Vilazodone Treatment for Marijuana Dependence: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Vilazodone Treatment for Marijuana Dependence (NCT01574183), a randomized phase 2 study. The primary outcome is Percent Marijuana-negative Urine Drug Screens (UDS).

2. Clinical Question

3. Trial Design

This was a phase 2, randomized, triple-masked, parallel-group trial. The registry lists enrollment as 76. Recruitment began in 2012-08, primary completion was recorded as 2015-08, and the study status is completed. The sponsor was the Medical University of South Carolina. These registry entries describe the trial structure and its recorded timeline; they do not establish how participants were recruited or how masking was implemented in practice.

The two arms were vilazodone and placebo. The vilazodone arm is listed with 41 participants and the placebo arm with 35 participants. Both are described as flexible-dose capsule regimens up to 40 mg daily. MET and CM are included in the study description as interventions intended to encourage engagement and retention. The record does not report whether adherence to the medication or behavioral components differed between groups.

A parallel design assigns participants to one treatment group rather than describing a sequence of treatments for each participant. Random allocation is intended, in general, to make treatment groups comparable on average at the time of assignment. It does not guarantee identical group characteristics, especially in a trial of this size. Triple masking indicates that the registry classifies the study as masked at three levels, but the identities of the masked parties and the procedures used to maintain masking are not reported in the registry record.

The primary outcome was assessed over 8 weeks, with participants submitting a urine sample weekly. Weekly cannabis use sessions and marijuana craving and withdrawal were listed as secondary outcomes. The registry does not report the treatment schedule in greater detail, the follow-up beyond the stated primary endpoint period, or the operational definitions and analysis methods for the secondary outcomes.

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

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 Percent Marijuana-negative Urine Drug Screens (UDS), measured over 8 weeks.

The primary endpoint was titled “Percent Marijuana-negative Urine Drug Screens (UDS).” The description says participants submitted a urine sample weekly and that the percentage of marijuana-negative urine samples was calculated per group. The stated timeframe was 8 weeks. A urine screen is an objective biological measure of whether marijuana is detected in the submitted sample; repeated weekly testing provides observations across the outcome period rather than relying only on a participant’s report of use.

In general, repeated testing can describe how often negative results occur during a defined period, but the statistical meaning depends on the precise calculation and handling of incomplete samples. The registry record does not explain whether the percentage used all scheduled samples, only submitted samples, or another denominator. It also does not report how missed or invalid samples were handled. Those details matter because percentages can change depending on which samples are counted and how missing observations are treated.

The registry gives an arm-level value of 5.5 for vilazodone and 3.6 for placebo, and identifies the unit as percentage of UDS. It does not provide a confidence interval or a test of the difference between arms. The stated primary endpoint and these arm values therefore offer descriptive information, but the record does not show how precisely the groups differed or whether the observed values represent an adjusted or unadjusted analysis.

The endpoint wording also requires care: the title refers to marijuana-negative screens, whereas the hypothesis describes reducing marijuana-positive results. These are complementary ways to frame urine-screen outcomes, but the record does not explain the precise calculation linking the stated arm values to the endpoint title.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

Statistical interpretation depends on how treatment assignment, repeated observations, and uncertainty are handled. The registry record identifies a randomized parallel-group design and an outcome based on weekly urine samples over 8 weeks. It does not report the statistical analysis plan, the model used for the repeated samples, or the method used to derive the arm-level endpoint values. The explanations below describe general statistical principles; they are not claims about methods used in this trial unless explicitly stated as registry entries.

What does randomization contribute?

In general, random assignment helps create groups that are comparable on average before treatment begins. A comparison based on assigned groups can therefore estimate the effect of assignment more fairly than a comparison based on treatment choices made by participants or clinicians. Randomization does not ensure that all characteristics are balanced in a particular trial, and it does not correct problems that arise after assignment, such as incomplete outcome collection or departures from the assigned treatment. The registry does not report the randomization sequence, allocation concealment procedures, or a participant-flow account that would clarify these issues.

Why does the outcome structure matter?

The primary outcome comes from weekly urine samples, so observations may be repeated within participants. In general, measurements from the same person can be related to one another; treating every sample as wholly independent can understate uncertainty. An analysis might instead summarize each participant’s results or use a model that accounts for within-participant correlation. The correct approach depends on the endpoint definition, available observations, and assumptions. The registry record does not report which approach was used, and the posted arm-level values do not reveal it.

The endpoint is expressed as a percentage of UDS, but the record does not state the denominator used to calculate that percentage or how it handled missing samples. A percentage based on submitted samples can differ from one based on all scheduled samples when collection is incomplete. In general, the handling of missing outcome data is part of the endpoint analysis, not a minor reporting detail. No missing-data rule or sensitivity analysis is reported in the registry record.

What does a confidence interval communicate?

