Double-Blind Treatment of Major Depressive Disorder With Vilazodone: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Double-Blind Treatment of Major Depressive Disorder With Vilazodone (NCT01742832), a randomized phase 2 study. The primary outcome is Montgomery-Åsberg Depression Rating Scale (MADRS).

2. Clinical Question

The study focuses on people for whom a generic SSRI had not been a satisfactory option because of partial response or inability to tolerate it. Its stated purpose was to evaluate vilazodone against citalopram and to assess whether vilazodone reduced depression symptoms more than a generic SSRI. Citalopram is the named comparison drug in the trial record.

The primary outcome is the Montgomery-Åsberg Depression Rating Scale (MADRS), a continuous symptom score. The record specifies baseline and final assessments during the double-blind phase, using the final last-observation assessment. It does not give the numerical MADRS results, an estimated between-treatment contrast, or a confidence interval. Therefore, the registry record does not establish the size or precision of any difference between the treatment strategies.

The record describes the study as randomized, triple-masked, and crossover. However, it does not describe the treatment sequences or provide a single numerical comparison. The clinical question can be stated from the registered treatments and endpoint, but the result of that question cannot be quantified from the registry record.

3. Trial Design

This is a phase 2 randomized trial of vilazodone and citalopram in major depressive disorder. The registry record lists a crossover model and triple masking. It records enrollment of 79 and a completed status. The study start is listed as 2013-05 and primary completion as 2016-03. The sponsor is the University of Chicago.

The target population was people with major depressive disorder following partial response to or inability to tolerate a generic SSRI. The registry’s brief description frames the study as a comparison of vilazodone with citalopram. The vilazodone regimen is described as a fixed-dose titration: 10mg/day for 1 week, 20mg/day for 1 week, and then 40mg/day. For the citalopram group, the stated dose was to be maximized to 40mg/day. For participants assigned to vilazodone, the record describes maintaining citalopram at 20mg/day for 1 week, reducing it to 10mg/day for 1 week, and then switching to vilazodone 10mg/day.

The registered crossover label indicates that the design involved treatment periods in some form, but the treatment sequence, period structure, washout arrangements, and handling of possible period or carryover effects are not reported in the registry record. The arm descriptions alone do not supply those details. The record also does not say which roles were masked, despite describing masking as triple.

The trial description states that the entire study would last 18 weeks, with visits every 2 weeks during the first 6 weeks, weekly during the next 4 weeks, every 2 weeks during the next 6 weeks, and a final visit 2 weeks later. MADRS was administered at 11 visits, but only baseline and final last-observation assessments were used for the registered outcome. The actual number contributing to each treatment-period analysis is not reported in the registry record, and the enrollment figure should not be interpreted as a treatment-arm count.

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: The results reported are for the double-blind phase, not the open label citalopram phase of the study.

Overall Study

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 Montgomery-Åsberg Depression Rating Scale (MADRS), measured over Baseline and final MADRS scores during the double-blind phase..

The primary endpoint is the Montgomery-Åsberg Depression Rating Scale (MADRS), a measure of depressive symptom severity. The registry record describes scores ranging from 0-60, with higher scores indicating greater severity. No subscales were used. The outcome is specified as a mean with standard deviation, so it is treated as a continuous measure rather than as a count or a time-to-event outcome.

The registered timeframe is baseline and final MADRS scores during the double-blind phase. Although the study description says MADRS was administered at 11 visits, only baseline and final assessments, with the final assessment defined as the last observation, were used in determining the reported outcome. This endpoint therefore concerns change or difference in symptom scores across those assessment points, rather than every visit’s score.

As a general measurement principle, a continuous symptom scale can retain information about the degree of severity instead of reducing people to a small number of response categories. A mean describes the group’s central score, while a standard deviation describes how spread out individual scores are around that mean. Neither statistic alone describes the full distribution or uncertainty in a treatment comparison.

