Fixed Dose Efficacy and Safety Study of Asenapine for the Treatment of Schizophrenia in Adolescents (P05896): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Fixed Dose Efficacy and Safety Study of Asenapine for the Treatment of Schizophrenia in Adolescents (P05896) (NCT01190254), a randomized phase 3 study. The primary outcome is Change From Baseline in Positive and Negative Syndrome Scale (PANSS) Total Score at Day 56.

2. Clinical Question

The PANSS total score combines ratings across positive symptoms, negative symptoms, and general psychopathology. The clinical question is therefore about average change in a broad clinician-rated measure of schizophrenia symptoms over the treatment period, rather than a single symptom or a long-term outcome. The registry record does not report whether the study’s original statistical design assumptions anticipated a particular effect size or how multiplicity across the two dose comparisons was handled.

3. Trial Design

This was a Phase 3 randomized, parallel-group trial with three arms: placebo, asenapine 2.5 mg twice daily, and asenapine 5.0 mg twice daily. The planned treatment period described in the registry was 8 weeks. The record lists quadruple masking, while the official title describes the trial as double-blind; further details about who was masked or how masking was maintained are not reported in the registry record.

The registry reports enrollment of 306 participants. This is the overall enrollment figure, not the count contributing to each posted primary outcome summary. The primary efficacy outcome lists 77 participants for placebo, 72 for asenapine 2.5 mg twice daily, and 79 for asenapine 5.0 mg twice daily. The efficacy population had additional eligibility requirements involving receipt of study drug and availability of baseline, post-baseline, and Day 56 PANSS measurements.

The study was sponsored by Organon and Co and is listed as completed. The registry record identifies a primary completion date of 2013-03-10 and a start date of 2010-09-28. Those record dates do not by themselves describe the length of follow-up for each participant; the treatment period specified in the study description was 8 weeks.

Participants in the 2.5 mg arm received that dose twice daily throughout the treatment period. In the 5.0 mg arm, participants received 2.5 mg twice daily through Day 3, then 2.5 mg in the morning and 5.0 mg in the evening on Day 4, followed by 5.0 mg twice daily for the remainder. The placebo arm received placebo tablets twice daily. The registry record does not report additional details about allocation concealment, stratification, adherence, or deviations from assigned treatment.

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 1 dose of study drug and had both a baseline and at least 1 post-baseline on-treatment PANSS Total Score (this group is termed the efficacy Full Analysis Set \[FAS\]); also, to be included an on-treatment Day 56 value of PANSS Total Score must be available for a participant.

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline in Positive and Negative Syndrome Scale (PANSS) Total Score at Day 56, measured over Baseline and Day 56.

The primary endpoint was change from baseline in PANSS total score at Day 56. PANSS is a 30-item clinician-rated measure of schizophrenia symptoms. Its positive subscale has 7 items, its negative subscale has 7 items, and its general psychopathology subscale has 16 items. Each item is rated from 1, absent, to 7, extreme; the total is the sum of the item ratings and ranges from 30 to 210. A higher total score indicates greater symptom severity.

Because the endpoint is change from baseline, negative values indicate a reduction in PANSS total score. The registry explicitly describes negative change as improvement in symptoms. Using change rather than only the Day 56 score places the result in relation to each participant’s baseline measurement. It is a continuous outcome, so the posted arm summaries report means and standard deviations rather than event counts.

The PANSS total score is used as a broad measure because it combines several symptom domains in one score. That breadth also means that a total-score change does not show which symptom domain accounts for the change. Secondary outcomes separately address CGI-S and PANSS subscales and factors, but they do not alter the definition of the primary endpoint. The registry record does not report a threshold for what would constitute a clinically important difference.

7. Results Posted in the Registry

• Asenapine 2.5 mg BID: mean -23.70 versus -17.80 on control; difference -5.90 (95% CI -11.75 to -0.05), standardized effect d = -0.32; z-test p = 0.048.
• Asenapine 5.0 mg BID: mean -25.50 versus -17.80 on control; difference -7.70 (95% CI -13.15 to -2.25), standardized effect d = -0.44; z-test p = 0.006.

