Couples Health Project: Couples-based Intervention to Reduce Drug Use and HIV Transmission Risk: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Couples Health Project: Couples-based Intervention to Reduce Drug Use and HIV Transmission Risk (NCT03386110), a randomized na study. The primary outcome is Illicit Drug Use.

2. Clinical Question

The trial is framed as a test of feasibility, acceptability, and preliminary efficacy. Its primary outcome is the self-reported number of illicit drug use instances, not including marijuana, during the past 30 days. That makes the question about reported frequency of use over a specified recall period, rather than a clinical diagnosis or a measure of HIV transmission itself. Sexual HIV transmission risk is part of the intervention’s stated focus, but it is not the listed primary endpoint.

The comparison is randomized and parallel: couples are allocated to CHP or the education control, and the two intervention approaches are delivered over the same stated schedule. The registry record identifies the outcome population as intent-to-treat and names baseline and follow-up assessment times. However, it does not report numerical outcome summaries, an estimated between-group effect, or uncertainty around that effect. The clinical question can therefore be described from the record, but the comparative result cannot be quantified from the reported information.

3. Trial Design

This is a completed, randomized, parallel-group trial with no masking reported. The registry record lists enrollment as 100 and describes a randomized controlled trial involving 50 couples. It also describes 25 couples allocated to CHP and 25 couples allocated to Education. These are the record’s stated enrollment and allocation details; they do not supply participant flow or outcome-specific analysis counts.

The intervention arm received the Couples Health Project, described as a three-session couples-based Motivational Interviewing intervention. Sessions were scheduled once a week for three weeks and delivered by MI-trained mental health counselors. The comparator was an attention-matched Education intervention, also delivered over three weekly sessions, by trained health educators. This design contrasts the CHP approach with an active educational control rather than with no intervention.

The listed primary outcome is continuous: the mean number of self-reported illicit drug use instances, excluding marijuana, in the past 30 days. The assessment schedule includes baseline, 3-month follow-up, and 6-month follow-up. The registry record identifies the population for this outcome as intent-to-treat, assigned to CHP or Education Control. It does not state how the repeated measurements were modeled or which time-point contrast was designated as the primary comparison in the analysis.

The project’s stated purpose includes feasibility, acceptability, and preliminary efficacy. The trial is marked completed, with a start date of 2018-03-06 and a primary completion date of 2020-09-14. The phase is listed as NA. The registry record does not report a formal sample-size justification, a detailed randomization procedure, or a statistical analysis plan. The planned allocation described in the arm summaries should not be mistaken for evidence that all allocated couples completed follow-up or contributed outcome data; participant flow and completeness of outcome measurement 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.

Overall Study

Analysis population for the primary outcome, as defined in the registry: Intent-to-treat population (assigned to either the CHP intervention or Education Control)

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 Illicit Drug Use, measured over Baseline, 3-month follow-up; 6-month follow-up.

The primary endpoint is the self-reported number of illicit drug use instances, excluding marijuana, during the past 30 days. It is assessed at baseline, 3-month follow-up, and 6-month follow-up. The registry record describes the measure as a mean with standard deviation and identifies the population as intent-to-treat, assigned to either the CHP intervention or Education Control.

A continuous count of reported use instances can describe the frequency of behavior over the stated recall period. Repeated assessments can also describe how that reported frequency changes over follow-up, provided the analysis specifies how observations at different times are compared. Baseline measurement can characterize participants before follow-up, while later measurements address the post-assignment period. Those are general reasons such an endpoint and schedule can be informative; the registry record does not report a rationale for selecting this endpoint or the assessment times.

The outcome is self-reported, so it represents participants’ reports rather than an independently verified count. It excludes marijuana, which is listed separately among the secondary outcomes as Marijuana Use. The measure does not directly quantify sexual HIV transmission risk, nor does its definition establish a particular clinical threshold. No group means, standard deviations, changes, or between-group estimates for the primary endpoint are reported in the registry record. Consequently, the endpoint’s definition is available, but its observed values and comparative result are not.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does a mean and standard deviation describe?

