Peer Support Dyads in Churches: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Peer Support Dyads in Churches (NCT03463941), a na na study. The primary outcome is Feasibility as Measured by Retention.

2. Clinical Question

The study’s stated purpose is to explore how working with a partner may influence participation in a church wellness program, and to learn what African American men and women think about working with a support partner. Its focus is therefore on feasibility and participant experience, rather than a randomized comparison of health outcomes between peer support and an alternative intervention.

The registry also lists goal attainment measures involving BMI, weight, fruit and vegetable consumption, and exercise. Those are secondary outcomes; their numerical results are not reported in the registry record. The available information does not establish whether participants achieved their goals or whether any change was attributable to peer support. Without a comparator and reported outcome values, the clinical question is best understood as exploratory: can a peer-support approach be studied in this church wellness context, and what does participant continuation look like?

3. Trial Design

NCT03463941, titled “Peer Support Dyads in Churches,” is recorded as completed. Duke University is listed as the sponsor. The study start date is 2019-01-05, and the primary completion date is 2019-07-31. The registry lists enrollment of 80 and describes the model as single group. Its phase and allocation are recorded as NA, and masking is listed as none.

The intervention is named Peer Support Dyad Intervention and is classified as behavioral. The group description identifies African American church members. The study concerns peer support within a health promotion program in African American churches, with the stated interest in how participants experience working with a partner toward health goals. The registry does not report the specific program schedule, the process for pairing participants, or details of intervention delivery.

The primary outcome is feasibility measured by retention, with a timeframe from baseline to week 18. The defined population comprises participants completing Phase I, meaning those with >50% attendance. Retention is to be calculated from the number who continue to Phase II relative to that Phase I population, alongside an attrition rate. The actual retention and attrition values are not reported in the registry record.

The registry lists four secondary outcome topics: goal attainment measured by BMI, weight in pounds, consumption of 7 or more fruits and vegetables per day, and days per week with at least 30 minutes of exercise. The listed conditions include peer support and chronic disease, obesity, type II diabetes, cardiovascular disease, and cancer. These condition labels describe the registry record; they do not show that participants had each condition or that the intervention changed disease risk.

Because this is a single-group study, it does not supply a randomized concurrent control comparison. The record does not report a protocol-level sample-size justification, interim analyses, or a detailed statistical analysis plan.

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: Participants who completed Phase I (\>50% attendance).

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 Feasibility as Measured by Retention, measured over Baseline to week 18.

The primary endpoint is feasibility measured by retention. The registry defines its population as participants who completed Phase I, which requires >50% attendance. Retention is based on how many of those participants continue to Phase II; the description also identifies attrition rate as part of the assessment. The endpoint timeframe is baseline to week 18.

Retention is useful in a feasibility study because continuation indicates whether participants remain engaged as the program proceeds. It can help describe the practical reach of an intervention and identify whether follow-up through a later program phase is possible. This is a general explanation of the role of retention as a feasibility measure; it does not establish what continuation means for health outcomes or whether a particular retention level is adequate in this study.

The threshold for completing Phase I is part of the registry’s endpoint definition. It determines who is counted in the stated retention population, so the endpoint is not simply a count of all enrolled participants. The registry record does not report the number meeting the Phase I attendance criterion, the number continuing to Phase II, or the attrition rate. It also does not explain how participants who stopped attending or had incomplete follow-up were handled in the analysis. As a result, the endpoint’s definition can be described, but its observed value and precision cannot be assessed.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does a single-group design allow?

The registry classifies this study as single group and identifies no comparator. General explanation: a single-group design can describe participant characteristics, attendance, continuation, and outcomes observed during a program. If measurements are taken over time, it may also describe change within the enrolled group when those measurements are available. It does not by itself show what would have happened to the same participants without the intervention. A concurrent comparison group can help address that question, but no such group is identified in this record.

This distinction limits interpretation of the secondary goal-attainment outcomes. Even if a change were reported, a single-group result would not isolate the contribution of peer support from other experiences or influences. Here, the numerical outcome results are not reported, so even a description of observed change is unavailable.

How should retention be understood?

The registry defines retention as a feasibility outcome from baseline to week 18. Its stated population consists of people who completed Phase I by attending >50% of sessions. Retention is based on continuation to Phase II among that group, and the description also refers to attrition. General explanation: retention summarizes continuation through a study or program, while attrition describes participants who do not continue under the defined rules. Those measures depend on the population and continuation criteria chosen. They should not be interpreted without knowing how many participants were eligible for the calculation and how incomplete follow-up was handled.

The record does not report the number who met the attendance threshold, continued to Phase II, or were counted as attrition. It also does not describe the handling of participants with unknown continuation status. Thus, the endpoint definition is available, but its estimate and precision are not.

