the standard errors. They do not recreate the sponsor’s repeated-measures model. Their estimates and uncertainty intervals are close in direction and scale to the sponsor’s reported results, while the p-values are not identical. Differences between the calculations are expected because the methods and inputs differ; the recalculated analysis is unadjusted and approximate.

The sponsor’s analysis is the trial’s reported model-based analysis. The recalculation is a supplementary way to check the broad direction and scale using the arm summaries. Neither should be interpreted as proving a clinical effect or as resolving questions that depend on unreported model specifications, missing-data handling, or outcome multiplicity.

15. Multiplicity, Missing Data and Analysis Populations

The registry identifies one primary outcome, change from baseline in Y-MRS total score at Day 21, and lists numerous secondary outcomes. It also includes comparisons of two asenapine doses against placebo. Testing multiple outcomes and comparisons raises a multiplicity question: without an adjustment or prespecified testing sequence, the chance of at least one apparently favorable result can be higher than for a single isolated test. Whether the sponsor controlled the overall type I error rate across the primary and secondary analyses is not reported in the registry record.

The registry identifies MMRM as the primary analysis method, but it does not report the detailed model specification, including all model terms and covariance assumptions. It also does not describe the approach to missing outcome measurements, the use of imputation, or sensitivity analyses. General: methods for incomplete repeated measurements can rely on assumptions about why measurements are missing and how the observed information relates to unobserved outcomes. Without the actual procedure and assumptions, robustness to missing data cannot be assessed from the registry record alone.

The primary analysis population is described as randomized participants who received at least one dose and had at least one baseline and post-baseline measurement. This definition excludes randomized participants who did not meet those criteria for the primary analysis, but the record does not report the number excluded or the reasons. It also does not explain whether additional analysis populations were used for secondary outcomes or safety results.

These reporting gaps do not establish that a procedure was absent from the trial protocol; they mean that the procedure is not reported in the registry record. They limit independent assessment of the primary model, the influence of missing data, and the strength of claims drawn from multiple endpoints. The sponsor’s reported primary comparison remains the registry’s model-based result, while interpretation of the secondary findings should account for the unreported multiplicity strategy.

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: bipolar i disorder (1.6%), suicidal ideation (0.8%), suicide attempt (0.8%), pneumonia (0.8%), mania (0.8%).

The registry reports serious adverse events among 3 of 122 participants at risk in the asenapine 5 mg group, 1 of 119 in the asenapine 10 mg group, and 2 of 126 in the placebo group. The listed top serious-event terms include bipolar I disorder, suicidal ideation, suicide attempt, pneumonia, mania, and facial bones fracture, each with a percentage reported in the safety record. These event terms are descriptions of reported events, not evidence that the trial established a cause.

The registry also records other adverse events affecting 43 of 122 participants in the 5 mg group, 67 of 119 in the 10 mg group, and 24 of 126 in the placebo group. These counts are distinct from the serious adverse event counts and should not be conflated. The record does not report deaths in the data summarized.

General: adverse event counts describe what was recorded during the study, while comparisons between groups require attention to follow-up, participant counts, event definitions, and the possibility of chance variation. A short trial can describe events observed during its period but cannot characterize longer-term safety. The registry figures alone do not establish causation or provide a complete clinical assessment.

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

The primary endpoint results show that the mean Y-MRS score decreased from baseline in each treatment group, and that the posted model-based and recalculated comparisons estimate a greater average decrease for both asenapine doses than for placebo at Day 21. The recalculated confidence intervals exclude zero, and the sponsor’s reported MMRM confidence intervals are also entirely negative. These findings describe the recorded group-level symptom scores and their statistical uncertainty.

They do not show that every participant improved, nor do they predict an individual participant’s outcome. Group means can conceal substantial variation among participants. The results also do not establish how participants would fare after the three-week treatment period, because longer follow-up is not part of the primary timeframe.

General: statistical evidence and clinical importance are related but distinct. The registry does not report a threshold for a clinically important change on the Y-MRS, so the numerical difference cannot be classified as clinically important from these results alone. A confidence interval describes uncertainty around an estimated group difference under a method’s assumptions; it does not establish causation by itself or remove uncertainty about model specification and missing observations.

