Study to Evaluate the Efficacy, Safety and Tolerability of an Oral Aripiprazole/Escitalopram Combination Therapy in Participants With Major Depressive Disorder (MDD): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study to Evaluate the Efficacy, Safety and Tolerability of an Oral Aripiprazole/Escitalopram Combination Therapy in Participants With Major Depressive Disorder (MDD) (NCT01111565), a randomized phase 3 study. The primary outcome is Phase C: Mean Change From End of Phase B (Week 8) in the Montgomery-Asberg Depression Rating Scale (MADRS) Total Score to End of Phase C (Week 14).

2. Clinical Question

3. Trial Design

This was a Phase 3, randomized, double-blind, parallel-group study of oral aripiprazole and escitalopram in participants with major depressive disorder. The sponsor was Otsuka Pharmaceutical Development & Commercialization, Inc. The registry record reports enrollment of 137 and a status of terminated. The recorded start date was 2010-10-04, and the primary completion date was 2011-09-01. The reason for termination is not reported in the registry record.

The study included sequential phases. Phase B was a single-blind prospective escitalopram treatment phase. Its description states that escitalopram was given at 10 mg daily, with an increase to 20 mg/day at the end of Week 1 depending on tolerability. The description also notes restrictions on later dose changes. Phase B+ continued single-blind treatment for participants who met the recorded responder criteria at the end of Phase B. The primary comparison concerned Phase C, in which participants with an incomplete response at Week 8 were randomized to combination therapy, escitalopram monotherapy, or aripiprazole monotherapy for 6 weeks.

The primary outcome analysis population was the intent-to-treat sample defined in the registry: randomized participants who received at least one dose of double-blind trial medication and had at least one post-randomization efficacy evaluation in Phase C. The primary endpoint estimates are based on 16 participants in the combination arm, 14 in the escitalopram arm, and 15 in the aripiprazole arm. Those arm counts describe the endpoint analysis and should not be confused with the overall enrollment.

The original sample-size justification, the reason for trial termination, and details of any interim analyses are not reported in the registry record. The available record does not establish why the trial ended or whether termination changed the planned analysis.

4. Participant Flow and Accounting

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

Before assignment: A total of 137 participants were enrolled in Phase B (Single-blind Prospective Treatment Phase) to receive escitalopram monotherapy(10 or 20mg/day),of which 26 responders continued to Phase B+(Single-blind Phase B Responders),received escitalopram monotherapy(10 or 20mg/day).45 non-responders were randomized in 1:1:1 ratio to Phase C(Double-blind Randomization Phase),received aripiprazole/escitalopram combination therapy or escitalopram or aripiprazole monotherapy.

Phase B (Weeks 0 to 8)

Reasons for not completing this period:

Phase B + and Phase C (Weeks 9 to 14)

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Intent-to-treat (ITT) Sample included all participants in the Randomized Sample who received at least one dose of double blind trial medication and had at least one post-randomization efficacy evaluation in Phase C.

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: Phase B Sample included all participants who took at least one dose of escitalopram as indicated on the dosing record.

6. Primary Endpoint

The registry lists the primary outcome as Phase C: Mean Change From End of Phase B (Week 8) in the Montgomery-Asberg Depression Rating Scale (MADRS) Total Score to End of Phase C (Week 14), measured over Week 8 to Week 14.

The primary endpoint was mean change in the Montgomery-Asberg Depression Rating Scale (MADRS) total score from the end of Phase B at Week 8 to the end of Phase C at Week 14. MADRS assesses depressive symptom severity across 10 items. Its total score ranges from 0 to 60, with higher scores indicating greater severity. A negative change indicates a reduction in score and therefore a reduction in measured symptom severity.

The scale covers symptoms including sadness, lassitude, pessimism, inner tension, suicidality, reduced sleep or appetite, difficulty concentrating, and lack of interest. Each item is rated on a 7-point scale from 0, indicating no symptoms, to 6, indicating symptoms of maximum severity. Using a standardized symptom scale makes it possible to express change numerically and compare average changes between randomized groups.