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 of Severity (CGI-S) Score at Day 56

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Asenapine 2.5 mg BID: mean -1.10 versus -0.80 on control; difference -0.30 (95% CI -0.64 to 0.04), standardized effect d = -0.29; z-test p = 0.082.
  • Asenapine 5.0 mg BID: mean -1.30 versus -0.80 on control; difference -0.50 (95% CI -0.83 to -0.17), standardized effect d = -0.48; z-test p = 0.003.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Asenapine 2.5 mg BID and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Asenapine 5.0 mg BID than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline in PANSS Positive Subscale Score at Day 56

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Asenapine 2.5 mg BID: mean -7.90 versus -6.00 on control; difference -1.90 (95% CI -3.81 to 0.01), standardized effect d = -0.32; z-test p = 0.051.
  • Asenapine 5.0 mg BID: mean -9.10 versus -6.00 on control; difference -3.10 (95% CI -4.94 to -1.26), standardized effect d = -0.53; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Asenapine 2.5 mg BID and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for Asenapine 5.0 mg BID than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Change From Baseline in PANSS Negative Subscale Score at Day 56

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Asenapine 2.5 mg BID: mean -4.80 versus -3.40 on control; difference -1.40 (95% CI -3.14 to 0.34), standardized effect d = -0.26; z-test p = 0.114.
  • Asenapine 5.0 mg BID: mean -4.90 versus -3.40 on control; difference -1.50 (95% CI -3.03 to 0.03), standardized effect d = -0.31; z-test p = 0.054.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Asenapine 2.5 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 5.0 mg BID and the control. The interval gives the range of effects that remain compatible with the data.

The registry lists multiple secondary measures spanning global severity, PANSS positive and negative subscales, combined subscales, general psychopathology, and Marder symptom factors. These outcomes broaden the description of change beyond the total score, but they are related measures of symptoms and should not be treated as independent confirmations of the primary finding.

Across the posted secondary results, the pattern is not uniform across measures and dose comparisons. Some posted group summaries and sponsor-reported comparisons show more evidence of between-group separation than others. That variation is expected to matter when interpreting a collection of outcomes: the overall secondary-outcome pattern is less definitive than a single prespecified primary analysis, especially when the registry record does not explain which analyses were confirmatory or how multiplicity was handled.

The secondary endpoints can provide context for the primary PANSS total result by indicating whether changes are also reflected in particular symptom domains or in the global severity measure. They do not replace the primary endpoint, and a result in one secondary measure does not establish a corresponding result in another. Because the outcomes overlap conceptually and many analyses are listed, isolated unadjusted p-values carry less weight than a coherent prespecified analysis strategy.

The registry reports 18 secondary outcome measures and 43 analyses overall. The multiplicity adjustment, if any, is not reported in the registry record. Without that information, the secondary findings are most appropriately treated as descriptive or exploratory evidence rather than as a set of separately definitive tests. The registry record also does not report thresholds for clinical importance for these secondary scales.

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

• Change From Baseline in Clinical Global Impression of Severity (CGI-S) Score at Day 56
• Change From Baseline in PANSS Positive Subscale Score at Day 56
• Change From Baseline in PANSS Negative Subscale Score at Day 56
• Change From Baseline in PANSS Positive and Negative Subscale Scores Combined at Day 56
• Change From Baseline in PANSS General Psychopathology Subscale Score at Day 56
• Change From Baseline in PANSS Marder Positive Symptoms Factor Score at Day 56
• Change From Baseline in PANSS Marder Negative Symptoms Factor Score at Day 56
• Change From Baseline in PANSS Marder Disorganized Thoughts Factor Score at Day 56

9. Statistical Interpretation

10. Statistical Methods Explained

The study used a randomized, parallel-group design. Random assignment is intended to make treatment groups comparable on average, including on characteristics that were not measured, although it cannot guarantee identical groups in a particular trial. The registry lists three assigned groups and quadruple masking. The official title also calls the trial double-blind; the registry record does not describe the masking procedures in enough detail to clarify the terminology.