General explanation: a confidence interval describes the uncertainty around an estimated effect under the statistical method used. A narrow interval indicates greater precision than a wide interval, while an interval that includes values consistent with no difference may leave the direction or size of the effect uncertain. An interval is not a guarantee that the true effect lies within its limits. The registry reports no confidence interval for the primary comparison, and no inferential interval can be reconstructed from the posted arm summaries alone without additional information about the endpoint distribution and analysis.

Why is a p-value not enough?

General explanation: a p-value measures how compatible the observed data are with a specified statistical model and null hypothesis. It does not measure the probability that the null hypothesis is true, and it does not describe the size or clinical importance of an effect. Interpretation should consider an effect estimate and its uncertainty, alongside the design and outcome definition. No p-value for the primary treatment comparison is reported in the registry record.

What is over-dispersion, and why might it matter?

General explanation: count outcomes sometimes vary more across participants than a simple statistical model expects. This extra variability is called over-dispersion. If it is ignored, standard errors can be too small and confidence intervals can be too narrow. The registry lists secondary outcomes involving weekly cannabis-use sessions, but it does not report their distributions, model choices, or any assessment of over-dispersion. It is therefore not possible to say whether that issue applied to those analyses.

How should planning calculations be read?

General explanation: sample-size planning illustrations describe how many participants might be needed under specified assumptions to detect an effect of a chosen size with a chosen level of statistical power. They are planning tools, not evidence about what the completed trial achieved. The registry’s stated illustration assumptions use a two-sided significance level of 0.05, equal allocation, and a normal approximation, with the effect to detect expressed as a stated fraction of the observed effect. For time-to-event outcomes the stated quantity is total events; for other outcomes it is participants per arm. Such illustrations are not observed power, and the record does not identify them as the trial’s original design justification.

The registry says the primary endpoint values were missing or not estimable for a two-arm comparison. Consequently, there is no reported unadjusted comparison to interpret as a recalculated treatment effect. A simple recalculation from summary statistics is not appropriate when the necessary comparison estimate and uncertainty are unavailable. The sponsor’s analysis does not take precedence on the basis of a reported discrepancy, because the registry does not flag one; however, no sponsor analysis is posted for the primary comparison.

10. Multiplicity, Missing Data and Analysis Populations

The registry names one primary outcome and two secondary outcomes: weekly cannabis use sessions, and marijuana craving and withdrawal. It does not report a statistical plan for controlling the chance of false-positive findings across multiple outcomes, time points, or analyses. Multiplicity procedures are not universal; the appropriate approach depends on which outcomes and contrasts were planned and how confirmatory claims were intended to be made. Without a prespecified hierarchy or adjustment method, results across several analyses would need cautious interpretation. The registry lists no posted analyses for the outcomes, so there are no secondary estimates to assess or compare.

Missing data are especially relevant to an endpoint built from repeated weekly urine samples. The record says participants submitted urine samples weekly, but does not report how many samples were missing, whether missingness differed between arms, or how missing samples were treated in the percentage calculation. It does not describe imputation, a complete-case analysis, or sensitivity analyses. These details are not reported in the registry record; no assumption about the missing-data mechanism is justified.

The analysis population is also not reported in the registry record. It is not stated whether the primary analysis included all randomized participants, only participants with outcome data, or another defined group. The registry’s arm counts are attached to the outcome summaries, but do not establish the rules used to select observations for analysis. The record also does not report how protocol deviations, treatment discontinuation, or adherence were handled.

These omissions limit interpretation of both the descriptive values and any attempt to generalize them. A prespecified outcome hierarchy, clear analysis population, explicit sample-handling rules, and sensitivity analyses would help readers understand the robustness of the results. None of these analysis details is reported in the registry record.

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 5% reporting threshold.

Most frequent non-serious adverse event terms

The registry reports serious adverse events affecting 0 participants in the vilazodone group, with 41 listed at risk, and 0 participants in the placebo group, with 35 listed at risk. These are counts of participants with serious adverse events as recorded in the registry. They should not be interpreted as proof that no serious event occurred outside the registry’s reporting scope or during unreported periods.

The record lists other adverse events affecting 25 participants in the vilazodone group and 28 in the placebo group. It does not provide the event terms, severity, timing, or attribution for these “other” events. The listed figures therefore do not identify which events occurred or whether they were judged related to treatment. The registry provides no top serious-event terms. Death counts are not reported in the registry record.

In general, adverse-event counts describe what was recorded among participants at risk; they do not by themselves establish comparative safety. A fuller assessment would consider event definitions, duration of observation, completeness of reporting, and the uncertainty around group differences. The registry does not report a statistical safety comparison or enough detail to conduct one. These safety summaries should be read as limited registry counts, not as a comprehensive account of harms.

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

The record establishes that a randomized, triple-masked, parallel-group phase 2 trial compared vilazodone with placebo in adults described as marijuana-dependent. The primary endpoint concerned marijuana-negative urine drug screens over 8 weeks, and the study description included MET and CM with both medication assignments. The registry reports arm-level primary endpoint values of 5.5 for vilazodone and 3.6 for placebo.