The endpoint focuses on the 6-week Phase C period, beginning after the prospective escitalopram phase. It therefore addresses the randomized comparison among participants who reached Phase C, rather than the entire group enrolled into the earlier study phase. The primary analysis used least-squares means and the last observation carried forward method. Least-squares means are model-based group estimates; the registry record does not provide enough detail to fully reconstruct the model specification.

7. Results Posted in the Registry

• Phase C: Escitalopram Monotherapy: mean -3.60 versus -9.00 on control; difference 5.40 (95% CI -0.56 to 11.36), standardized effect d = 0.65; z-test p = 0.076.
• Phase C: Aripiprazole Monotherapy: mean -3.80 versus -9.00 on control; difference 5.20 (95% CI -0.62 to 11.02), standardized effect d = 0.63; z-test p = 0.080.

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.

Phase C: Clinical Global Impression - Improvement Scale (CGI-I) Score at the End of Phase C

• 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:
  • Phase C: Escitalopram Monotherapy: mean 3.00 versus 2.50 on control; difference 0.50 (95% CI -0.05 to 1.05), standardized effect d = 0.64; z-test p = 0.077.
  • Phase C: Aripiprazole Monotherapy: mean 2.90 versus 2.50 on control; difference 0.40 (95% CI -0.15 to 0.95), standardized effect d = 0.51; z-test p = 0.157.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Phase C: Escitalopram Monotherapy 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 Phase C: Aripiprazole Monotherapy and the control. The interval gives the range of effects that remain compatible with the data.

Phase C: Mean Change From End of Phase B (Week 8) in the Sheehan Disability Scale (SDS) Mean Score to End of Phase C (Week 14)

• 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:
  • Phase C: Escitalopram Monotherapy: mean -1.80 versus -1.60 on control; difference -0.20 (95% CI -2.14 to 1.74), standardized effect d = -0.08; z-test p = 0.840.
  • Phase C: Aripiprazole Monotherapy: mean -0.60 versus -1.60 on control; difference 1.00 (95% CI -0.94 to 2.94), standardized effect d = 0.38; z-test p = 0.312.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Phase C: Escitalopram Monotherapy 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 Phase C: Aripiprazole Monotherapy and the control. The interval gives the range of effects that remain compatible with the data.

The two posted secondary outcomes add different perspectives to the primary symptom-scale result. One is the Clinical Global Impression - Improvement score at the end of Phase C; the other is change in Sheehan Disability Scale mean score from Week 8 to Week 14. The registry reports comparisons of combination treatment with each monotherapy for both measures. Taken together, the posted secondary estimates do not provide a consistent, precise pattern of separation across all outcomes and comparators. Their confidence intervals include zero, and the registry's own analyses do not show a clear statistical distinction in these comparisons.

These outcomes relate to the primary result by assessing improvement and disability through measures other than the MADRS total score. They can help describe whether the pattern on the primary symptom measure is accompanied by a similar pattern on other recorded outcomes. They do not replace the primary endpoint, and their distinct measurement scales mean that their numerical values should not be compared directly with MADRS points.

Secondary results generally carry less confirmatory weight when there are several outcomes or comparisons, particularly when multiplicity handling is not described. Testing more outcomes can increase the opportunity for chance findings. Whether a prespecified multiplicity adjustment was used is not reported in the registry record. The secondary results are therefore best viewed as supporting context, not as separate proof or as a reason to override the primary analysis.

The registry reports only two secondary outcomes, and the number of posted analyses is six. The analysis plan governing selection, multiplicity, and interpretation of those comparisons is not reported in the registry record. This makes it difficult to determine whether the secondary analyses were intended as confirmatory tests or descriptive assessments.

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

• Phase C: Clinical Global Impression - Improvement Scale (CGI-I) Score at the End of Phase C
• Phase C: Mean Change From End of Phase B (Week 8) in the Sheehan Disability Scale (SDS) Mean Score to End of Phase C (Week 14)

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is a continuous score, and the registry reports a group mean change for each Phase C arm. A mean summarizes the average observed change within a group, but by itself it does not show how uncertain that average is. The registry gives a standard error alongside each least-squares mean. A standard error describes the precision of an estimated mean: a larger standard error generally corresponds to greater uncertainty in the estimate. It is not the same as the spread of individual participant scores.

