Social Network Diffusion of COVID-19 Prevention for Diverse Criminal Legal Involved Communities: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Social Network Diffusion of COVID-19 Prevention for Diverse Criminal Legal Involved Communities (NCT05500274), a randomized na study. The primary outcome is COVID-19 Testing.

2. Clinical Question

The trial addressed a prevention question in a population identified by its interaction with law enforcement. The study summary describes a goal of engaging participants in COVID-19 prevention, including testing and/or vaccination, through social-network mobilization and theory-driven messaging in an interactive group format. The posted primary outcome, however, is specifically about testing. It does not measure vaccination or a broader measure of prevention behavior.

The registry reports identical event proportions for the two arms: 1.0 in the Education Arm and 1.0 in the Motivational Arm. The estimated risk difference is 0.0, with a confidence interval from 0.0 to 0.0 and p = 1.0. These figures describe the posted outcome contrast. They do not by themselves explain how the outcome was recorded, whether testing was verified, or how missing outcome information was handled; those details are not reported in the registry record.

3. Trial Design

The registry describes a randomized, parallel, two-arm trial with no masking. Its summary characterizes the allocation as 1:1. The trial status is completed, and its phase is listed as NA. The registry lists an enrollment of 778. The study summary describes a target of 800 participants, so the enrollment field and the summary’s stated target are not the same figure.

The Education Arm received COVID-19 prevention messaging and an interactive activity intended to reinforce those messages. Its description also refers to testimonial videos about testing experiences and motivations for testing. The Motivational Arm used a social network diffusion approach, with specific training on mobilizing network members. More detailed descriptions of the interventions and their delivery are not reported in the registry record.

The registered primary outcome was the number of participants with at least one test within 3 months of baseline. The record lists the Education Arm with 378.0 participants and 378.0 outcome events, and the Motivational Arm with 400.0 participants and 400.0 outcome events. The posted comparison uses the Education Arm as the reference and reports a risk difference for the Motivational Arm.

The record gives a study start date of 2023-01-10 and a primary completion date of 2024-05-31. Information about sequence generation, allocation concealment, recruitment locations, the detailed eligibility criteria, intervention fidelity, or deviations from the intended interventions is not reported in the registry record. The statistical analysis plan, including any adjusted analyses or interim analyses, is also not reported in the registry record. The posted result therefore supports a description of the registered comparison, but does not supply the additional implementation and analysis details that would help readers evaluate how the trial was conducted.

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: A total of 1235 participants were screened, 936 were eligible, and 778 consented. Baseline surveys could be completed remotely, but intervention sessions required in-person attendance. Randomization occurred only when participants were physically present. Some participants did not attend due to scheduling conflicts and were not randomized.

Overall Study

Reasons for not completing this period:

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 COVID-19 Testing, measured over 3 months.

The primary endpoint counts participants who had at least one COVID-19 test within 3 months of baseline. It is a binary participant-level outcome: for each participant, the relevant status is whether at least one test occurred during the stated period. The registry expresses the endpoint as a count of participants with the event, rather than as a testing rate over time or the total number of tests taken.

This outcome is relevant to the study’s stated focus on COVID-19 prevention because testing was one of the prevention-related activities described in the study summary. A defined follow-up period makes the outcome interpretable as testing within a specific interval after baseline. The endpoint does not capture vaccination, the number of tests, the timing of a test within the interval, test results, or other prevention behaviors. Those outcomes are not part of the posted primary measure.

The registry reports 378.0 events among 378.0 participants in the Education Arm and 400.0 events among 400.0 participants in the Motivational Arm. These are the posted counts used for the comparison. The registry record does not report how a test was verified, whether participants self-reported testing, how incomplete follow-up was treated, or the operational rules for classifying the endpoint. Those details matter when interpreting what the event count represents in practice.