The registry record does not report the baseline or final MADRS means, standard deviations, treatment contrast, confidence interval, or p-value. It also does not provide a clinical threshold for interpreting a change in score. The endpoint is defined, but its numerical findings and clinical magnitude are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registered endpoint is continuous: MADRS scores are summarized as means and standard deviations. The record specifies baseline and final values, with the final value defined as the last observation. No numerical means, standard deviations, treatment contrast, or inferential statistics are reported in the registry record. The statistical concepts below explain how such quantities are generally read; they do not identify methods used in this trial unless the record explicitly says so.

What does a mean describe?

As a general concept, a mean is an average that locates the center of a set of measurements. For a symptom scale, it gives a compact summary of the group’s scores, but it does not show whether individual scores cluster near the mean or are widely dispersed. A standard deviation is a measure of that dispersion. The mean and standard deviation together provide more context than either alone, but they do not reveal the full score distribution, and they do not by themselves establish a difference between treatments.

For a treatment comparison, an estimate of the contrast is typically more directly relevant than separate group means. Its interpretation depends on the definition of the contrast, the population analyzed, and the statistical model. The record does not report such an estimate. It also does not state whether the primary comparison was based on final scores, change from baseline, or another summary, beyond identifying baseline and final last-observation assessments as the outcome values used.

How should uncertainty be understood?

As a general explanation, a confidence interval expresses uncertainty around an estimated quantity under the assumptions of the method used. A narrower interval indicates greater precision for that estimate; a wider interval indicates less precision. Whether an interval includes a particular reference value can be informative for a defined hypothesis, but it is not a measure of clinical importance. The registry record provides no confidence interval for MADRS, so the precision of the primary comparison cannot be assessed from this record.

A p-value, in general, describes how compatible observed data are with a specified null model, assuming the model and analysis are appropriate. It is not the probability that the null hypothesis is true, and it does not measure the size of an effect. No primary-outcome p-value is reported in the registry record. Therefore, neither statistical significance nor its absence can be inferred from the endpoint description or enrollment figure.

Why does the crossover label matter?

In general, a crossover study has participants receive treatments in a sequence, allowing comparisons that may use measurements from more than one treatment period. The analysis must account for the design’s repeated observations and may need to consider period effects, treatment sequence, and carryover from an earlier treatment. These are design-specific considerations, not claims about what occurred in this trial. The registry record labels the model as crossover, but treatment order, periods, washout, and the analysis of these factors are not reported in the registry record.

Because observations from the same participant may be related, treating them as independent when they are not can misstate uncertainty. General methods for repeated or paired measurements account for this dependence. Which method was used for the MADRS comparison is not reported in the registry record. It is therefore not possible to assess whether the analysis matched the crossover structure or to reproduce the analysis from the registered description.

What do the design labels establish?

Randomized allocation indicates that assignment was intended to use randomization, but the method for generating or concealing the allocation is not reported in the registry record. Triple masking indicates a masking designation, but the record does not identify the three roles or explain how masking was maintained. These labels are relevant design information, but they do not establish that every participant completed each treatment period or that outcome data were complete.

The record’s description of MADRS administration across 11 visits and use of baseline and final last-observation values raises a distinction between scheduled measurements and the values used for the outcome. Last observation carried forward is a general approach in which an earlier recorded value may stand in for a later missing value. The registry description calls the final assessment the last observation, but it does not explain whether or how missing observations were carried forward, how missingness was defined, or whether sensitivity analyses were conducted. The specific missing-data procedure is not reported in the registry record.

How should planning figures be read?

General sample-size planning asks how many participants per arm might be needed to detect a prespecified effect under stated assumptions. Such figures are planning illustrations, not results observed in a trial and not observed power. The registry’s planning description refers to a two-sided significance level of 0.05, equal allocation, a normal approximation, and effects defined as fractions of an observed effect. Those assumptions do not describe the trial’s original design justification. The original sample-size rationale and any protocol-based calculation are not reported in the registry record. In a crossover study, a generic equal-allocation illustration may also fail to capture the dependence between repeated treatment measurements unless the design and model are incorporated.