What does the adjusted comparison represent?

The registry identifies ANCOVA as the method for the primary comparisons. ANCOVA, or analysis of covariance, compares group outcomes using a statistical model that can adjust for other variables included in that model. Such adjustment can account for measured differences or baseline outcome information, depending on the specified model. The registry record does not report the full covariate list or enough model details to reproduce the adjusted analysis. The sponsor's treatment differences are therefore best read as the posted model-based comparisons rather than as simple subtractions of the group means.

The reported adjusted treatment difference for combination treatment versus escitalopram monotherapy was -5.4. For combination treatment versus aripiprazole monotherapy, it was -5.2. Since the group mean changes are more negative for combination treatment, the negative sign of these sponsor-reported contrasts is consistent with expressing combination minus monotherapy. The unadjusted recalculations use the reverse subtraction order and consequently have positive estimates. The sign convention changes the label's direction, not the underlying comparison.

Why do confidence intervals matter?

A confidence interval gives a range of values compatible with the data under the analysis assumptions. Its width conveys precision: narrower intervals indicate more precise estimates, while wider intervals leave more uncertainty about the size and direction of the difference. For the two primary sponsor comparisons, the 95% intervals extend across zero. Zero represents no difference on the treatment-difference scale. This means that the posted intervals include no difference, while also including nonzero differences. An interval is not a guarantee that the true effect lies in the range, nor does it identify which value within the range is most likely.

The registry reports p-values with the sponsor's comparisons, and the recalculations include unadjusted p-values. A p-value measures how inconsistent the observed data are with a specified null model, under the assumptions of the analysis. It does not measure the probability that the null hypothesis is true, and it does not establish that a clinically meaningful difference exists. The registry's adjusted comparisons and the simple unadjusted recalculations are distinct analyses and should not be treated as interchangeable.

What does the unadjusted recalculation add?

The recalculations compare posted summary statistics without the full adjustment model used by the sponsor. The pooled standard deviations in these calculations are approximate because they were reconstructed from the reported standard errors and group sizes. These calculations offer a transparent, simple comparison of the posted group estimates, but they cannot recover unreported model details or covariate adjustment. They are a check on the broad numerical pattern, not a replacement for the registry's analysis. No discrepancy between the recalculations and sponsor results is flagged in the registry record, and the sponsor's own analysis remains the primary reported analysis.

For general context, over-dispersion means that the observed variability is greater than a model assumes. If a method underestimates variability, standard errors and confidence intervals can be too small, making results look more precise than they are. The registry record does not identify over-dispersion as a concern in this trial, and the primary endpoint is reported as a continuous measure rather than as an event-count outcome.

What assumptions underlie the planning illustrations?

The planning illustrations are based on the observed effect, rather than on the original trial design. Their stated assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The target effect is expressed as a stated fraction of the observed effect. These are planning assumptions for the illustrations, not a report of the trial's own original assumptions. The original sample-size justification and design assumptions are not reported in the registry record.

For general explanation, statistical power is the probability that a planned analysis will detect an effect of a specified size if that effect is real and the assumptions of the calculation hold. It depends on the effect size, variability, analysis approach, and number of participants. The illustrations do not say what the observed study's power was. Their purpose is to show how participant requirements would change under the stated hypothetical planning conditions.

How should multiple outcomes be treated?

The registry identifies one primary outcome and posts two secondary outcomes. If many outcomes or comparisons are tested, the chance of at least one apparently notable result can increase. Multiplicity procedures can address that issue, but any such procedures for these analyses are not reported in the registry record. The secondary results should therefore be interpreted as additional, exploratory context rather than as independent confirmation of the primary result.