The primary outcome is continuous: each participant has a PANSS total score, and the reported endpoint is its change from baseline at Day 56. The posted arm summaries give the mean change and standard deviation for each group. A mean describes the group’s average observed change; a standard deviation describes the spread of individual changes around that average. These summaries do not give the full distribution of individual outcomes.

The sponsor’s primary comparisons are reported as differences in least-squares means from a mixed model for repeated measures, or MMRM. In general, an MMRM uses repeated outcome measurements over time and models their relationship within participants while estimating group differences. Least-squares means are model-based group means or contrasts, conditional on the model specification. They are not necessarily the same as simple differences between the posted arm means. The registry record does not report the full MMRM specification, including the covariance structure, fixed effects, handling of baseline values, or missing-data assumptions.

In general, repeated-measures models can use available measurements from participants with incomplete follow-up, but the validity of the resulting estimates depends on model assumptions and on how missingness relates to observed and unobserved outcomes. That general property does not establish which assumptions or data-handling choices were used in this trial. Apart from the stated efficacy population criteria and the named MMRM, further details about missing observations and analysis populations are not reported in the registry record.

The recalculated comparisons use the posted means, standard deviations, and group counts to form simple unadjusted estimates of between-group mean differences. They are not adjusted for other variables or for repeated measurements, and they do not reproduce the sponsor’s MMRM. The registry identifies a discrepancy between the recalculation and the reported analyses; accordingly, the sponsor’s own analysis takes precedence for the trial’s inferential findings. The recalculated values are useful as a transparent comparison based on the summary statistics, not as a replacement for the trial analysis.

A confidence interval describes a range of estimates compatible with the data and the specified statistical procedure. Its width reflects uncertainty: narrower intervals generally indicate greater precision, while wider intervals indicate less precision. A confidence interval is not a guarantee that the true value lies inside it, and it does not describe the range of individual participant outcomes. The sponsor reports 95% confidence intervals for the two pairwise MMRM contrasts.

A p-value measures how incompatible the observed data are with a specified null hypothesis, under the model and its assumptions. It does not measure the probability that the null hypothesis is true, the size or clinical importance of an effect, or the probability of replication. Interpretation also depends on whether the test was planned, whether multiple comparisons were made, and which analysis population and model were used. The registry lists multiple outcomes and analyses, but the multiplicity strategy is not reported in the registry record.

Dispersion matters because people’s changes can vary substantially even when the group mean difference is modest. In general, greater variability makes a given mean contrast harder to estimate precisely. The posted primary standard deviations are 17.8 for placebo, 18.6 for the 2.5 mg group, and 16.9 for the 5.0 mg group. These values describe variation in the observed outcome changes; they are not standard errors or confidence intervals.

Power is the probability, under a specified alternative and analysis plan, of detecting an effect by a chosen test. The planning illustrations use stated assumptions and observed effect estimates, but they are not the trial’s original design calculation. The original sample-size justification and its assumptions are not reported in the registry record. The planning figures therefore should not be read as evidence about the trial’s observed power.

In general, over-dispersion arises when outcome variability is greater than a model’s assumptions allow. That can make standard errors too small and intervals too narrow if not addressed. The primary PANSS measure is continuous, and the registry record does not identify over-dispersion as a concern or describe a diagnostic assessment. Count-outcome remedies should not be assumed to apply to this continuous endpoint.

11. Confidence Intervals and Precision

The sponsor’s reported MMRM estimate for asenapine 2.5 mg twice daily versus placebo is -4.8 PANSS points, with a 95% confidence interval from -9.9 to 0.4. That interval includes zero, so the reported estimate is compatible with values on either side of no difference under the stated interval procedure. The reported p-value is 0.070. The registry does not report a confidence interval for the sponsor’s three-group analyses.