The secondary findings provide additional measures, but the registry does not report whether multiplicity was controlled. Their direction can inform the overall pattern, but unadjusted comparisons should not be treated as separate proof. The safety counts likewise describe events recorded during the study and do not by themselves establish that a treatment caused an event.

The results should be understood within this trial’s population, treatment schedule, and follow-up. The registry record does not provide the details needed to assess every aspect of the analysis plan, nor does it establish conclusions beyond the outcomes and time period recorded.

18. Why This Trial Matters Statistically

This trial illustrates why interpretation of a clinical result depends on more than a single p-value. The primary endpoint is a continuous symptom score, analyzed with a repeated-measures model and reported as least-squares mean change. The registry also makes it possible to compare that model-based result with an unadjusted recalculation from arm-level summaries. The close directional agreement is informative, while the methodological differences explain why the numbers should not be treated as interchangeable.

The example also highlights the value of reporting uncertainty. The primary comparisons include estimated differences and confidence intervals, allowing readers to assess both the direction and range of plausible group differences under the analyses. Secondary outcomes show how a broadly similar pattern can coexist with less precise binary comparisons whose recalculated intervals include no difference.

Many outcomes and treatment comparisons create a multiplicity challenge. Without a reported adjustment or testing hierarchy, readers should distinguish the primary result from secondary signals rather than treating every comparison as equally confirmatory. The registry’s limited reporting of missing-data methods and model details further demonstrates why transparent analysis documentation matters when evaluating repeated measures.

Finally, sample-size planning illustrations based on observed effects are not a substitute for the original design rationale. They can help readers understand how assumptions about effect size and target power shape planning, but they do not reveal what assumptions governed this trial. Separating observed results, model-based estimates, recalculations, and planning scenarios is essential for a statistically careful reading.

19. Limitations

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

The registry record describes a three-week trial, so the primary outcome addresses change through Day 21 rather than longer-term course or durability. The primary analysis population requires receipt of at least one dose and at least one post-baseline measurement, and the record does not report the number or reasons for participants who did not meet that definition.

Details needed to reproduce or fully assess the MMRM are not reported, including the full model specification, covariance structure, and missing-data procedures. The record also does not report sensitivity analyses that would show how conclusions might change under alternative assumptions. The recalculated comparisons use approximate standard deviations derived from summary standard errors, so they are not a substitute for participant-level analyses.

The original sample-size justification, interim analyses, and trial-specific planning assumptions are not reported. The registry also does not report whether or how multiplicity was handled across the primary and secondary outcomes. This limits how strongly the multiple secondary findings can be interpreted.

The record does not provide a clinically important difference threshold for the Y-MRS, so the practical importance of the estimated mean differences cannot be determined from the statistical results alone. Safety figures are counts recorded during a short study; the registry summary does not provide enough information to establish causation or characterize longer-term safety. These limitations concern what can be concluded from the registry record and do not establish that additional analyses or procedures were not conducted.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Fixed-dose Safety and Efficacy Study of Asenapine for the Treatment of Acute Manic or Mixed Episode in Bipolar 1 Disorder (P05691) — NCT00764478.
• Registry record last updated 2024-06-18; status last verified 2022-02.
• Results first posted 2015-04-24.
• 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

NCT00764478 is a completed Phase 3 randomized, quadruple-masked, parallel-group placebo-controlled trial of asenapine in bipolar 1 disorder with an acute manic or mixed episode. The trial enrolled 367 participants and compared 5 mg twice daily and 10 mg twice daily with placebo over 21 days.

The primary outcome was change from baseline in Y-MRS total score at Day 21. The posted arm summaries show greater mean decreases in both asenapine groups than in placebo, and the registry’s sponsor-reported MMRM comparisons are negative for both doses. The registry also lists clinical severity, responder, remitter, symptom-timepoint, and safety outcomes.

Important details—including the original sample-size rationale, multiplicity strategy, and missing-data procedures—are not reported in the registry record. The results describe the recorded outcomes over the trial period and should be interpreted with those reporting limits in mind.