11. Confidence Intervals and Precision

The primary estimates are based on 16 participants in the combination arm, 14 in the escitalopram monotherapy arm, and 15 in the aripiprazole monotherapy arm. The reported standard errors for the group mean changes are 2.1, 2.2, and 2.1, respectively. These values accompany least-squares means and indicate uncertainty in the estimated group averages; they do not describe the full range of individual participant changes.

The sponsor's 95% confidence interval for combination treatment versus escitalopram monotherapy runs from -11.5 to 0.7, around a treatment difference of -5.4. For combination treatment versus aripiprazole monotherapy, the interval runs from -11.2 to 0.7, around a treatment difference of -5.2. Each interval includes zero. The intervals also cover values on both sides of zero, so the data do not pin down the direction of the difference with high precision.

The recalculated unadjusted intervals are -0.561 to 11.36 for the mean difference between escitalopram monotherapy and combination treatment, and -0.621 to 11.02 for the difference between aripiprazole monotherapy and combination treatment. Their positive direction reflects the reverse contrast order. They too include zero and span a range of possible differences. These intervals are derived from summary statistics and do not replace the registry's adjusted intervals.

Confidence intervals express uncertainty under the analysis assumptions; they are not ranges of individual responses and do not indicate that every value in the range is equally plausible. Here, the relatively small Phase C groups and the intervals' inclusion of zero limit how precisely the between-group differences can be described. The posted results support reporting the estimated contrasts and their uncertainty, rather than treating the point estimates alone as conclusive.

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 entries give participants per arm for 80% power and participants per arm for 90% power. They are not total trial enrollment figures. The calculations use the observed effect as a starting point and show hypothetical planning values when the target effect is 100%, 75%, or 50% of that observed effect. For example, the primary comparison with escitalopram monotherapy lists 38 participants per arm for 80% power when planning for 100% of the observed effect, and 67 participants per arm for 80% power when planning for 75% of that effect.

The stated assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. For this continuous endpoint, the entries are participants per arm, not total events. The event-count convention applies to time-to-event planning calculations, which are not the type of outcome analyzed as the primary endpoint. The trial's own original design assumptions and sample-size justification are not reported in the registry record.

In plain terms, the 80% column gives the number per arm that the planning calculation associates with an 80% chance of detecting the specified effect under its assumptions. The 90% column gives the number per arm associated with a higher planned chance of detection for that same target effect. Smaller target effects require more participants because they are harder to distinguish from ordinary variability. The entries are planning illustrations, not a description of what happened in the trial, and they are not observed power.

The sample-size curve should be read as a visual expression of the same relationship: as the target effect becomes smaller, the required number of participants rises. The values depend on the assumptions and the effect fractions used in the calculation. They should not be interpreted as evidence that the observed trial had a particular chance of detecting its result, or as evidence that the original trial was designed using these assumptions.

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 = 5.400; pooled standard deviation σ = 8.322.
2. n = 2 × (1.96 + 0.842)² × 8.322² / 5.400² = 37.3, rounded up to 38 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 <- 5.4                      # observed difference in means
sigma <- 8.32225930862527                     # 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(1111565)
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 = 38 (80% power), 50 (90% power)
 75% of observed effect: n per arm = 67 (80% power), 89 (90% power)
 50% of observed effect: n per arm = 150 (80% power), 200 (90% power)
power.t.test: 38.3 
Simulated power at n = 38 per arm: 0.801 (20000 replicates)

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

14. Analyses Reported by the Sponsor

The registry's own primary analyses use ANCOVA and report treatment differences, 95% confidence intervals, and p-values. For combination treatment compared with escitalopram monotherapy, the reported difference is -5.4, with a 95% confidence interval from -11.5 to 0.7 and p =0.079. For combination treatment compared with aripiprazole monotherapy, the reported difference is -5.2, with a 95% confidence interval from -11.2 to 0.7 and p =0.085.

The simple recalculations compare the posted group means without reproducing the sponsor's full adjusted model. Their estimates are 5.4 for escitalopram monotherapy versus combination treatment and 5.2 for aripiprazole monotherapy versus combination treatment. The opposite signs reflect the reverse order of subtraction. The unadjusted confidence intervals and p-values are also close to, but not identical to, the adjusted registry results.