For asenapine 5.0 mg twice daily versus placebo, the sponsor reports a difference of -5.6 points and a 95% confidence interval from -10.7 to -0.5. This interval is entirely below zero, while the associated reported p-value is 0.064. Because that p-value and interval are discordant under the usual matching two-sided test interpretation, the registry record does not support a simple inference from one while disregarding the other. Details that might explain the discrepancy are not reported in the registry record.

In general, a confidence interval communicates both the direction and precision of an estimate. Wider limits indicate more uncertainty about the size of the contrast; they do not imply that individual outcomes fall within those limits. The intervals above concern model-based differences in average PANSS change, not the range of participant responses. The registry does not report a clinically important-difference threshold for interpreting these intervals.

The arm-level standard deviations also indicate that individual changes varied around each group mean. A mean contrast can therefore be estimated with uncertainty even when the arm averages differ. The recalculated unadjusted intervals are distinct from the sponsor’s MMRM intervals and arise from a different analysis. Given the discrepancy flag, the sponsor’s analysis remains the primary basis for describing the trial’s inferential precision.

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 describe participants per arm for comparisons between two groups. They are not totals across all three trial arms and are not total event counts. The stated 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 to the stated fraction of the observed effect. These are planning illustrations based on the observed effect, not assumptions known to have guided the original study design.

For each effect assumption, the 80% power column gives the estimated number of participants per arm for an 80% chance of detecting that effect under the stated planning assumptions. The 90% power column gives the corresponding number per arm for a 90% chance. These are prospective planning quantities conditional on the assumptions; they do not describe the probability that the completed trial detected an effect or the probability that a result is true.

Rows planning for 75% or 50% of the observed effect consider smaller effects than the row using the full observed effect. Smaller effects require more participants per arm to reach the same target power, all else being equal. The values should be read as illustrations of how sample-size needs change with the effect being targeted, not as a retrospective verdict on whether the trial was adequately designed. This is not observed power.

The original sample-size justification, targeted effect, and design-stage assumptions are not reported in the registry record. The posted enrollment of 306 is the study enrollment figure, whereas the planning illustrations are per-arm calculations for two-group comparisons. Those quantities answer different questions and should not be conflated.

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 = -5.900; pooled standard deviation σ = 18.191.
2. n = 2 × (1.96 + 0.842)² × 18.191² / -5.900² = 149.2, rounded up to 150 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 <- -5.9                      # observed difference in means
sigma <- 18.1907878307885                     # 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(1190254)
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 = 150 (80% power), 200 (90% power)
 75% of observed effect: n per arm = 266 (80% power), 356 (90% power)
 50% of observed effect: n per arm = 597 (80% power), 800 (90% power)
power.t.test: 150.2 
Simulated power at n = 150 per arm: 0.800 (20000 replicates)

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

14. Analyses Reported by the Sponsor

The registry reports sponsor analyses using MMRM and differences in least-squares means. For the primary outcome, the reported contrasts are -4.8 for asenapine 2.5 mg twice daily versus placebo and -5.6 for asenapine 5.0 mg twice daily versus placebo. Their reported 95% confidence intervals are -9.9 to 0.4 and -10.7 to -0.5, respectively; the reported p-values are 0.070 and 0.064.

The simple recalculations use the posted group means, standard deviations, and counts rather than the sponsor’s repeated-measures model. They estimate mean differences of -5.9 and -7.7, with unadjusted p-values of 0.048 and 0.006. The differences between these results can reflect that the analyses estimate contrasts differently, but the registry record does not give enough model detail to identify the reason in this trial.

