HIV Prevention Toolkit for HIV-negative Male Couples: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for HIV Prevention Toolkit for HIV-negative Male Couples (NCT02494817), a randomized na study. The primary outcome is Formation of a Sexual Agreement at 6 Months.

2. Clinical Question

The study’s broader aims included assessing the toolkit and examining behaviors related to sexual agreements, condomless anal sex with casual male partners, and HIV testing. The listed secondary outcomes cover these behaviors at several time periods. These aims describe the questions of interest, not evidence that any particular behavior changed. The available registry information identifies a primary endpoint but does not give its group-specific results, an estimated treatment effect, or the uncertainty around that estimate.

3. Trial Design

The registry describes a randomized, single-masked, parallel-group study of a behavioral intervention, with a listed enrollment of 298 and a status of completed. The study is titled “HIV Prevention Toolkit for HIV-negative Male Couples.” Its primary completion is recorded as 2016-09, and its start as 2015-10. The phase is listed as NA. The registry identifies the University of Miami as sponsor.

In a parallel-group design, participants are assigned to one of the study groups and remain in that group for the study comparison. Random allocation is intended to make groups comparable on average, although it cannot guarantee that every characteristic will be balanced. The registry labels masking as single but does not identify who was masked or what masking involved. Those details are not reported in the registry record.

The intervention is described as an interactive website toolkit for male couples. The control description includes HIV prevention information, a sexual health resource center, and an app link. The registry’s arm descriptions are incomplete, so the precise content and delivery of each arm cannot be fully characterized from this record. The broader project description refers to assessing the toolkit and to a later pilot of an RCT; the available information does not establish further details about the relationship between those project phases and this registered study.

The listed primary outcome is formation of a sexual agreement at six months. Outcome data are described for 115 men in the control group and 98 men in the intervention group, with the number of couples represented also reported. These outcome-data counts are not the same as the registered enrollment figure, and the record does not explain the full flow from enrollment to outcome reporting.

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: For control, 115 men (52 dyads both partners provided data and 11 "dyads" where only one partner provided data) provided outcome data. For intervention, 98 men (45 dyads where both partners provided data and 8 "dyads" where only one partner provided data) provided outcome data. Only dyads where both partners provided data were included.

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 Formation of a Sexual Agreement at 6 Months, measured over 6 month.

The primary endpoint concerns whether participants reported forming a sexual agreement by six months. The registry describes a self-reported yes-or-no response collected through an electronic survey and expresses the outcome as a count of participants. It is a behavioral measure: it records a reported agreement, rather than a clinical event such as HIV infection.

Sexual agreements are relevant to the study’s stated focus on HIV prevention behavior among male couples. Measuring whether an agreement was formed can describe one aspect of how couples approach sexual health. It does not, by itself, establish whether an agreement was followed, whether condomless sex occurred, or whether HIV testing took place. Those topics appear among the secondary outcomes, with some assessed at different time periods.

The endpoint description identifies what was asked and when, but the registry record does not report the number or proportion of participants answering yes in either group. It also does not report a group contrast or its precision. The record notes that the primary outcome has several categories or time points and was not reduced to one comparison. Consequently, the endpoint’s definition can be explained, but a numerical effect estimate cannot be interpreted from the registry information available.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

Statistical methods determine how observed outcomes are turned into estimates and how much uncertainty should be attached to those estimates. The registry record identifies randomization, a parallel-group design, a binary self-report endpoint, and outcome-data counts. It does not report the statistical analysis plan or the methods used to analyze the primary or secondary outcomes. The explanations below describe general statistical principles, not methods confirmed as having been used in this study.

What randomization contributes

In general, randomization assigns participants to groups using a chance process. If implemented as intended, it helps avoid systematic allocation based on participant characteristics and supports a fair comparison of groups. It does not eliminate random differences between groups, loss to follow-up, measurement error, or problems caused by departures from the assigned intervention. Details about the sequence generation, concealment of assignments, and implementation are not reported in the registry record.

The registry calls this study single-masked, but does not specify which people were masked. In general, masking can reduce some forms of influence on treatment delivery, outcome assessment, or reporting, depending on who is masked and how it is implemented. A label alone is not enough to determine which biases masking could address in a particular study.