The recalculations rely on summary statistics, and the pooled standard deviations are approximate. They cannot account for covariates or other details that may be part of the sponsor's model. The registry record does not flag a discrepancy between the recalculations and the sponsor analysis. The sponsor's adjusted results are the primary reported comparisons; the recalculations are useful as a transparent, unadjusted cross-check, not as a substitute for that analysis.

15. Multiplicity, Missing Data and Analysis Populations

The registry identifies the MADRS change from Week 8 to Week 14 as the primary outcome and lists two secondary outcomes: CGI-I score at the end of Phase C and change in SDS mean score. It also posts comparisons of the combination group with each monotherapy group. When a study examines several outcomes and contrasts, the chance of at least one apparently unusual result can rise even if there is no true difference. Statistical plans may address this through prespecified testing order or multiplicity adjustment, but such procedures are not reported in the registry record.

The primary population is defined as randomized participants who received at least one dose of double-blind trial medication and had at least one post-randomization efficacy evaluation in Phase C. The registry states that the last observation carried forward method was used for analyses. This method carries a participant's last available observation forward to represent a later measurement. Its interpretation depends on assumptions about the missing measurements and what would have happened after the last observation.

The number of participants with missing outcome data, reasons for missingness, timing of missing measurements, and results from alternative missing-data approaches are not reported in the registry record. The full statistical analysis plan, including details of the ANCOVA model and any interim analyses, is also not reported in the registry record. These omissions limit independent assessment of whether the analysis choices were prespecified and how robust the findings are to other reasonable choices.

The study's status is terminated, but the reason for termination is not reported in the registry record. The record does not explain whether termination was related to recruitment, safety, efficacy, operational factors, or another reason. No inference about the cause of termination or its effect on analysis completeness is warranted from the status alone.

16. Safety Results

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

Deaths

Other (non-serious) adverse events

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

Most frequent non-serious adverse event terms

For serious adverse events, the registry reports zero affected participants in each listed phase group. The at-risk counts were 137 in Phase B, 26 in Phase B+, 16 in the Phase C combination group, 14 in the Phase C escitalopram monotherapy group, and 15 in the Phase C aripiprazole monotherapy group. The registry also reports zero deaths in each of these groups. No serious adverse event terms are listed among the top serious terms.

These figures describe the recorded counts in the registry and should be read with the size and duration of each group in mind. Phase C involved relatively small groups and lasted 6 weeks, while Phase B covered the prospective escitalopram phase. Zero reported serious adverse events in a group does not establish that an event could not occur, and these counts do not by themselves provide a complete comparison of safety between treatments.

The record separately reports participants affected by other, non-serious adverse events: 65 in Phase B, 4 in Phase B+, 12 in the combination group, 11 in the escitalopram monotherapy group, and 13 in the aripiprazole monotherapy group. These are counts of participants affected, not counts of all event occurrences. The registry summaries do not provide enough detail to characterize the events' causes or clinical significance.

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

The posted primary estimates show a more negative average MADRS change in the combination group than in either monotherapy group over the Week 8 to Week 14 interval. The registry's adjusted comparisons estimate treatment differences of -5.4 and -5.2 for the two monotherapy comparisons. However, both 95% confidence intervals include zero. The results therefore do not precisely establish the size or direction of a between-group difference under the reported analyses.

These findings describe the participants who reached Phase C and met the stated analysis-population criteria. They do not directly describe all 137 enrolled participants as a single randomized comparison, because the primary analysis population required exposure to double-blind medication and a post-randomization efficacy evaluation in Phase C. The results also concern a defined group with major depressive disorder and an incomplete response to prospective escitalopram treatment, rather than all people with depression or all treatment settings.

A numerical reduction in MADRS score is a change on a symptom rating scale. It is not, by itself, a complete account of functioning, individual experience, longer-term outcomes, or the balance of benefits and harms. The secondary measures add information on global improvement and disability, but they do not remove the uncertainty in the primary comparisons. Safety counts also need to be interpreted in light of the small Phase C groups and the study's recorded duration.