What does an uncertainty interval mean?

General explanation: a confidence interval describes uncertainty around an estimate under the assumptions of the statistical method used. A relatively narrow interval indicates greater precision than a wider interval, but neither an interval nor a point estimate resolves limitations in design, measurement, or missing follow-up. The registry record does not report a retention estimate or confidence interval, so precision for the primary endpoint cannot be assessed from the available information.

What do the listed analyses establish?

The record lists 7 outcome measures and 6 analyses. Those counts indicate that several measures and analyses are represented in the registry, but they do not identify the statistical model, adjustment variables, testing procedure, or analysis population for each result. Those details are not reported in the registry record. The measures include the primary retention outcome and secondary goal-attainment topics, but the exact mapping between every analysis and outcome is not given in the record summarized for this study.

General explanation: an analysis plan specifies how outcomes are translated into estimates, which participants are included, and how uncertainty is quantified. For counts, the relevant denominator and definition of an event are essential to interpretation. For measurements such as BMI and weight, the timing of measurements and method for handling incomplete observations also matter. Without those details and the outcome values, it is not possible to reconstruct or evaluate the analyses.

Why does multiplicity matter?

General explanation: when multiple outcomes or statistical tests are examined, the chance of at least one apparently notable result can increase if each is interpreted independently. Researchers may address this through a prespecified hierarchy, adjustment, or cautious interpretation of exploratory analyses. The registry record lists multiple outcomes and analyses, but whether the study used a multiplicity strategy is not reported. No claims about statistical significance or confirmatory status can be made from the outcome list alone.

How should planning calculations be read?

The described sample-size illustrations are planning illustrations, not the trial’s own design. Their stated assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation, with the effect to detect expressed as a stated fraction of the observed effect. The record says that non-time-to-event illustrations report participants per arm and that time-to-event illustrations report total events. These assumptions describe hypothetical planning comparisons; they do not change the study’s recorded single-group design or create a comparator that was not used.

General explanation: a planning calculation estimates the sample size associated with specified assumptions. It is not observed power and does not demonstrate that an actual study detected an effect. The assumptions must match the intended design and outcome. In this case, the stated equal-allocation, two-arm framework is not a description of the single-group study design. The numerical planning results and the observed effects on which they are based are not reported in the registry record summarized for this study, so no particular sample-size value or effect estimate can be interpreted.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("African American Church Members")
n      <- c(65)
events <- c(62)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  African American Church Members  65  62  95.4  87.1  99.0  87.3  98.4  87.3  98.3

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 7 outcome measures and 6 analyses. It names the primary outcome as retention and identifies secondary outcomes involving BMI, weight, fruit and vegetable consumption, and exercise. The record does not state whether the analyses were prespecified in a protocol, how the six analyses correspond to the listed measures, or whether a hierarchy or multiplicity adjustment was used. The numerical results and test statistics are not reported in the registry record.

General explanation: assessing multiple outcomes can create a risk of overinterpreting an isolated finding when many results are examined. A prespecified outcome hierarchy or statistical adjustment can help clarify which findings are intended as primary and how uncertainty should be interpreted. Without those details, no claim about multiplicity control or the evidential status of any secondary result is warranted.

The registry defines the population for the primary retention outcome as Phase I completers with >50% attendance. It does not report how many enrolled participants met that criterion, the number who continued, or the way missing continuation status was handled. For the secondary outcomes, the analysis populations and missing-data procedures are not reported in the registry record. The record also does not specify whether all enrolled participants contributed to each outcome or whether analyses used a different eligible subset.

These omissions matter because denominators, missing observations, and analysis populations affect the interpretation of both counts and changes in measurements. The endpoint definitions alone do not establish how incomplete records were treated. No imputation method, sensitivity analysis, or missing-data assumption is reported in the registry record.

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 registry lists the African American Church Members group with 80 participants at risk for serious adverse events and 80 at risk for other adverse events. It records 0 serious adverse events, 0 other adverse events, and 0 deaths. No serious adverse event terms are listed.

These figures describe the events recorded in the registry, rather than proving that no event occurred. General explanation: safety counts depend on how events are defined, collected, and reported, as well as the period and population covered. The record does not provide further details about ascertainment, event definitions, or the completeness of follow-up. The counts also do not provide a comparison with an untreated or alternative-treatment group, since the study is recorded as single group.

Accordingly, the registry supports the statement that no serious adverse events, other adverse events, or deaths were recorded in the listed group. It does not support a broader conclusion about safety beyond those recorded counts and the information documented in the registry.