For a continuous measure, the mean describes the average observed value in a group, while the standard deviation describes how spread out individual values are around that average. In this trial, the outcome is the self-reported number of illicit drug use instances, excluding marijuana, in the past 30 days. A mean would summarize the reported frequency across participants with outcome data at a specified assessment. A standard deviation would show how much those reports vary among participants. These summaries answer different questions: the mean concerns the group’s average, while the standard deviation concerns variation within that group.

The registry record specifies mean and standard deviation as the parameter and dispersion for the primary outcome. It does not report their values by group or assessment. Those summaries alone would not necessarily establish an intervention effect: comparing groups requires a defined contrast, and interpretation also depends on uncertainty and the analysis population.

Why do repeated assessments need a stated comparison?

The primary measure is scheduled at baseline, 3-month follow-up, and 6-month follow-up. Repeated measurement allows outcomes to be described over time, but it creates more than one possible statistical question. An analysis might compare assigned groups at a particular follow-up, compare changes from baseline, or estimate a pattern across all assessment times. These approaches are not interchangeable. A clear interpretation needs to identify which contrast is being estimated and how the repeated observations are handled.

The registry record notes that the primary outcome has several categories or time points and is not reduced to one comparison. It does not report a specific repeated-measures model, the primary time-point contrast, or an estimated result. No particular model should therefore be attributed to the trial on the basis of the information in the record.

How should an effect estimate and confidence interval be read?

In general, an effect estimate expresses the size and direction of a contrast, such as a difference between assigned groups under a specified analysis. A confidence interval communicates the statistical uncertainty around that estimate. A narrower interval indicates greater precision under the model and assumptions used; a wider interval indicates less precision. The interval is not a guarantee that the true value lies within its limits, and it does not by itself establish practical importance.

The registry record does not report a primary-outcome effect estimate or confidence interval. It is therefore not possible to describe the estimated direction, magnitude, or precision of a difference between CHP and Education. A p-value, if reported, would address compatibility of the observed data with a specified null model, not the size or practical importance of an effect. No primary-outcome p-value is reported in the registry record.

Why can outcome distributions matter?

General statistical consideration: methods based on a normal approximation may be less suitable when an outcome has a strongly skewed distribution, many zero values, or variability that changes with its mean. Counts of reported instances can have those features, but the registry record does not report the observed distribution for this endpoint. This is not a claim about the trial’s data. Analysts may examine the outcome distribution and model assumptions before choosing an estimation method. If the data show over-dispersion—variation greater than a chosen model expects—standard errors and resulting uncertainty estimates can be misleading unless the analysis accounts for it. No distributional diagnostics or modeling choices are reported in the registry record.

What does the sample-size planning description mean?

The sample-size assumptions describe a planning illustration computed from the observed effect, not the trial’s own design. The stated assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, a normal approximation, and an effect to detect expressed as a stated fraction of the observed effect. For non-time-to-event outcomes, the planning results are expressed as participants per arm. This is a planning exercise, not observed power and not evidence that the trial was designed or enrolled to detect a particular effect. The registry record does not report the trial’s sample-size justification. The numerical planning results are not reported in the registry record.

In general, planning estimates depend on the effect size, variability, allocation, significance level, and assumptions used. They do not predict that a trial will find a statistically significant result. Retrospective calculations based on an observed effect also inherit uncertainty in that effect; they should not be interpreted as a measure of what the completed trial was capable of detecting. Any such illustration is distinct from the outcome analysis itself.

What can randomization support?

General statistical consideration: random allocation is intended to make assigned groups comparable on average, including with respect to factors that were not measured. It does not guarantee identical groups in a particular trial, especially when the study is modest in size. An intent-to-treat analysis generally preserves the randomized assignment comparison by analyzing participants according to their assigned group, regardless of intervention receipt. The registry record labels the primary outcome population intent-to-treat and identifies assignment to CHP or Education Control, but it does not describe the operational rules used for missing observations or deviations from assigned intervention.

