This page provides an independent statistical analysis and educational interpretation of publicly reported results. ClinicalTrials.gov provides the official trial registry record. Numerical trial results on this page are restricted to the results posted in the ClinicalTrials.gov record; calculations added by Clinical Biostats are labelled as such.
1. Trial at a Glance
This page covers the registry results for Randomized, Double-Blind, Placebo Controlled Study of Vilazodone's Efficacy, Safety, and Biomarkers of Response in Major Depressive Disorder (MDD) (NCT00683592), a randomized phase 3 study. The primary outcome is Change From Baseline to Week 8 in the MADRS (Montgomery-Asberg Depression Rating Scale) Total Score..
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT00683592 |
| Phase | Phase 3 |
| Condition | Major Depressive Disorder |
| Allocation | Randomized |
| Design model | Parallel |
| Masking | Quadruple |
| Enrollment | 481 |
| Arms in the primary outcome | 2 |
| Lead sponsor | Forest Laboratories |
| Results posted | Yes |
2. Clinical Question
Population
Adults diagnosed with major depressive disorder using DSM-IV-TR criteria. The primary efficacy analysis used the intent-to-treat population: randomized patients who took at least 1 dose of study drug and had at least 1 post-baseline efficacy endpoint measurement. The registry record lists enrollment of 481 participants.
Intervention
Vilazodone 40 mg once daily. The trial assessed efficacy and safety and also aimed to evaluate genetic biomarkers associated with treatment response.
Comparator
Placebo. The study was randomized, double-blind, placebo-controlled, and used a parallel-group model. The record describes quadruple masking.
Primary question
What was the difference between vilazodone and placebo in mean change from baseline to Week 8 in the MADRS total score? The scale’s change measure ranges from -60 to 60, with negative values indicating improvement in depression symptom severity.
3. Trial Design
This was a phase 3, randomized, parallel-group trial of vilazodone and placebo in patients with major depressive disorder. The registry describes it as double-blind and placebo-controlled, and records quadruple masking. It was multicenter and lasted 8 weeks. The trial was designed to assess efficacy and safety and to evaluate genetic biomarkers associated with treatment response.
The registry record lists enrollment of 481. For the primary outcome, the intent-to-treat population included participants who were randomized, took at least 1 dose of study drug, and had at least 1 post-baseline efficacy endpoint measurement. Each primary-outcome arm included 231 participants. The safety population included 235 participants in the vilazodone group and 233 in the placebo group. These analysis populations are defined separately in the registry and should not be treated as interchangeable.
The primary endpoint was change from baseline in MADRS total score, assessed across baseline and the listed study visits through Week 8. The record also lists secondary outcomes covering HAM-D 17, CGI-I, HAM-A, and MADRS response and remission. The posted secondary results include response and remission outcomes. The method used to generate the random sequence, allocation concealment details, and the reason for the distinction between enrollment and analysis populations are not reported in the registry record.
The registry lists a start date of 2008-03, primary completion in 2009-02, and status as completed. The protocol’s sample-size justification and any planned interim analyses are not reported in the registry record.
4. Participant Flow and Accounting
The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.
Before assignment: This study included a washout period to allow patients to discontinue their current antidepressant medications and any additional medications prohibited by the protocol, if applicable.
Overall Study
| Stage | Vilazodone | Placebo |
|---|---|---|
| STARTED | 240 | 241 |
| Intent to Treat Population | 231 | 232 |
| Safety Population | 235 | 233 |
| COMPLETED | 193 | 195 |
| NOT COMPLETED | 47 | 46 |
Reasons for not completing this period:
| Reason | Vilazodone | Placebo |
|---|---|---|
| Adverse Event | 12 | 4 |
| Withdrawal by Subject | 11 | 11 |
| Lost to Follow-up | 17 | 17 |
| Lack of Efficacy | 3 | 7 |
| Physician Decision | 0 | 1 |
| Non-compliance | 3 | 5 |
| Other | 1 | 1 |
Analysis population for the primary outcome, as defined in the registry: Intent-to-Treat (ITT): the ITT population consisted of patients who were randomized, took at least 1 dose of study drug, and had at least 1 post-baseline efficacy endpoint 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.