The registry record does not report the reason for termination, the original sample-size justification, a complete statistical analysis plan, or detailed missing-data sensitivity analyses. Those omissions make it harder to judge how the study was intended to operate and how robust the posted estimates are. The findings should therefore be understood as the results of the recorded analyses, with uncertainty, rather than as a definitive answer about treatment effects.

18. Why This Trial Matters Statistically

This trial illustrates why an estimate and its uncertainty need to be read together. The primary group means favor a more negative change in the combination arm numerically, but the sponsor's confidence intervals extend across zero. The point estimates alone would give an incomplete account; the intervals show that the comparison remains imprecise.

It also demonstrates the distinction between an adjusted analysis and a simple recalculation. ANCOVA is the registry's reported method, while the recalculations use posted summary statistics and do not reproduce the full model. Their numerical proximity offers a useful check on the general pattern, but the methods answer the comparison using different information. Clear interpretation requires retaining the sponsor's contrast direction and recognizing that the recalculated signs use the reverse order.

The study's sequential design matters for understanding who contributes to the primary comparison. Participants first entered a prospective escitalopram phase; the primary randomized comparisons apply to the Phase C analysis population. The overall enrollment is not the same as the number contributing to each Phase C estimate. This distinction is important when assessing precision and the scope of the conclusions.

Finally, the registry record shows how missing information can shape statistical interpretation. The termination reason, original design assumptions, multiplicity approach, and detailed missing-data information are not reported. Naming those unknowns helps keep interpretation aligned with what the posted results can support. The sample-size illustrations further show that planning requirements depend strongly on the effect size targeted, rather than representing a retrospective measure of what the trial achieved.

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 Phase C primary comparisons are based on 16, 14, and 15 participants in the respective arms. These small analysis groups contribute to the uncertainty reflected in the confidence intervals. The study's overall enrollment of 137 does not mean that all enrolled participants were included in each Phase C comparison; the primary analysis population was defined by treatment exposure and availability of a post-randomization Phase C efficacy evaluation.

The primary analysis used last observation carried forward. The registry record does not report the extent or pattern of missing data, reasons for missingness, or sensitivity analyses using other methods. Because carrying the last observation forward is an assumption-based approach, the absence of this information limits assessment of the possible impact of missing measurements.

The registry describes the primary comparisons as ANCOVA but does not report the full model specification or its covariates. The unadjusted recalculations are based on summary statistics, with approximate pooled standard deviations, and cannot recreate that adjusted model. They are therefore supplementary, not an independent reproduction of the sponsor's analysis.

Multiplicity procedures for the primary and secondary analyses are not reported in the registry record. The reason the study was terminated, the original sample-size justification, and details of interim analyses are also not reported. Those gaps prevent a full assessment of the intended analysis strategy and the context of termination. The recorded results should be interpreted with these trial-specific limitations in mind.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Study to Evaluate the Efficacy, Safety and Tolerability of an Oral Aripiprazole/Escitalopram Combination Therapy in Participants With Major Depressive Disorder (MDD) — NCT01111565.
• Registry record last updated 2021-12-21; status last verified 2021-12.
• Results first posted 2021-12-21.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

23. Record Summary

The registry record describes a randomized, double-blind, parallel-group Phase 3 study of aripiprazole, escitalopram, and their combination in participants with major depressive disorder. Enrollment was 137, and the status is terminated. The primary comparison was change in MADRS total score from Week 8 to Week 14 among the Phase C analysis population.

The combination group had a more negative mean change than either monotherapy group, while the sponsor's adjusted 95% confidence intervals for both comparisons included zero. The analysis used ANCOVA and last observation carried forward. Two secondary outcomes were posted, and zero serious adverse events and zero deaths were reported in each listed phase group.

The reason for termination, original sample-size justification, multiplicity approach, and detailed missing-data information are not reported in the registry record. The posted estimates therefore warrant interpretation alongside their uncertainty and the limits of the available analysis details.