The trial is listed as randomized and parallel, with masking listed as none. Randomization and masking are different design features: randomization concerns assignment, while masking concerns whether participants or study personnel know the assigned intervention. The record’s masking entry does not identify which individuals, if any, were unmasked beyond the listed designation. The randomization method and allocation concealment are not reported in the registry record.

10. Multiplicity, Missing Data and Analysis Populations

The registry record lists three outcome measures and 12 analyses. The primary outcome is measured at baseline, 3-month follow-up, and 6-month follow-up, and the record notes that it has several categories or time points rather than one reduced comparison. Multiple outcomes, assessment times, or analysis choices can create multiple opportunities to observe a statistically unusual result. General statistical consideration: when many hypotheses are tested, the chance of at least one small p-value can increase unless the analysis plan addresses multiplicity. The registry record does not report a multiplicity adjustment, a hierarchy of outcomes, or which contrasts were confirmatory.

Missing-data methods are not reported in the registry record. There is no reported account of how many participants contributed primary outcome data at each assessment, how missing observations were handled, or whether any sensitivity analyses examined the effect of missingness. The listed enrollment and planned arm allocations do not establish how many participants completed follow-up or were included in each outcome analysis.

The primary outcome population is described as intent-to-treat, assigned to either CHP or Education Control. This identifies the intended assignment-based population, but it does not explain how an intent-to-treat analysis was implemented when outcomes were unavailable. The record also does not report a statistical analysis plan or the assumptions used to address missing observations. As a result, the extent to which missingness or analysis choices could affect the estimate cannot be assessed from the registry record.

These omissions do not show that the trial failed to use appropriate methods; they mean those methods are not reported in the registry record. Interpreting a primary comparison requires the analysis definition, the available data by assessment, and the treatment of missing observations and multiple comparisons.

11. 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 0% reporting threshold.

The registry record lists serious adverse events, other adverse events, and deaths by arm. For Couples Health Project (CHP), the listed at-risk count is 56, with zero serious adverse events, zero other adverse events, and zero deaths. For Education, the listed at-risk count is 44, also with zero serious adverse events, zero other adverse events, and zero deaths. These are the recorded figures; the arm-specific at-risk counts are not the same as the planned allocation of 25 couples per arm, and the record does not explain the relationship between these counts and participant flow.

A zero count means no events in that category were recorded in the registry entry. It does not establish that participants experienced no symptoms or other health concerns, nor does it show that every possible event was collected or reported. The registry record does not provide serious-event terms, and the list of top serious terms is empty. It also does not describe the event-collection method, observation period for safety reporting, or criteria used to classify events.

These counts should therefore be read as limited descriptive safety information, not as a complete assessment of risk or as evidence comparing the interventions’ safety. The absence of reported event counts in these categories cannot establish that the interventions are free of harm.

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

The record describes a randomized comparison between a three-session couples-based Motivational Interviewing intervention and an attention-matched education control. It defines the primary endpoint as self-reported illicit drug use instances, excluding marijuana, in the past 30 days, with assessment at baseline, 3-month follow-up, and 6-month follow-up. It also identifies the primary outcome population as intent-to-treat. These details clarify what the trial set out to compare.

They do not establish what happened to the primary outcome. The registry record does not report group means, standard deviations, changes over time, an intervention-versus-control estimate, a confidence interval, or a p-value for illicit drug use. Without those results, it is not possible to state whether the groups differed, how large any difference was, or how precisely it was estimated. The completed status and the stated aims of feasibility, acceptability, and preliminary efficacy do not fill that gap.

The posted safety counts show zero recorded serious adverse events, other adverse events, and deaths in each listed arm. These entries are limited to the categories and counts reported; they do not demonstrate the absence of all adverse experiences or establish comparative safety.

General statistical interpretation distinguishes statistical evidence from clinical importance. Even when an estimate and uncertainty are available, the numerical result needs to be interpreted in light of the outcome definition, study design, data completeness, and the question the analysis answers. Here, the registry record does not provide the primary effect estimate or the analytical detail needed for that assessment. No conclusion that CHP does or does not change drug use is supported by the reported primary-outcome information. Nor does the outcome definition itself establish a change in sexual HIV transmission risk, which is part of the intervention’s stated focus but is not the listed primary endpoint.