7. Results Posted in the Registry

• Motivational Arm: 100.0% (400/400) versus 100.0% (378/378) on control; risk difference 0.0 percentage points (95% CI 0.0 to 0.0), risk ratio 1.00 (1.00–1.00); unadjusted two-proportion z-test p = n/a.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary endpoint is binary at the participant level: a participant either had at least one test within 3 months of baseline or did not. For such outcomes, a group proportion describes the fraction of participants experiencing the event. A risk difference compares those proportions by subtraction. This measure is expressed on the proportion scale, so zero represents equal proportions, a positive value represents a higher event proportion in the intervention group, and a negative value represents a lower event proportion in that group.

What does the reported contrast measure?

The registry reports the risk difference for the Motivational Arm relative to the Education Arm. It gives event proportions of 1.0 and 1.0, respectively, and a risk difference of 0.0. The value describes the difference in the proportion of participants with at least one test during the defined follow-up period. It does not measure the number of tests per participant, the timing of testing, or a difference in vaccination.

For a binary endpoint, the risk difference is one possible effect measure. Other measures, such as a risk ratio or an odds ratio, describe the same comparison on different scales. The posted result gives a risk difference and also lists a ratio interval with values of 1.0, but the registry record does not report an analysis rationale for selecting a particular effect measure. With event proportions equal to 1.0, the risk difference directly states that the observed proportions match.

How should the p-value be read?

In general, a p-value assesses how compatible the observed data are with a specified null hypothesis under the statistical procedure used. It is not the probability that the null hypothesis is true, and it does not indicate the probability that the result will replicate. Here, the reported p-value is 1.0. The record does not identify the test, whether it was one-sided or two-sided, or any adjustments used in computing it. Consequently, the value should not be used to reconstruct an undocumented analysis plan.

The p-value is not a measure of effect size. The estimated risk difference and its confidence interval describe the observed contrast and its reported uncertainty, while the p-value is a test statistic’s probability under a null model. In general, interpretation of a p-value depends on the design, data quality, analysis method, and assumptions. The registry does not provide enough detail to evaluate those elements beyond the randomized, parallel design and posted outcome summary.

What does a confidence interval add?

In general, a confidence interval gives a range of effect values compatible with the data and the interval procedure. Its width is often used to describe statistical precision, but it is not a direct measure of data quality or clinical importance. The registry reports an interval from 0.0 to 0.0 for the risk difference. As both observed proportions are 1.0, there is no observed difference to place above or below zero. The interval’s zero width should not be treated as evidence that every source of uncertainty is absent, particularly because the record does not report the interval method or missing-data handling.

What is not documented about the analysis?

The registry record does not report the planned statistical model, covariate adjustment, handling of missing outcomes, analysis population, or rules for protocol deviations. It also does not report whether an interim analysis was performed. These are distinct aspects of statistical planning and conduct; none can be inferred from the point estimate or p-value. The randomized allocation identifies the comparison as a trial contrast, but details needed to reproduce or fully assess the analysis are not reported in the registry record.

General planning calculations based on an observed effect are not the same as evidence of achieved power. They are illustrations that depend on their stated assumptions and the effect chosen for planning. The registry record does not report the trial's sample-size justification or a statistical plan explaining the enrollment target. No conclusion about observed power should be drawn from the posted result.

The endpoint has no variation in the posted counts because every listed participant is recorded with the event. In general, variability in binary outcomes is important for estimating uncertainty and distinguishing event and non-event patterns. When all records fall into one category, some conventional procedures may yield boundary estimates or depend heavily on their method. The registry does not describe the procedure used, so readers should not assume a particular model, correction, or calculation method.

10. Confidence Intervals and Precision

The risk difference is reported as 0.0, with a confidence interval from 0.0 to 0.0. The interval’s endpoints coincide with the estimate, so the posted interval expresses no spread around the estimate. The accompanying proportions are 1.0 in each arm, based on outcome counts equal to the listed participant counts. These are the precision-related values recorded for the primary comparison.

In general, confidence intervals are useful because they show a range of estimates that are compatible with the data under a specified method. A narrower interval is often described as more precise than a wider interval, assuming comparable methods and data quality. But precision is not the same as validity: an interval can be narrow while depending on incomplete measurement, an unsuitable model, or unreported assumptions. The registry does not report the confidence-interval construction method, endpoint verification procedures, or handling of missing outcome information.