| Characteristic | Unit | Vilazodone (ITT Population) | Placebo (ITT Population) | Total |
|---|---|---|---|---|
| Participants analysed | 231 | 232 | 463 | |
| Age Continuous | years | 41.1 (SD 12.22) | 42.4 (SD 12.49) | 41.7 (SD 12.36) |
| Sex: Female, Male: Female | Participants | 138 | 123 | 261 |
| Sex: Female, Male: Male | Participants | 93 | 109 | 202 |
| Region of Enrollment: United States | participants | 231 | 232 | 463 |
6. Primary Endpoint
The registry lists the primary outcome as Change From Baseline to Week 8 in the MADRS (Montgomery-Asberg Depression Rating Scale) Total Score., measured over Baseline, Week 1, Week 2, Week 4, Week 6, Week 8.
| Element | Registry entry |
|---|---|
| Result type | Least Squares Mean |
| Measure of spread | 95% Confidence Interval |
| Unit | Units on a scale |
| Endpoint classification | Continuous Endpoint |
The primary endpoint was change from baseline to Week 8 in the total score on the Montgomery-Asberg Depression Rating Scale, or MADRS. The registry describes MADRS as an observer rating scale intended to measure depression and to be sensitive to treatment effects. Its change score has a possible range of -60 to 60, and negative values represent improvement in depression symptom severity.
The endpoint is expressed as a least-squares mean change, with a 95% confidence interval. The primary comparison is the difference between the vilazodone and placebo least-squares mean changes. This provides an estimate of the between-group contrast while accounting for the model used in the reported analysis. A confidence interval communicates the statistical uncertainty around that estimate; it does not establish whether a difference is important to patients.
Measurements were listed at baseline and Week 1, Week 2, Week 4, Week 6, and Week 8. The record says last observation carried forward was used for participants who discontinued prematurely. The clinical threshold, if any, for judging a particular MADRS difference as meaningful is not reported in the registry record.
7. Why No Re-analysis Is Shown
8. Statistical Interpretation
The reported least-squares mean change was -13.3 in the vilazodone group and -10.8 in the placebo group. Both estimates were negative, corresponding to improvement in symptom severity under the scale’s stated direction. The reported between-group difference in least-squares mean change was -2.5, with a 95% confidence interval from -4.4 to -0.6 and p = 0.009. The interval does not include zero, so the posted analysis is statistically inconsistent with no between-group difference at the conventional 0.05 level. This is a statement about the result’s statistical precision, not about clinical importance.
The individual arm confidence intervals were -15.1 to -11.5 for vilazodone and -12.6 to -9.1 for placebo. The primary comparison should be interpreted using the reported between-group estimate and its interval, rather than by comparing the two arm intervals informally. The analysis used ANCOVA, and the registry reports least-squares means rather than raw arithmetic means.
The posted secondary outcomes include MADRS response and remission. For response, the registry’s reported risk difference was 0.134, with a 95% confidence interval from 0.047 to 0.221 and p = 0.002. For remission, the reported risk difference was 0.069, with a 95% confidence interval from -0.008 to 0.147 and p = 0.066. The response interval excludes zero, whereas the remission interval includes zero. These secondary findings provide additional outcome-specific information, but their interpretation depends on how the outcomes were defined and on whether multiplicity was addressed; those details are not reported in the registry record.
The posted results therefore show a statistically detectable difference in the primary continuous endpoint and a less consistent pattern across the reported secondary outcomes. They do not by themselves establish the practical importance of the difference, explain how missing outcomes may have affected it, or address unreported analysis choices. The registry does not provide a clinical-importance threshold for the primary endpoint.
9. Statistical Methods Explained
The primary result comes from a comparison of least-squares mean changes in MADRS total score. Least-squares means are model-based estimates. They can differ from simple averages because they are obtained from a statistical model rather than by taking the unadjusted mean of the observed scores. The registry identifies ANCOVA as the method for the primary comparison, but the covariates and full model specification are not reported in the registry record.
What does the confidence interval express?
A confidence interval describes uncertainty around an estimated effect under the assumptions of the analysis. In general, a narrower interval indicates greater precision, while a wider interval indicates more uncertainty. For the primary contrast, the reported estimate is -2.5 and the 95% confidence interval runs from -4.4 to -0.6. Because this interval does not include zero, it is consistent with a difference between the groups under the reported model. The interval does not show the probability that the true effect lies within its limits, and it does not indicate whether the effect is clinically important.
How should the p-value be read?
In general, a p-value describes how compatible the observed data are with a specified null hypothesis under the statistical model. It is not the probability that the null hypothesis is true, nor does it measure the size or importance of an effect. The registry reports p = 0.009 for the primary comparison. This should be read alongside the effect estimate and confidence interval rather than on its own.
What does the analysis population mean?