13. Why This Trial Matters Statistically

This trial raises several statistical issues that are important in couples-based behavioral research. The intervention is delivered to couples, and the registry record describes allocation in couples. Outcomes are described for an intent-to-treat population assigned to intervention arms, but the record does not state whether outcomes were analyzed at the individual or couple level, or whether dependence between partners was accounted for. General statistical consideration: observations from partners in the same couple may be correlated. If an analysis treats correlated observations as independent when they are not, its uncertainty estimates can be affected. The registry record does not report how this issue was handled.

The primary outcome is a self-reported count over a defined recall period and is assessed repeatedly. General statistical consideration: count outcomes may have distributions that differ from the assumptions of simple continuous-outcome methods, and repeated observations from the same participant are not independent. The record gives the intended summary as a mean and standard deviation but does not report the model, distributional checks, or handling of within-person dependence. Those details matter when evaluating whether an estimate and its uncertainty are well supported.

The project’s stated aims include feasibility, acceptability, and preliminary efficacy. These are related but distinct questions. A trial can examine whether an intervention can be delivered and accepted while also estimating an outcome contrast; the evidence needed for each aim differs. The record does not report numerical feasibility or acceptability findings, and it does not provide the primary comparative estimate. This makes transparent reporting particularly important: readers need results and methods to judge what the trial contributes.

Finally, multiple outcomes and assessment times raise the need to identify the intended comparisons. The record lists three outcome measures and 12 analyses, but does not report how multiplicity was addressed or which contrasts were designated as primary. These features do not invalidate the trial; they identify information needed to assess the strength and scope of its statistical conclusions.

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.

The most direct limitation for interpreting the primary outcome is that the registry record does not report numerical results. There are no group summaries, between-group estimates, confidence intervals, or p-values for the primary measure. The direction and magnitude of any difference, and its precision, therefore cannot be assessed. The record also notes multiple categories or time points without reducing the primary outcome to one comparison, leaving the intended primary contrast unclear.

Important analysis details are not reported in the registry record. These include a statistical analysis plan, the method used for repeated measurements, the handling of missing outcome data, the participant counts contributing data at each assessment, and any adjustment for multiple outcomes or analyses. The record does not state whether the possible dependence between partners in a couple was incorporated into the analysis. It also does not report the randomization procedure or allocation concealment.

The primary measure relies on self-report and uses a past-30-day recall period. As a general limitation, self-reported behavior can be affected by recall and reporting, but the registry record does not establish whether or how those concerns affected these data. The record does not provide distributional summaries or diagnostics that would clarify how well a particular statistical model fits the continuous count measure.

Safety interpretation is also limited: recorded event counts are available, but event-collection details, observation periods, and classification methods are not reported in the registry record. In addition, the record’s enrollment figure and planned allocation details do not provide a participant-flow account or outcome-specific analysis denominators. These gaps constrain interpretation without establishing that any particular bias or methodological problem occurred.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Couples Health Project: Couples-based Intervention to Reduce Drug Use and HIV Transmission Risk — NCT03386110.
• Registry record last updated 2021-08-19; status last verified 2021-07.
• Results first posted 2021-08-19.
• 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 record describes NCT03386110, a completed randomized, parallel-group trial of the Couples Health Project (CHP) versus an attention-matched Education control. It lists enrollment as 100 and describes 50 couples, with 25 couples allocated to each arm. Both interventions consist of three weekly sessions. The trial’s stated aims are feasibility, acceptability, and preliminary efficacy among partnered HIV-negative YMSM ages 18–29.

The primary outcome is the mean self-reported number of illicit drug use instances, excluding marijuana, in the past 30 days, assessed at baseline, 3-month follow-up, and 6-month follow-up. The record identifies an intent-to-treat population but does not report the primary outcome results or the analysis details needed to interpret a comparative effect. It lists zero serious adverse events, zero other adverse events, and zero deaths in each arm. Those counts are descriptive and do not establish the absence of all adverse experiences.