The zero-width interval should therefore be read in the context of the posted outcome pattern, not as a guarantee that the true effect is exactly zero. The recorded proportions show no separation, but the registry does not explain how the endpoint was collected or whether all randomized participants were included in the primary analysis. The information needed to assess alternative sources of uncertainty is not reported in the registry record.

Precision also concerns the range of effects the data can distinguish, not whether a result is important. Since the registry reports no variation in the primary endpoint, the usual intuition that a confidence interval summarizes uncertainty from observed differences is limited. The reported interval remains the registered result, but it cannot answer questions about other outcomes, populations, implementation settings, or follow-up periods.

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 2 outcome measures but posts no secondary results. The primary outcome is the count of participants with at least one test within 3 months of baseline. The record does not report a prespecified hierarchy among outcomes, a multiplicity-adjustment procedure, or whether any other outcome was tested. It is therefore not possible to assess how multiple statistical comparisons may have been handled. The primary result should be interpreted as the posted result for that endpoint, not as a complete account of all outcome analyses conducted.

Missing data can affect both the event proportions and the precision of a treatment contrast. The registry lists participant counts and outcome counts that match in each arm, but does not describe whether these figures represent everyone randomized, everyone with available follow-up, or a defined analysis population. It does not report missingness by arm, methods for imputation, or sensitivity analyses. No conclusions about completeness of outcome follow-up should be inferred from matching counts alone.

The registry record also does not identify the analysis population—for example, whether the primary analysis followed randomized assignment regardless of intervention participation—or how participants who did not receive their allocated intervention were handled. The randomization and parallel-group design are reported, but analysis-population rules and protocol-deviation handling are not. These details can affect interpretation of a randomized comparison.

Interim analyses, stopping rules, and any prespecified statistical analysis plan are not reported in the registry record. Without those details, readers cannot assess whether the posted test reflects all planned analyses or whether the analysis was changed during the study. This absence does not establish that such procedures were or were not used; it means the registry record does not report them.

12. 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 safety record reports zero serious adverse events in the Education Arm and zero in the Motivational Arm. It also reports zero other adverse events and zero deaths in each arm. The listed at-risk counts are 378 for the Education Arm and 400 for the Motivational Arm. These are the safety counts recorded in the registry.

These figures are event counts, not an estimate of comparative safety risk with uncertainty. A zero count means that no events of the listed category were reported in the record; it does not establish that no event occurred outside the recorded safety system or that the interventions have no safety risks. The registry record does not describe adverse-event definitions, collection procedures, observation periods, severity grading beyond the serious category, or how relatedness to an intervention was assessed.

Safety counts should also be kept distinct from the primary outcome. The primary result concerns COVID-19 testing within 3 months of baseline, whereas the safety fields concern serious events, other adverse events, and deaths. No serious adverse event terms are listed. The available counts alone do not permit broader conclusions about the nature, timing, or ascertainment of safety events.

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

The result means that the registry reports the same primary endpoint proportion in both randomized arms. The Education Arm has 378.0 participants recorded with at least one test among 378.0 listed, and the Motivational Arm has 400.0 recorded with the event among 400.0 listed. The reported risk difference is 0.0, its confidence interval runs from 0.0 to 0.0, and the p-value is 1.0. This is the numerical result for the registered testing endpoint.

It does not establish that the interventions are equivalent or that their effects are identical in the wider population. A non-difference in the observed proportions is not, by itself, an equivalence finding. The registry does not report an equivalence margin, a noninferiority framework, or the analysis details needed to support such a claim. The posted confidence interval also cannot be interpreted as eliminating all uncertainty about the underlying effect, especially given the absence of reported information about endpoint ascertainment and missing data.

The result does not address whether either intervention changed vaccination, testing frequency, test timing, test results, or other health behaviors. Although the study summary mentions COVID-19 prevention efforts involving testing and/or vaccination, the posted primary endpoint is limited to whether a participant had at least one test within 3 months of baseline. No secondary results are posted in the registry record.