The primary endpoint used the intent-to-treat population as defined in the record: randomized participants who took at least 1 dose and had at least 1 post-baseline efficacy endpoint measurement. This definition excludes randomized participants without a post-baseline efficacy measurement, so it is not a strict analysis of every randomized participant. The safety population was distinct and included 235 participants receiving vilazodone and 233 receiving placebo. The registry does not explain the participant-level reasons for the population counts.
How does last observation carried forward matter?
The record states that last observation carried forward was used for participants who discontinued prematurely. Under this approach, a participant’s most recent observed value is carried forward to represent a later measurement that is missing. In general, this method can make assumptions about how outcomes behave after discontinuation and can understate uncertainty if those assumptions are not appropriate. The registry does not report the extent of missing data, the reasons for discontinuation, or sensitivity analyses using alternative missing-data methods.
How should secondary comparisons be considered?
The registry reports Cochran-Mantel-Haenszel analyses for the binary MADRS response and remission outcomes, with risk differences and confidence intervals. A risk difference expresses the difference between the proportions meeting an outcome in the two groups. For these outcomes, the registry also contains simple unadjusted recalculations. Such recalculations are not substitutes for the sponsor’s reported analyses; when the two differ, the sponsor’s own analysis takes precedence. The registry record does not report a multiplicity adjustment for secondary outcomes, so separate p-values should not automatically be treated as confirmatory evidence.
What do the planning illustrations mean?
The sample-size illustrations are planning scenarios based on fractions of the observed effect, equal allocation between groups, a two-sided significance level of 0.05, and a normal approximation. For non-time-to-event outcomes, the estimates are participants per arm for 80% power or participants per arm for 90% power under those assumptions. They are not the trial’s documented sample-size rationale and are not observed power. The protocol’s planning assumptions and sample-size justification are not reported in the registry record.
In general, planning from an observed effect is uncertain because an effect estimated in a completed trial can be imprecise and may not recur at the same size. Planning illustrations are therefore best understood as conditional scenarios, not promises about the results of a future study.
10. Analyses Reported by the Sponsor
| Method | Estimate | 95% CI | P-value |
|---|---|---|---|
| ANCOVA | Difference in Least Squares Mean Change -2.5 | -4.4 to -0.6 | 0.009 |
The sponsor-reported primary analysis used ANCOVA and gave a difference in least-squares mean change of -2.5, with a 95% confidence interval from -4.4 to -0.6 and p = 0.009. The posted primary result is internally aligned across its estimate, interval, and p-value; the registry record does not flag a discrepancy. The sponsor’s reported analysis is the primary source for interpreting this endpoint.
For the binary secondary outcomes, the registry reports Cochran-Mantel-Haenszel analyses. Simple unadjusted recalculations from the posted counts can differ from those reported analyses because the calculations do not reproduce all features of the sponsor’s method. The response recalculation has p = 0.003, compared with the reported p = 0.002; the remission recalculation has p = 0.081, compared with the reported p = 0.066. The reported analyses take precedence over these unadjusted recalculations.
These comparisons do not establish why the estimates or p-values differ, and the full analysis specifications are not reported in the registry record. The recalculations should be treated as checks based on posted summary statistics, not as replacements for the sponsor’s analyses.
11. Multiplicity, Missing Data and Analysis Populations
The primary analysis population was the intent-to-treat population as defined in the registry: randomized participants who took at least 1 dose and had at least 1 post-baseline efficacy endpoint measurement. This definition requires an observed post-baseline efficacy measurement, so it does not include every randomized participant by definition. The safety analyses used a separate population, with 235 participants in the vilazodone group and 233 in the placebo group.
The primary endpoint used last observation carried forward for participants who discontinued prematurely. In general, carrying the last observed score forward assumes that it is a suitable substitute for the unobserved later outcome. If outcomes would have changed after the last observation, this assumption may affect the estimated treatment contrast. The registry record does not report how many outcomes were missing, reasons for missingness, or sensitivity analyses that test alternative assumptions.
The record lists six outcome measures and six analyses, including the primary and secondary measures. It does not report a multiplicity correction, a hierarchy for testing outcomes, or which secondary tests were intended to be confirmatory. Without that information, the reported secondary p-values should not be interpreted as if each test were the sole planned hypothesis. The primary endpoint remains the clearest focal comparison in the posted results, but the record does not establish how the full family of outcomes was controlled statistically.