Those values do not, on their own, demonstrate that one assignment produced a larger or smaller outcome. The registry does not report a two-arm effect estimate, confidence interval, or p-value, and it notes that values were missing or not estimable for a two-arm comparison. The record also does not specify the denominator or missing-sample rules behind the percentage. As a result, the precision and statistical meaning of the difference between the posted arm summaries cannot be established from this record.

The results do not show whether the primary hypothesis was supported, and they do not establish a treatment effect. That is not the same as showing that there was no effect: the absence of an inferential comparison leaves the question unresolved in the registry record. Nor can the listed secondary outcomes be interpreted, because their results are not reported.

These registry data also do not determine how the findings apply beyond the participants and study conditions represented in the trial. The record does not provide detailed eligibility criteria, adherence information, or analysis-population definitions. The study summary describes a medication comparison alongside MET and CM, so the design does not isolate those behavioral components from the medication assignment.

The safest statistical conclusion is narrow: the registry documents a completed randomized trial and reports descriptive arm values for its primary endpoint, but does not post the analysis needed to quantify the between-group effect or its uncertainty. The serious adverse-event counts are likewise limited registry summaries and do not constitute a complete comparative safety analysis.

13. Why This Trial Matters Statistically

This trial illustrates why an endpoint value and a treatment comparison are not interchangeable. The registry reports a value for each arm, but does not report an effect estimate, confidence interval, or p-value, and notes that a two-arm comparison was not estimable. A reader can describe the posted summaries, but cannot infer the precision or statistical significance of a difference from those values alone.

The outcome also highlights the importance of defining the unit of analysis. Participants submitted weekly urine samples, while the primary endpoint is expressed as a percentage of UDS. Statistical interpretation depends on how repeated samples within one participant were combined or modeled, and how missing samples affected the denominator. The registry does not report these methods. Without them, it is difficult to know exactly what the group-level values represent or how much uncertainty surrounds them.

The trial’s shared behavioral components matter for the question being asked. MET and CM are described alongside both randomized medication assignments. The randomized contrast therefore concerns vilazodone versus placebo in that study context; it does not estimate the separate contribution of MET or CM. This is a design distinction, not a judgment about those interventions.

Finally, the record shows how registration entries may document a trial and its arm summaries without posting a complete statistical analysis. The missing inferential results, secondary outcome findings, and analysis details constrain conclusions even though the study is marked completed. For biostatisticians and clinical researchers, the case underscores the value of explicit endpoint definitions, transparent missing-data rules, a stated analysis population, and accessible estimates with measures of uncertainty.

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 limitations are specific to the information recorded for this trial. First, although the primary endpoint is described as the percentage of marijuana-negative urine samples, the registry does not explain the denominator, sample-level aggregation, or handling of absent or invalid samples. The weekly collection schedule makes these details important to interpreting an endpoint summarized as a group percentage.

Second, the primary arm values are not accompanied by a reported two-arm comparison. The registry says values were missing or not estimable for such a comparison. No confidence interval or p-value is reported, and the record does not explain why the comparison could not be estimated. This prevents assessment of effect size and precision from the posted results.

Third, the registry does not report the analysis population, statistical model, treatment of repeated samples, or sensitivity analyses. The allocation and masking labels describe the design, but the record does not detail implementation, adherence, or participant flow. These omissions make it difficult to evaluate how the planned design translated into the reported outcome summaries.

Fourth, the two secondary outcomes are named but their results are not reported in the registry record. The record also gives no multiplicity strategy or analysis plan. The safety information is limited to counts, without event terms for the other adverse events, attribution, or a reported death count. Finally, the study summary mentions genomic DNA collection and characterization by gene polymorphisms, but no related results are reported. These gaps limit what can be concluded from the registry record, independently of the trial’s completed status.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Vilazodone Treatment for Marijuana Dependence — NCT01574183.
• Registry record last updated 2016-08-10; status last verified 2016-07.
• Results first posted 2016-01-14.
• 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

The registry describes a completed, randomized, triple-masked, parallel-group phase 2 trial sponsored by the Medical University of South Carolina. It compares vilazodone with placebo among adults described as marijuana-dependent, with MET and CM included in the study description. Enrollment is listed as 76; the arm summaries list 41 participants for vilazodone and 35 for placebo.

The primary endpoint was the percent of marijuana-negative urine drug screens over 8 weeks, based on weekly urine samples. The posted arm values are 5.5 for vilazodone and 3.6 for placebo. A two-arm statistical comparison and its uncertainty are not reported, and the registry notes that values were missing or not estimable for such a comparison. Results for the listed secondary outcomes are not reported in the registry record. The record therefore supports a description of the trial design and posted summaries, but not an inferential conclusion about the primary treatment contrast.