The sponsor’s reported analysis takes precedence over the recalculation for describing the trial’s own inferential results. The recalculation is best understood as a separate, unadjusted check based on summary statistics. In particular, the sponsor’s 5.0 mg confidence interval and p-value are not mutually aligned under the usual matching test interpretation; the registry record does not explain this. The reported figures should therefore be retained as reported rather than replaced by a recalculated result or reconciled by speculation.

15. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when several hypotheses are tested, because the chance of at least one apparently notable result can increase across a collection of tests. This trial’s primary objective was to demonstrate superiority of at least one of two asenapine doses over placebo on PANSS total change at Day 56. That objective involves more than one dose comparison. The registry also lists many secondary outcomes and analyses.

The record includes five sponsor-reported MMRM entries for the primary outcome: two pairwise estimates and three p-values for analyses involving all three groups. The latter entries do not identify their specific hypotheses or test types. The record does not say whether the primary dose comparisons were adjusted for multiplicity, whether a testing hierarchy was used, or how the secondary analyses were treated. Therefore, it is not possible to determine from the registry record whether the reported p-values are adjusted or how they relate to a prespecified family of tests.

Missing-data handling is also incompletely described. The primary efficacy population includes randomized participants who received at least one dose, had baseline and at least one post-baseline on-treatment PANSS total score, and had a Day 56 PANSS total score available. The sponsor reports use of MMRM, but the registry record does not report the model’s missing-data assumptions, the amount or pattern of missing outcome data, or sensitivity analyses for missingness.

The record reports overall enrollment of 306, while the primary efficacy summaries include fewer participants in each arm. The eligibility definition and analysis counts should not be confused with all randomized participants. Details of the full randomized analysis population, exclusions, and reasons for missing endpoint data are not reported in the registry record. These gaps limit assessment of how robust the endpoint results are to analysis-population choices and missing observations.

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: schizophrenia (2.9%), hallucination, auditory (1.0%), pneumonia (1.0%), typhoid fever (0.9%).

The safety summaries list 102 participants at risk in the placebo group, 98 in the asenapine 2.5 mg twice-daily group, and 106 in the asenapine 5.0 mg twice-daily group. Three participants in each group are listed as affected by a serious adverse event. These are counts, and the at-risk group sizes are distinct from the primary efficacy outcome counts.

The record also lists participants affected by other adverse events: 23 for placebo, 39 for asenapine 2.5 mg twice daily, and 46 for asenapine 5.0 mg twice daily. The registry’s top serious adverse event terms include Schizophrenia at 2.9%, Hallucination, auditory at 1.0%, Pneumonia at 1.0%, and Typhoid fever at 0.9%. Those terms and percentages are registry entries, not a complete account of every event or its clinical context.

Deaths are not reported in the registry record. The available summary does not provide event-level narratives, timing, duration, relatedness, or severity for each participant. Counts across groups alone do not establish causation or permit a full comparison of safety. These figures describe the posted registry data and should be interpreted alongside the record’s limited detail.

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

The posted results describe average PANSS total-score change over the 8-week treatment period in the efficacy population. Negative changes indicate reductions from baseline, and the observed arm means are negative in all three groups. The two asenapine groups have more negative mean changes than placebo in the posted summaries. The sponsor’s MMRM estimates also point toward greater mean reductions in the active-dose groups, but their reported uncertainty and p-values require careful, qualified reading.

These results do not by themselves establish how meaningful a difference would be to participants. The registry record does not report a threshold for clinically important change, and group averages do not describe every participant’s experience. The trial’s primary endpoint is a clinician-rated symptom scale, not a direct measure of every aspect of functioning, quality of life, or longer-term outcome.

The results also do not establish whether any observed difference would persist beyond the treatment period. The study description specifies 8 weeks of treatment, and longer-term follow-up results are not reported in the registry record. The record does not provide enough information to assess all aspects of the analysis plan, including the multiplicity approach, full missing-data procedures, or the reason for the discrepancy between recalculated and sponsor-reported results.