More generally, analyses based on posted summary statistics can differ from a sponsor’s or trial team’s prespecified analysis because they may not account for covariates, repeated measures, missingness, stratification, or the crossover structure. No recalculated primary comparison is reported in the registry record, and there is no basis to substitute an unadjusted calculation for a study-specific analysis. Where trial-level analysis details are absent, the appropriate conclusion is that the registry does not report them, not that a particular method was or was not used.

10. Multiplicity, Missing Data and Analysis Populations

The outcome description includes MADRS measurements at baseline and final, while the study narrative describes administration at 11 visits. The registry record says that only baseline and final last-observation assessments were used for the outcome, and the outcome note indicates that multiple categories or time points were not reduced to one comparison. A single numerical primary-outcome contrast is not reported in the registry record.

Multiplicity arises in general when several outcomes, time points, treatment comparisons, or subgroups are tested. Conducting multiple tests can increase the chance of at least one apparently unusual result if no adjustment or prespecified hierarchy is used. Whether multiplicity adjustments, a testing hierarchy, or other controls were planned or applied is not reported in the registry record. The number of analyses listed in the record does not by itself establish what was tested or how multiplicity was handled.

Missing-data handling is also not described in enough detail to evaluate. The outcome uses a final last-observation assessment, but the registry record does not explain the rule for participants without a final scheduled measurement, the amount or pattern of missing data, or any sensitivity analysis. The term last observation identifies the stated endpoint value; it does not, on its own, establish a complete missing-data method.

The registry record does not identify the analysis population, such as whether the primary analysis included all randomized participants or another defined group. It also does not report exclusions, adherence requirements, or the number contributing to each outcome analysis. These omissions limit assessment of how the randomized design was carried into the analysis. No assumptions about the analysis population or missing-data approach can be made from the outcome definition alone.

11. 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 0% reporting threshold.

Most frequent non-serious adverse event terms

The registry records serious adverse events for the vilazodone group as 0 among 19 at risk and for the citalopram group as 0 among 23 at risk. For other adverse events, the figures are 3 among 19 at risk for vilazodone and 1 among 23 at risk for citalopram. These are the recorded counts and denominators; they are not a complete account of all possible adverse events.

The serious-event terms list is empty, so the types of serious events are not reported in the registry record. Death counts are also not reported in the registry record. The other-event counts are not accompanied by event terms in the available record, so their clinical descriptions and severity are not available. The number at risk is specific to the adverse-event reporting entry and should not be treated as the denominator for the MADRS analysis.

As a general statistical point, small event counts provide limited information about event rates and comparative safety. A count of zero in a group does not establish that an event cannot occur, and differences in observed counts alone do not establish a treatment-related difference. The registry record does not report uncertainty intervals or a formal statistical comparison for these safety figures. They should be read as descriptive registry entries, not as definitive evidence of safety equivalence or of a causal effect.

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

The registry record establishes that a phase 2 randomized, triple-masked crossover study was completed and that its primary measure was MADRS, assessed at baseline and final during the double-blind phase. It also describes vilazodone and citalopram regimens and identifies a population with major depressive disorder following partial response to or inability to tolerate a generic SSRI. These details define the clinical and measurement context of the study.

The record does not report numerical MADRS outcomes or a treatment-effect estimate. It therefore does not show the magnitude or direction of the primary comparison, how precise any estimate was, or whether a statistical test met a chosen threshold. The result cannot be characterized as favoring either treatment from the registry information stated. Nor can a conclusion about clinical importance be drawn without the scores, contrast, uncertainty, and an appropriate clinical interpretation threshold.

As a general principle, statistical evidence and clinical meaning are related but different. An estimate can be precise yet small, or potentially meaningful but imprecise. The endpoint range and direction provide scale context, but they cannot replace the missing observed values. Similarly, the completed status and enrollment figure do not establish that the outcome data were complete or that the analysis included everyone enrolled.

The adverse-event entries show recorded counts for serious and other events, but do not provide event descriptions for serious events, death counts, uncertainty estimates, or a comparative safety analysis. They are not enough to establish that the treatments have the same safety profile or that one is safer than the other.

Consequently, the most defensible reading is descriptive: the registry specifies the population, treatment strategies, design labels, and primary endpoint, while leaving key outcome estimates and analysis details unreported. Any stronger efficacy, safety, or equivalence claim would require information not reported in the registry record.