The registry record also does not report the randomization sequence method, allocation concealment, detailed covariates in the primary ANCOVA model, or the handling of missing data for every secondary outcome. It does not provide the protocol’s sample-size justification or describe interim analyses. These omissions prevent a complete assessment of prespecification and robustness, even though the main endpoint analysis and several key population definitions are reported.
12. Safety Results
The registry reports serious adverse events as affected participants divided by participants at risk.
| Arm | Participants with serious adverse events | Participants at risk | Percentage |
|---|---|---|---|
| Vilazodone (Safety Population) | 4 | 235 | 1.7% |
| Placebo (Safety Population) | 2 | 233 | 0.9% |
Other (non-serious) adverse events
Participants with at least one non-serious event at or above the registry's 5% reporting threshold.
| Arm | Participants affected of at risk |
|---|---|
| Vilazodone (Safety Population) | 148 of 235 |
| Placebo (Safety Population) | 85 of 233 |
Most frequent serious adverse event terms
| Event term | Organ system | Vilazodone (Safety Population) | Placebo (Safety Population) |
|---|---|---|---|
| Angina pectoris | Cardiac disorders | 1 of 235 | 0 of 233 |
| Ankle fracture | Injury, poisoning and procedural complications | 0 of 235 | 1 of 233 |
| Asthma | Respiratory, thoracic and mediastinal disorders | 0 of 235 | 1 of 233 |
| Carotid arteriosclerosis | Nervous system disorders | 1 of 235 | 0 of 233 |
| Chest pain | General disorders | 1 of 235 | 0 of 233 |
| Cholecystitis | Hepatobiliary disorders | 1 of 235 | 0 of 233 |
| Pneumonia | Infections and infestations | 1 of 235 | 0 of 233 |
Most frequent non-serious adverse event terms
| Event term | Organ system | Vilazodone (Safety Population) | Placebo (Safety Population) |
|---|---|---|---|
| Diarrhea | Gastrointestinal disorders | 72 of 235 | 25 of 233 |
| Nausea | Gastrointestinal disorders | 61 of 235 | 13 of 233 |
| Headache | Nervous system disorders | 30 of 235 | 24 of 233 |
| Dizziness | Nervous system disorders | 21 of 235 | 9 of 233 |
| Dry Mouth | Gastrointestinal disorders | 21 of 235 | 9 of 233 |
| Upper Respiratory Infections | Infections and infestations | 8 of 235 | 21 of 233 |
| Insomnia | Psychiatric disorders | 17 of 235 | 7 of 233 |
| Abnormal Dreams | Psychiatric disorders | 14 of 235 | 4 of 233 |
| Vomiting | Gastrointestinal disorders | 12 of 235 | 1 of 233 |
Serious events with the highest arm-level rate: ankle fracture (0.4%), asthma (0.4%), angina pectoris (0.4%), carotid arteriosclerosis (0.4%), chest pain (0.4%).
The safety population included 235 participants in the vilazodone group and 233 in the placebo group. The registry lists serious adverse events affecting 4 participants in the vilazodone group and 2 in the placebo group. It also lists other adverse events affecting 148 and 85 participants, respectively. These are counts in the recorded safety groups, not evidence on their own that a treatment caused an event or that the groups differed reliably.
The serious adverse-event terms listed include ankle fracture, asthma, angina pectoris, carotid arteriosclerosis, chest pain, and cholecystitis, each recorded as 0.4%. The registry summary does not identify an arm for each listed term in this record, so those terms should not be attributed to a particular group from these details alone. Death counts are not reported in the registry record.
Safety counts are descriptive and depend on how events were collected and coded. The registry does not provide event-level timing, duration, severity beyond serious status, or a statistical comparison for the listed adverse events. These figures therefore describe what was posted for the safety populations but do not, by themselves, establish comparative safety.
13. What the Result Does, and Does Not, Mean
The primary result is an estimate of the average difference between groups in change in MADRS total score through Week 8 under the reported ANCOVA analysis. The negative contrast indicates a larger mean reduction in score in the vilazodone group than in the placebo group, consistent with the scale’s definition that negative change reflects improvement. Its confidence interval indicates statistical uncertainty around that estimated contrast.
Statistical evidence of a between-group difference is not the same as evidence that the difference is clinically important. The registry record does not report a threshold for meaningful change on MADRS, nor does it provide patient-level distributions that would show how responses varied within each group. The average estimate cannot establish that every participant experienced the same outcome.