What a binary outcome means

A yes-or-no survey response is a binary outcome. For a group comparison, analysts commonly report counts and proportions answering yes, then estimate a contrast such as a difference in proportions or a relative measure. The choice should match the study question and analysis plan. The registry record describes the primary endpoint as a count of participants, but does not report group-specific yes counts, proportions, a contrast, or a statistical model. No such estimate can therefore be interpreted from this record.

A confidence interval, in general, describes the range of values reasonably compatible with the data and the statistical assumptions used to calculate it. Its width reflects precision: a wider interval indicates greater uncertainty about the estimated effect. A confidence interval is not reported for the primary endpoint in the registry record. Without an estimate and its interval, the magnitude and precision of any between-group difference cannot be assessed.

Why couples may affect the analysis

Participants are members of couples, so partners’ responses may be related. In general, observations from people in the same couple may not be statistically independent. An analysis that treats all individuals as independent when their responses are correlated can misstate uncertainty. Methods for clustered or paired data can account for this dependence, but the appropriate approach depends on the outcome and analysis question. The registry record does not report whether the primary analysis treated individuals, couples, or both as the analysis unit, or how within-couple dependence was handled.

The outcome-data description distinguishes couples where both partners provided data from couples where only one did. That distinction matters because the information available differs across couples. It does not, on its own, show how those data were used or whether the analysis included all available individual responses. Analysis populations and the handling of incomplete couple data are not reported in the registry record.

How to read tests and planning calculations

In general, a significance test evaluates how compatible data are with a specified null hypothesis under a model. A small p-value does not measure the size or importance of an effect, and a larger p-value does not establish that groups are identical. The registry record does not report a p-value or a testing procedure for the primary endpoint.

The record describes assumptions for planning illustrations: a two-sided significance level of 0.05, equal allocation between arms, a normal approximation, and effects set as stated fractions of the observed effect. These are described as illustrations computed from an observed effect, not as the trial’s own design assumptions. No illustration values are reported in the registry record. Such calculations are planning aids, not observed power and not evidence about the outcome itself. The registry does not report the original sample-size justification.

Multiple outcomes and time periods can create multiple opportunities to detect a difference. In general, a statistical plan may specify a primary comparison, secondary analyses, and a method for addressing multiplicity. Such a method can affect how results are interpreted when many hypotheses are tested. The registry record does not report a multiplicity strategy or the tests used for the listed outcomes. Accordingly, no inference about adjustment or selective reporting is warranted from the listed outcomes alone.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists a primary outcome and six secondary outcomes. The secondary outcomes address sexual agreement formation and adherence, condomless anal sex with casual male partners, and HIV testing, with some outcomes tied to different time periods. The primary outcome is also described as having several categories or time points and is not reduced to one comparison. Multiple outcomes and time points raise a general multiplicity issue: when several comparisons are examined, the chance of at least one apparently notable result can increase. Any adjustment strategy or hierarchy among outcomes is not reported in the registry record.

The primary outcome population description reports data for 115 control-group men and 98 intervention-group men, with both-partner and one-partner couple counts specified for each group. These figures show that outcome data were not described solely as complete pairs. The registry text is insufficient to determine exactly how couples with one responding partner contributed to the primary analysis. Reasons for missing outcome data, missingness by assigned group beyond these counts, and any imputation or sensitivity analysis are not reported in the registry record.

Analysis populations are also not described. In general, an analysis based on assigned groups and an analysis limited to participants with observed outcomes can answer different questions, especially when data are missing. The registry does not say whether analyses followed assignment, included all available responses, or used another population definition. The number of analyses is listed as zero, but this does not establish what analyses were performed outside the registry record. No analysis plan or multiplicity correction is reported.

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 serious adverse event summary reports zero serious events among 162 participants at risk in the control group and zero among 136 participants at risk in the intervention group. Deaths are reported as zero in both groups. The registry also gives the same group counts for participants at risk for other adverse events and reports zero affected in each group. These are event counts as recorded; they do not establish that no events occurred outside the registry’s collection or reporting procedures.

Zero recorded events should not be read as proof that the underlying risk is zero. In general, when no events are observed, the data still leave uncertainty about how often an event might occur in a broader population. The precision of a safety estimate depends on the observation period, event definition, completeness of follow-up, and analysis method. Those details, including the period covered and the methods used to collect serious adverse events, are not reported in the registry record.

The group counts alone do not provide a formal comparison, confidence interval, or account of event severity beyond the serious-event classification. They should be interpreted as descriptive safety reporting, not as a determination of comparative safety.