13. Why This Trial Matters Statistically

This study is statistically notable because its registry combines a crossover design label with a primary outcome defined using baseline and final MADRS assessments. In a crossover study, the relationship between repeated measurements and the order of treatments can matter to both the estimated contrast and its uncertainty. A clear account of sequences, periods, and analysis methods is therefore important for evaluating whether the statistical analysis reflects the design. Those details are not reported in the registry record.

The endpoint is a continuous symptom scale, summarized as a mean and standard deviation. That representation can communicate average severity and variability, but interpreting a comparative result would require the treatment contrast and its uncertainty. The registry record does not report those primary-outcome quantities. This illustrates why an endpoint definition and a completed trial status are not substitutes for transparent results.

The record also distinguishes scheduled measurement from analysis measurement: MADRS was administered at 11 visits, while baseline and final last-observation assessments were used. For statistical interpretation, it is useful to know how intermediate observations, missing final values, and repeated measurements were handled. The registry record does not supply that information. Without it, readers cannot assess the role of missing data or whether alternative analyses were considered.

Finally, the trial highlights the difference between a planning illustration and a trial’s original design rationale. General sample-size calculations depend on assumptions about the target effect, allocation, and statistical model. The record’s planning description is not evidence of the trial’s original sample-size justification, which is not reported in the registry record. Clear separation of design assumptions, observed results, and analysis methods is essential for interpreting clinical research without overstating what the data establish.

14. Limitations

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

Several trial-specific details needed to evaluate the primary comparison are not reported in the registry record. Although the model is labeled crossover, the treatment sequences, period structure, washout arrangements, and handling of possible carryover or period effects are not described. The arm descriptions provide dosing and switching information but do not resolve these design questions.

The primary endpoint is defined, but numerical MADRS results are absent. The record gives no baseline or final group means, standard deviations, treatment contrast, confidence interval, or p-value. It also does not describe the precise estimand or clarify whether the comparison concerned final scores, change from baseline, or another summary. The outcome note indicates that multiple categories or time points were not reduced to one comparison.

The record does not report the analysis population, outcome-specific participant counts, missing-data procedures, or sensitivity analyses. Although the final assessment is described as the last observation, the handling of unavailable scheduled measurements is not explained. It is also not reported whether the analysis accounted for repeated observations in a way appropriate to the crossover design.

Randomized allocation and triple masking are recorded, but the randomization procedure, allocation concealment, and identities of the masked roles are not reported in the registry record. The entry does not provide enough detail to judge implementation or potential sources of bias. The record’s enrollment figure does not establish how many participants contributed to each treatment-period analysis.

For safety, serious-event terms are not listed, deaths are not reported, and the other-event counts lack event descriptions. No formal comparative safety analysis is reported. Together, these gaps mean that the registry record supports a description of the trial design and measurement plan, but a full evaluation of efficacy, precision, missingness, and safety is not possible from the reported information.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Double-Blind Treatment of Major Depressive Disorder With Vilazodone — NCT01742832.
• Registry record last updated 2023-02-23; status last verified 2023-02.
• Results first posted 2017-05-30.
• 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.

18. Record Summary

NCT01742832 is a completed phase 2 randomized, triple-masked crossover study sponsored by the University of Chicago. It concerns vilazodone and citalopram for major depressive disorder following partial response to or inability to tolerate a generic SSRI. Enrollment is recorded as 79; the study start is 2013-05 and primary completion is 2016-03.

The primary outcome is mean MADRS score with standard deviation, using baseline and final last-observation assessments during the double-blind phase. Scores range from 0-60, with higher scores indicating greater severity. The registry record does not report numerical primary-outcome results or a treatment comparison. It also does not report the analysis population, detailed crossover analysis, or missing-data methods.

Recorded serious adverse events were 0 among 19 at risk for vilazodone and 0 among 23 at risk for citalopram. Other adverse events were 3 among 19 and 1 among 23, respectively. Serious-event terms and death counts are not reported in the registry record.