Nor does the result explain why every listed participant in both arms is recorded with the event. The data could reflect the outcome as collected and coded, but the registry does not report the process behind the counts. Interpretation should remain anchored to the recorded endpoint rather than presuming a particular explanation for the universal event counts.

Finally, the trial's completed status and randomized design describe important features of the study, but they do not resolve limitations in the reporting. A result can be reported precisely as recorded while remaining limited in what it can support. The registry record supports a direct account of the posted comparison; broader claims about effectiveness, mechanism, or outcomes outside this endpoint are not supported by this result alone.

14. Why This Trial Matters Statistically

This trial is statistically notable because its primary outcome is binary, yet the posted data record the event for every participant listed in both arms. That pattern yields identical proportions and a risk difference of 0.0. It is a useful reminder that an effect estimate, a p-value, and a confidence interval must be interpreted alongside the underlying event counts and the way an outcome is defined.

For researchers, a binary endpoint such as having at least one test is not interchangeable with a count of tests or a measure of testing over time. The endpoint’s definition determines what the comparison can answer. Here, the outcome addresses whether testing occurred within a specified period, not how often participants tested or whether they received a vaccine. Clear distinctions between an intervention’s broad aims and the registered endpoint help prevent overinterpretation.

The study also illustrates why reporting of analysis details matters. The registry identifies randomized parallel groups and posts a risk difference, confidence interval, and p-value, but does not report the statistical test, missing-data strategy, or analysis populations. These details help readers understand how uncertainty was quantified and which participants contributed to the comparison. Their absence limits independent appraisal even when the reported values are straightforward.

Finally, a zero-width interval can look exceptionally precise. In general, however, an interval must be interpreted with its method and data context. Identical event proportions arising from all participants being recorded with the event are not the same informational situation as a result supported by a broad range of event and non-event observations. The endpoint counts and the limits of the registry reporting are central to statistical interpretation.

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.

The registry record offers limited detail on the population beyond describing people who had interacted with law enforcement and focusing on diverse criminal legal involved communities. Eligibility criteria, recruitment settings, participant characteristics, and the extent to which the enrolled group reflects other settings are not reported. This restricts assessment of how broadly the result might apply.

Intervention descriptions are incomplete. The Education Arm is described as prevention messaging with an interactive activity and testimonial videos, while the Motivational Arm uses social-network diffusion and training to mobilize network members. Further information about intervention content, delivery, adherence, exposure, and fidelity is not reported in the registry record. The extent to which the arms differed in contact or other features cannot be assessed from the descriptions alone.

The primary endpoint is narrowly defined as at least one test within 3 months of baseline. Measurement and verification procedures are not reported. The posted counts equal the listed participant counts in both arms, but the record does not explain the outcome ascertainment process or the handling of missing information. This is especially relevant to interpreting an outcome recorded for every listed participant.

Statistical limitations include the absence of a reported analysis plan, test method, missing-data strategy, analysis population, adjustment approach, and multiplicity procedure. The record also does not report an explanation for the sample-size target or interim analysis details. These omissions limit assessment of whether the posted analysis followed a prespecified plan and how robust the result is to alternative analytical choices.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Social Network Diffusion of COVID-19 Prevention for Diverse Criminal Legal Involved Communities — NCT05500274.
• Registry record last updated 2025-05-18; status last verified 2025-05.
• Results first posted 2024-10-01.
• 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.

19. Record Summary

The registry describes a completed, randomized, parallel, two-arm trial with no masking, comparing an Education Arm with a Motivational Arm. Enrollment is listed as 778, while the study summary describes a target of 800. The primary outcome is the number of participants with at least one test within 3 months of baseline.

The posted outcome counts are 378.0 of 378.0 in the Education Arm and 400.0 of 400.0 in the Motivational Arm. The estimated risk difference is 0.0, with a confidence interval from 0.0 to 0.0 and p = 1.0. The registry also reports zero serious adverse events, zero other adverse events, and zero deaths in each arm.

The record does not report the statistical analysis plan, missing-data handling, analysis populations, or details of outcome verification. No secondary outcome results are posted. The result therefore describes the recorded primary endpoint comparison, with important methodological details not reported in the registry record.