Online Family Dyadic Skills Training for Black Adults in Behavioral Weight Loss Program: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Online Family Dyadic Skills Training for Black Adults in Behavioral Weight Loss Program (NCT05981508), a randomized na study. The primary outcome is Change in Body Weight.

2. Clinical Question

The study’s stated purpose was to test the feasibility and acceptability of an interactive, counselor-led online family skills training as part of a behavioral weight loss program for Black adults. The registry record also lists changes in BMI, eating self-regulation and self-efficacy, social support, family communication, and family cohesion among the secondary outcomes. The posted body-weight results describe change within each arm; they do not report a statistical estimate or test of the difference between arms. Consequently, the record can describe the observed group summaries but does not establish whether the arms differed beyond the variation reflected in those summaries.

3. Trial Design

The registry record describes a randomized, parallel-group study with no masking. It lists the study as completed and records enrollment of 21. The study start date is 2024-02-05, and primary completion is dated 2024-08-30. The phase is listed as NA. The sponsor is the University of North Carolina, Chapel Hill.

Participants were assigned to online or in-person family skills training. In both arms, the index partner was to participate in the intervention as a dyad with a family member; the difference stated in the arm descriptions is whether the skills training was online or in person. Both interventions are categorized as behavioral. The registry record does not describe allocation concealment, the sequence-generation method, or any additional masking procedures.

The primary outcome is change in body weight in kg, measured on a digital scale and recorded as a continuous variable. The stated measurement timeframe is baseline and 12 weeks. The reported primary-outcome summaries include 11 participants in the in-person arm and 8 in the online arm. These are the counts reported for this measure and should not be treated as a description of every participant enrolled or of the family members involved in dyads.

The study was framed around feasibility and acceptability, rather than only a between-arm weight comparison. The registry’s brief summary states that purpose, while the posted primary outcome supplies descriptive body-weight results. The registry record does not report a formal feasibility threshold, acceptance criterion, or decision rule for judging whether the online format met a prespecified standard. It also does not explain the rationale for the enrollment target or provide a statistical design plan that would clarify the intended precision of the weight estimates.

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: This was a dyad based study in which each Index Participant(IP) was invited to enroll with a Family Member(FM). In some cases, FM also chose to enroll as IP as part of the related dyad. The reported data reflect all enrolled IP, including those who were also FM. FM not enrolled as IP were nonetheless represented in the participant flow as FM. No data were collected for FM who did not enroll as IP. As such, these individuals are not represented in any of the reported data.

Overall Study

Analysis population for the primary outcome, as defined in the registry: Overall Number of Participants Analyzed in this measure includes Index Participants. Family Member who were part of a dyad did not participate in data collection are not included in the reported numbers.

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.

Population: This study utilized a dyadic design, wherein each Index Participant (IP) was invited to enroll alongside a Family Member(FM). In certain cases, FM also elected to enroll as IP (together with an IP). The reported enrollment figures reflect all individuals who were formally enrolled as IP. No data were collected for FM who did not enroll as IP; therefore, these individuals are not represented in the reported data.

6. Primary Endpoint

The registry lists the primary outcome as Change in Body Weight, measured over Baseline, 12 weeks.

The primary endpoint is change in body weight, measured in kg, between baseline and 12 weeks. Body weight was collected on a digital scale and treated as a continuous measure. The registry reports the mean change and its standard deviation for each arm.

Change from baseline places the follow-up measurement in relation to an individual’s starting measurement. This can make a treatment-period outcome easier to interpret than a follow-up weight alone, because it describes how the recorded measure moved over the stated timeframe. The mean summarizes the group’s average change, while the standard deviation describes how spread out individual changes were around that mean. Neither summary by itself establishes a difference between randomized arms.