Accordingly, the most defensible statistical reading is limited to the reported sample, outcome, time point, and analyses. The arm means are descriptive; the sponsor’s MMRM results are the trial’s reported inferential analyses; and the recalculated comparisons are unadjusted alternatives that do not supersede those analyses. Neither the numerical estimates nor their p-values alone establish clinical importance, an individual-level response, or a result beyond the registry’s stated scope.

18. Why This Trial Matters Statistically

This trial illustrates why the analysis used matters when interpreting a continuous endpoint. The posted arm means permit a transparent unadjusted comparison, while the sponsor reports model-based least-squares mean contrasts from MMRM. Those estimates are not identical, and the registry explicitly flags a discrepancy. Treating one set as if it were the other would obscure which analysis generated each result.

It also shows why estimates and uncertainty should be read together. A point estimate gives a direction and scale for an average contrast, while a confidence interval describes its precision under a specified procedure. Here, the sponsor’s reported p-values and confidence intervals are not fully aligned under usual matching-test interpretation, and details explaining that issue are not reported in the registry record. Statistical reporting needs enough model and test information for readers to understand such combinations.

The study also highlights multiplicity as a design and interpretation concern. The primary objective compares two active doses with placebo, and the record contains numerous secondary outcomes and analyses. Without the reported multiplicity strategy, readers cannot tell whether the presented tests were controlled as a family, prioritized hierarchically, or intended to be exploratory.

Finally, planning sample sizes derived from observed effects are illustrations, not a substitute for a prespecified design justification. The original assumptions are not reported in the registry record. Keeping these distinctions clear supports a more disciplined reading of effect estimates, uncertainty, and the limits of registry reporting.

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.

Several limitations are specific to the available record. First, the sponsor’s reported primary MMRM p-values and confidence intervals are not fully consistent under the usual matching two-sided test interpretation. The record does not provide enough detail to explain the discrepancy, so it cannot be resolved from the posted information.

Second, the MMRM is named, but the full model specification is not reported in the registry record. Covariance structure, covariates, model assumptions, and missing-data procedures are not described. The registry defines an efficacy population with a Day 56 PANSS value requirement, but does not report a full accounting of exclusions, missing measurements, or sensitivity analyses.

Third, the record does not report the multiplicity strategy for two primary dose comparisons and the many secondary outcomes and analyses. This limits the strength of interpretation for isolated p-values, especially among secondary measures. The original sample-size justification and design-stage assumptions are also not reported; the planning illustrations based on observed effects cannot fill that gap.

Finally, the primary outcome is a symptom scale measured at Day 56, and the record does not report a clinical-importance threshold or longer-term outcome results. Safety summaries provide counts and selected serious-event terms but not full event-level details or deaths. These limitations constrain interpretation of the estimates and the scope of conclusions that can be drawn from the registry record.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Fixed Dose Efficacy and Safety Study of Asenapine for the Treatment of Schizophrenia in Adolescents (P05896) — NCT01190254.
• Registry record last updated 2024-05-21; status last verified 2022-02.
• Results first posted 2014-06-06.
• 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

NCT01190254 is a completed Phase 3 randomized, parallel-group trial of asenapine in adolescents with schizophrenia. It enrolled 306 participants and compared placebo with asenapine 2.5 mg twice daily and 5.0 mg twice daily over an 8-week treatment period. The registry lists quadruple masking, while the official title describes the study as double-blind.

The primary endpoint was change from baseline in PANSS total score at Day 56, with negative values representing improvement. The posted arm means were -17.8 for placebo, -23.7 for asenapine 2.5 mg twice daily, and -25.5 for asenapine 5.0 mg twice daily. Sponsor-reported MMRM comparisons and unadjusted recalculations differ; the sponsor’s own analysis takes precedence for the trial’s inferential results.

The registry lists numerous secondary outcomes and analyses, but the multiplicity strategy, detailed model specification, and full missing-data procedures are not reported in the registry record. Safety summaries report serious adverse event counts and selected event terms, with deaths not reported in the registry record.