The result also does not establish whether the difference would persist beyond the listed follow-up, apply to populations beyond those enrolled, or be reproduced in another trial. The registry describes an 8-week study in adults with major depressive disorder, and no longer-term outcomes are reported in the record. The biomarker objective is described, but biomarker results are not reported in the registry record.
Secondary outcomes and adverse-event counts provide additional context, but they do not replace the primary comparison. The registry does not report enough detail about multiplicity, missing-data sensitivity analyses, or the full analysis plan to resolve every uncertainty in the statistical interpretation. The result should therefore be read as the specific estimate from the posted population, endpoint, time period, and analysis—not as a universal conclusion about treatment effects.
These findings are a statistical description of a trial record, not medical advice. They do not determine what treatment is appropriate for any individual.
14. Why This Trial Matters Statistically
This trial illustrates why an endpoint’s direction and scale definition matter. Here, negative MADRS change represents improvement, so interpreting the sign of the between-group contrast depends on reading that definition before considering the estimate. The primary result is reported as a model-based difference in least-squares mean change, rather than as a simple comparison of raw group averages.
It also demonstrates the value of reading an estimate with its confidence interval. The primary contrast is reported with an interval that excludes zero, while the secondary outcomes do not have a uniformly conclusive pattern. That distinction helps separate the main endpoint finding from evidence across multiple related outcomes, especially when the registry does not describe a multiplicity strategy.
The record makes analysis populations and missing-data handling visible. The intent-to-treat definition requires a post-baseline measurement, and last observation carried forward was used for premature discontinuations. These details are important because a headline estimate is conditional on who was analyzed and how unobserved outcomes were handled. The absence of missingness summaries and sensitivity analyses limits how fully that result can be stress-tested.
Finally, planning illustrations based on observed effects are not the same as the trial’s own sample-size rationale or a measure of its observed power. Keeping design planning, model-based inference, and clinical interpretation distinct helps avoid claims that the registry result cannot support. This record offers a useful example of how a statistically significant primary estimate can coexist with uncertainty about clinical importance, secondary testing, and robustness to analysis assumptions.
15. Limitations
- The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
- Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.
Several trial-specific details needed for a full statistical appraisal are not reported in the registry record. These include the method used to generate the random sequence, allocation concealment, the complete ANCOVA specification, and the protocol’s sample-size justification. The record also does not describe interim analyses or state whether secondary outcomes were governed by a prespecified testing hierarchy.
The primary analysis used last observation carried forward for participants who discontinued prematurely, but the number of such participants, the reasons for discontinuation, and the amount of missing outcome data are not reported. No sensitivity analyses using alternative missing-data assumptions are reported. The primary analysis population also required at least 1 post-baseline efficacy measurement, so its definition does not encompass all randomized participants.
The registry lists response and remission outcomes but does not report their threshold definitions. Numerical findings for several other listed secondary measures are not reported in the registry record. Consequently, the degree of consistency across the full set of clinical measures cannot be assessed from the posted results.
The study’s duration was 8 weeks, and the record does not report longer-term outcomes. The biomarker objective appears in the trial description, but biomarker results are not reported in the registry record. The record does not provide a threshold for interpreting the clinical importance of the MADRS difference. These limits constrain judgments about durability, biomarker findings, clinical meaning, and the robustness of the estimate; they do not change the numerical result reported for the primary analysis.
16. Related Tutorials
17. Related Statistical Calculators
18. Sources
- ClinicalTrials.gov: Randomized, Double-Blind, Placebo Controlled Study of Vilazodone's Efficacy, Safety, and Biomarkers of Response in Major Depressive Disorder (MDD) — NCT00683592.
- Registry record last updated 2010-10-27; status last verified 2010-10.
- Results first posted 2010-10-27.
- 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.
Continue through the Clinical Biostats statistical pathway
Use this trial's endpoint as a starting point for deeper study of effect measures, confidence intervals, and sample-size planning.
19. Record Summary
This completed phase 3 study randomized adults with major depressive disorder to vilazodone 40 mg once daily or placebo in a parallel-group, multicenter, 8-week trial. The registry records quadruple masking and enrollment of 481 participants.
The primary endpoint was change from baseline to Week 8 in MADRS total score. The reported least-squares mean difference was -2.5, with a 95% confidence interval from -4.4 to -0.6 and p = 0.009. The primary analysis used ANCOVA and the intent-to-treat population defined in the registry.
The record also lists secondary symptom, response, remission, and safety outcomes. It states that last observation carried forward was used for premature discontinuations. Details on multiplicity, the sample-size rationale, interim analyses, several secondary results, and biomarker results are not reported in the registry record.