Body weight is a direct, quantitative outcome relevant to a behavioral weight loss program, and a digital scale provides a measurement method stated in the registry record. The outcome is not a direct measure of feasibility or acceptability, which are the study’s stated purpose. The registry record does not report how feasibility or acceptability were defined as formal endpoints, nor does it give a measurement protocol beyond the scale, unit, and timing. The primary results should therefore be read as arm-specific descriptive summaries of body-weight change, alongside the study’s broader feasibility aim.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary endpoint is a continuous outcome: body-weight change in kg. For a continuous measure, a mean is a compact description of the group’s average observed value, while the standard deviation describes dispersion among individual observations. The registry reports both summaries by arm. The mean answers what average change was recorded; the standard deviation helps show whether individual changes clustered closely around that average or varied more widely. Neither is a direct measure of uncertainty about the mean.

What does a standard deviation tell the reader?

A standard deviation describes the spread of observed values around their group mean. A larger spread indicates more variability in the recorded outcomes; it does not mean that the mean itself is more or less favorable. Standard deviations also do not provide a range containing every participant’s result. In this trial, the reported standard deviations place the arm means in the context of variation in body-weight change, but they do not substitute for a confidence interval or a direct comparison.

Why is a between-arm estimate important?

Randomization assigns participants to intervention groups, but the descriptive means alone do not quantify the randomized comparison. A comparative analysis would estimate the contrast between groups and would ordinarily communicate its uncertainty, for example with a confidence interval. A confidence interval is a range of values compatible with the data and the statistical method used; its width conveys precision. The registry record does not report such an interval or a test for the primary between-arm comparison. No comparative effect or statistical significance should be inferred by informally contrasting the two means.

The record’s skip note says that values were missing or not estimable for a two-arm comparison of the continuous endpoint. The record also gives zero analyses. Those details indicate that the posted material does not contain an estimable comparative analysis for this endpoint. The reason the comparison was not estimable is not reported in the registry record. It is therefore not possible to attribute the absence of a comparison to a particular statistical method, data feature, or study decision.

What do planning assumptions mean?

The stated sample-size illustration uses the observed effect as its reference and describes assumptions of a two-sided significance level of 0.05, equal allocation between arms, and a normal approximation. It frames the effect to detect as a stated fraction of the observed effect. Such calculations are planning illustrations, not evidence about the trial’s achieved ability to detect an effect and not observed power. They should not be interpreted as the study’s original sample-size justification: that rationale is not reported in the registry record. Numerical planning results or specific effect fractions are not reported in the record details described for this trial.

In general, power calculations depend on assumptions about the target effect, variability, allocation, and analysis. Altering those assumptions changes the planning estimate. A calculation based on an effect observed in a small study may be especially uncertain as a guide to future planning, because the observed effect itself can vary from study to study. This general caution does not alter the stated fact that the illustration is not the trial’s own design justification. No conclusion about observed power should be drawn from it.

Why can variability complicate continuous-outcome analyses?

For continuous outcomes, common analyses can be sensitive to distributional features, including unusually influential observations and departures from model assumptions. If variation differs across groups or is more irregular than an analysis assumes, conventional uncertainty estimates may be less reliable. General methods can address such issues, but the registry record does not identify a model, diagnostic procedure, robust variance method, or transformation used for this endpoint. It would be speculation to claim that any such procedure was used.

Over-dispersion is a general concern most often discussed for count outcomes: it means that observed variation exceeds what a simple model assumes. It is not a reported feature of this continuous body-weight endpoint, and the registry record does not report an over-dispersion assessment. More generally, matching the statistical model to the measurement scale and observed distribution matters because uncertainty estimates depend on those choices. The posted mean and standard deviation do not reveal which modeling choices would have been appropriate or whether any were applied.

For a trial with a feasibility purpose, descriptive summaries can be useful for characterizing measurements and informing later study planning. However, a feasibility interpretation requires defined criteria and suitable feasibility outcomes. The registry record does not report a formal threshold, protocol for judging acceptability, or statistical plan for those aims. The weight summaries can be interpreted as descriptive outcome data, but they cannot by themselves establish feasibility, acceptability, or comparative efficacy.