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

The record describes a completed study of a behavioral peer-support dyad intervention among African American church members, with enrollment of 80 and a single-group design. Its primary focus is feasibility measured by retention from baseline to week 18. The registry defines the retention population as participants completing Phase I with >50% attendance, and describes continuation to Phase II and attrition as the basis for that assessment.

The primary outcome’s observed value is not reported in the registry record. The number of Phase I completers, the number who continued to Phase II, and the attrition rate are also not reported. The secondary outcome topics are listed, but their results are not reported either. Therefore, the record does not establish how well participants were retained, whether goal attainment changed, or how precisely any such outcome was estimated.

The study’s single-group design is important to what can be inferred. General explanation: observed outcomes in one group do not by themselves provide the counterfactual comparison needed to attribute an outcome to an intervention. The record identifies no randomized control group, so it cannot support a comparative estimate of peer support versus another condition.

The safety entries report 0 serious adverse events, 0 other adverse events, and 0 deaths among 80 listed at risk. Those counts are appropriately read as registry-recorded events, with the limits of event ascertainment and reporting unspecified. They do not demonstrate the absence of all possible harms.

The study is relevant as an investigation of peer support in a church wellness context and as a feasibility-oriented design. Its registry information documents the question, population, intervention label, endpoint definition, and recorded safety counts. It does not provide the outcome results needed to judge retention or goal attainment, or a comparative design capable of estimating an intervention effect.

14. Why This Trial Matters Statistically

This study raises a statistical question that is distinct from whether an intervention changes health outcomes: can a peer-support approach be implemented and can participants continue through the program? Retention is the primary outcome, and the registry makes the attendance threshold and Phase II continuation criterion explicit. Clear endpoint definitions matter because they determine which participants count in a feasibility estimate and what continuation means.

The design also illustrates why the study question and the statistical comparison need to align. A single-group study can describe participation and outcomes within the group. It cannot supply a randomized contrast against a control condition, and so it cannot isolate the effect of peer support from other influences. This is a general design principle, not a claim that a particular alternative design was planned.

Another statistical issue is the distinction between having an outcome listed and having an interpretable result. The registry names retention and several goal-attainment measures, but does not report their numerical results. Without estimates and information about analysis populations or missing data, the reader cannot assess the size, precision, or completeness of those outcomes.

The record also lists multiple outcome measures and analyses, while leaving the multiplicity approach unreported. That makes it important not to assign confirmatory meaning to unreported findings or to presume how analyses were handled. The safety counts are similarly bounded: they communicate the entries recorded, not the completeness of event ascertainment.

Overall, the statistical importance of the record lies in its feasibility focus and in the limits of what its design and reported information can answer. The endpoint definition is informative, but without its observed result, and without a comparator, the registry record cannot establish retention performance or an intervention effect.

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 principal limitation for interpreting this record is that it does not report the primary retention result. Although the endpoint definition specifies the Phase I attendance criterion, Phase II continuation, attrition, and timeframe, the counts needed to describe retention are not reported. No estimate of precision is available.

The registry lists secondary goal-attainment outcomes, but it does not report their numerical results. Consequently, there is no basis in this record for describing changes in BMI, weight, fruit and vegetable consumption, or exercise. The record also does not specify the timing or analytic handling of these secondary measures beyond their listed names.

The single-group design and absence of a comparator limit causal interpretation. Even if within-group outcome changes were reported, the study would not provide a randomized comparison to distinguish intervention effects from other influences. The registry does not report additional design details that would support a stronger causal interpretation.

Further information about the statistical procedures is not reported in the registry record. This includes analysis populations for outcomes other than the defined primary population, missing-data handling, multiplicity procedures, and a protocol-level sample-size justification. The record lists 6 analyses, but does not specify their methods or mapping to outcomes.

Finally, the safety entries record 0 serious adverse events, 0 other adverse events, and 0 deaths, but event ascertainment and reporting completeness are not described. These limitations do not negate the study’s stated exploratory purpose; they define what can be concluded from its registry information.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Peer Support Dyads in Churches — NCT03463941.
• Registry record last updated 2020-09-02; status last verified 2020-08.
• Results first posted 2020-09-02.
• 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

NCT03463941 is a completed, single-group study sponsored by Duke University, with enrollment of 80 and no masking. It examines a behavioral peer-support dyad intervention in African American church members in a church wellness program. The primary endpoint is feasibility measured by retention from baseline to week 18 among Phase I completers with >50% attendance.

The registry lists secondary goal-attainment outcomes for BMI, weight, fruit and vegetable consumption, and exercise. It records 0 serious adverse events, 0 other adverse events, and 0 deaths among 80 listed at risk. Numerical results for retention and the secondary outcomes are not reported in the registry record. The single-group design does not provide a randomized comparator, and details of missing-data and multiplicity procedures are not reported.