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

The registry record establishes that a randomized, parallel-group study of a behavioral HIV prevention toolkit was completed and identifies formation of a sexual agreement at six months as its primary outcome. It also describes the survey method and reports the number of men with outcome data by group, including how many couples had data from both partners or one partner. These details clarify the intended question and the available outcome-data structure.

The record does not report how many participants formed an agreement, the difference between groups, or uncertainty around a difference. It therefore does not show whether the outcome was more or less frequent in either group, or how precisely a group difference was estimated. The absence of results in the registry record is not evidence that the groups had the same outcome, and it is not evidence that the intervention changed the outcome.

The study’s wider aims include other behaviors, such as agreement adherence, condomless anal sex with casual male partners, and HIV testing. Those are distinct outcomes and cannot be inferred from the primary endpoint. A report of agreement formation would not establish adherence to that agreement or a change in HIV risk. The registry’s listed serious adverse event counts are also descriptive and do not settle broader questions about safety.

Interpretation is limited further because statistical methods, analysis populations, missing-data procedures, and multiplicity handling are not reported in the registry record. The study description and endpoint definition are useful for understanding what was intended to be measured, but they do not substitute for outcome estimates and their uncertainty.

13. Why This Trial Matters Statistically

This study illustrates several statistical features common in behavioral research with couples. The intervention is directed at couples, while the primary outcome is described as a count of individual participants. When partners’ experiences may be related, the choice of analysis unit and treatment of dependence matter for uncertainty. The registry describes couples with data from both partners and couples with data from one partner, making the distinction between individual-level and couple-level information especially relevant.

The outcome is self-reported through an electronic survey. In general, self-report can capture experiences or decisions that are not readily observed in other ways, but it also depends on participants’ interpretation and recall. The registry identifies the response format and timing but does not report validation information or further details about outcome measurement.

The record also illustrates why a completed study status and a clearly defined endpoint are not enough to interpret effectiveness statistically. An estimate, its uncertainty, the analysis population, and the analytic methods are needed to understand what the results say. Here, the registry identifies a set of outcomes and reports some data-completeness counts, but does not report the primary result or analyses. That distinction prevents the study’s aims from being mistaken for evidence about its outcomes.

Finally, multiple outcomes and time periods make prespecification and multiplicity methods important to interpretation. Those methods are not reported in the registry record. The record is therefore informative about study structure and measurement, while leaving key elements needed for statistical conclusions unavailable.

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 main limitation for interpreting this trial from the registry record is the lack of reported outcome results. Although the primary endpoint is defined, group-specific counts of participants reporting agreement formation and a between-group estimate are not reported. No confidence interval or test result is reported either. The study’s completed status cannot fill this gap.

The description of the primary outcome population gives outcome-data counts for each group and distinguishes couples with data from both partners from those with data from one partner. It does not explain the full flow of participants, reasons for missing data, or how one-partner couple data were incorporated. It also does not identify the analysis population or missing-data methods.

The statistical analysis plan is not reported in the registry record. In particular, the record does not describe how within-couple dependence was handled, how outcomes across multiple time periods were tested, or whether multiplicity was addressed. Masking is labeled as single, but who was masked is not specified. The intervention and control descriptions are also incomplete, limiting detailed comparison of the content delivered to each group.

The serious adverse event counts are reported as zero in both groups, but the registry does not describe event ascertainment, follow-up duration, or uncertainty. These limitations restrict conclusions about both the behavioral outcomes and the interpretation of safety reporting.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: HIV Prevention Toolkit for HIV-negative Male Couples — NCT02494817.
• Registry record last updated 2019-04-16; status last verified 2019-03.
• Results first posted 2019-04-16.
• 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, single-masked, parallel-group behavioral study of an HIV prevention toolkit for at-risk HIV-negative male couples. Enrollment is listed as 298. The primary endpoint is formation of a sexual agreement at six months, measured by a yes-or-no electronic survey. Outcome data are described for 115 control-group men and 98 intervention-group men, with couple-level response patterns also specified.

The record lists six secondary outcomes concerning sexual agreements, condomless anal sex with casual male partners, and HIV testing. It reports zero serious adverse events and zero deaths in both groups. It does not report the primary outcome result, group comparison, statistical analysis methods, or missing-data procedures. As a result, the registry record describes the study question and some design and outcome details, but does not permit interpretation of an estimated effect.