10. Confidence Intervals for Each Arm

No two-arm comparison is shown for this trial, but each arm's mean can be given with a t-based 95% confidence interval computed from the posted mean, spread and number of participants.

R code and output

arm <- c("In-person Family Skills Training", "Online Family Skills Training")
n   <- c(11, 8)
m   <- c(-0.91, -2.92)
sp  <- c(4.83, 4.04)
sd  <- sp      # posted standard deviations
for (i in seq_along(n)) {
  se <- sd[i] / sqrt(n[i]); h <- qt(0.975, n[i] - 1) * se
  cat(sprintf("CARM|%s|%d|%.3f|%.3f|%.3f|%.3f\n", arm[i], n[i], m[i], sd[i], m[i] - h, m[i] + h))
}

CARM  In-person Family Skills Training  11  -0.910  4.830  -4.155  2.335
CARM  Online Family Skills Training  8  -2.920  4.040  -6.298  0.458

11. Multiplicity, Missing Data and Analysis Populations

The registry record identifies 12 outcome measures and indicates 11 secondary outcomes posted. Listed secondary outcomes include changes in BMI, self-regulation and self-efficacy of eating behaviors, social support effectiveness and support for eating or exercise, family communication, and family cohesion. The primary endpoint is change in body weight. The record lists zero analyses, and it does not report a statistical plan describing which outcomes were confirmatory, how multiple comparisons would be handled, or whether any adjustment for multiplicity was intended.

Multiplicity is a general issue when many outcomes or comparisons are examined: the chance of finding an apparently unusual result can increase as more tests are considered. Methods such as prespecifying a primary analysis or adjusting inference can address different multiplicity concerns, but the registry record does not say that any particular approach was used. Since no inferential analyses are reported, the posted arm summaries should not be treated as a set of statistically tested findings.

The record reports analysis counts for the primary measure and arm-specific participant counts, but it does not describe missing-data methods, reasons for missingness, imputation, or sensitivity analyses. It does not report whether the analysis population followed an intention-to-treat principle or another prespecified population definition. The primary-outcome description clarifies that family members in a dyad who did not participate in data collection are excluded from the reported numbers; it does not explain other reasons that could account for participants not appearing in the outcome summaries. Those details are not reported in the registry record, so the potential effect of missing data on the observed summaries cannot be assessed from the posted information.

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.

For serious adverse events, the registry lists 11 participants at risk in the in-person arm and 8 in the online arm, with zero serious adverse events in each arm. For other adverse events, it lists 11 at risk in the in-person arm and 8 in the online arm, with zero events in each arm. Deaths are recorded as zero in both groups. These are the event counts posted for the reported groups.

A zero count means that no events of the specified category were recorded among the participants at risk in that group during the reported safety accounting. It does not establish that an event is impossible, nor does it show that the groups have identical underlying risks. With no event counts to compare, the record does not provide an estimated safety difference or an uncertainty interval. The registry record does not report the event-collection period, detailed definitions, or additional information needed to interpret the scope of safety surveillance. The serious adverse event terms list is empty, consistent with the posted zero serious adverse event counts.

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

The primary outcome provides descriptive information about body-weight change in the two assigned formats over the stated baseline-to-12-week timeframe. The mean change is -0.91 kg for in-person training and -2.92 kg for online training. The standard deviations and participant counts show that these means summarize groups with observed variation, rather than identical individual responses. The summaries describe what was recorded; they do not establish a treatment effect or a causal advantage of one format over the other.

The record does not report a between-arm estimate, confidence interval, or statistical test for the primary endpoint. It is therefore not possible to determine from the posted results how precisely the contrast between formats is estimated, or whether the observed ordering of the means is distinguishable from chance variation. No numeric contrast should be inferred from the arm means in place of a reported analysis. The record’s note that a two-arm comparison was not estimable further limits comparative interpretation.

The stated research purpose was feasibility and acceptability of an interactive counselor-led online family skills training incorporated into a behavioral weight loss program for Black adults. The body-weight endpoint is relevant to the program context, but it is not, by itself, a measure of whether online training was feasible or acceptable. The registry record does not report formal criteria or results for those aims. It also does not provide enough information to judge whether all relevant outcome data were captured or how any missing measurements were treated.

The trial’s results should not be generalized beyond the population, intervention formats, measurement timeframe, and study context recorded in the registry without further evidence. In particular, the record describes Black adults enrolled in a behavioral weight loss intervention and a dyadic training arrangement; it does not establish how the findings apply to other populations or program settings. These limitations concern what can be inferred from the record and do not negate the descriptive value of the posted summaries.

14. Why This Trial Matters Statistically

This trial is statistically interesting because it places an online family skills format beside an in-person format within a randomized parallel-group design, while stating feasibility and acceptability as the research purpose. That combination raises distinct questions. A descriptive outcome summary can characterize observed body-weight changes, a comparative analysis can estimate how the randomized groups differ, and a feasibility assessment can address whether an intervention can be delivered and accepted. These questions require different evidence and should not be collapsed into a single interpretation.

The primary outcome is reported with an arm-specific mean, standard deviation, and participant count, which gives readers a basic view of both average change and variability. The absence of a reported between-arm estimate and uncertainty interval is equally important: descriptive summaries alone do not quantify the precision of a randomized contrast. The registry record’s notation that the comparison was not estimable makes this distinction explicit. It also illustrates why a result can be present while the principal comparative inference remains unavailable.

The enrollment and outcome counts also highlight the value of transparent reporting of analysis populations and missing-data handling. The record explains that dyad family members who did not participate in data collection are excluded from the outcome numbers, but does not give a full accounting of other exclusions or missing measurements. That distinction matters when interpreting group summaries and planning later research.

Finally, the study’s feasibility focus makes prespecified feasibility definitions and reporting especially relevant. The registry record does not give formal thresholds or a statistical plan for those aims. Future interpretation would be clearer with explicit criteria, a defined analysis population, methods for handling incomplete data, and a planned approach to the primary comparison. These are general reporting considerations, not claims about procedures used in this study.

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 for evaluating how the study was conducted and how the primary outcome was analyzed. It identifies randomization, parallel assignment, and no masking, but does not report how the allocation sequence was generated or concealed. It also does not provide the intervention schedule or a detailed description of the online and in-person training beyond participation as a dyad with a family member. Those features limit assessment of intervention delivery and potential differences between formats.

The record reports body-weight change at baseline and 12 weeks, but gives no additional measurement procedures beyond use of a digital scale. The handling of missing measurements, reasons for non-inclusion in the outcome summaries, and analysis-population definition are not reported in the registry record. The family-member exclusion note clarifies who is not included in reported numbers, but does not account for all possible differences between enrollment and outcome reporting.

The primary outcome summaries are descriptive, and a two-arm comparison is noted as missing or not estimable. No comparative estimate, confidence interval, or test is reported. The statistical model, diagnostics, and any adjustment for baseline values or other factors are also not reported. This prevents assessment of the intended precision and of whether the observed summaries support a comparative inference.

The study’s stated feasibility and acceptability purpose is not accompanied in the registry record by formal criteria or results for those aims. The record also does not report a rationale for enrollment, a prespecified statistical plan, or a multiplicity approach for the outcome measures. These limitations do not change the values posted for body-weight change, but they constrain conclusions about feasibility, acceptability, missing data, and differences between intervention formats.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Online Family Dyadic Skills Training for Black Adults in Behavioral Weight Loss Program — NCT05981508.
• Registry record last updated 2025-11-06; status last verified 2023-07.
• Results first posted 2025-11-06.
• 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 record describes a completed randomized, unmasked, parallel-group feasibility study of online and in-person family skills training for Black adults enrolled in a behavioral weight loss program. Enrollment is 21, and the primary endpoint is change in body weight in kg from baseline to 12 weeks. The reported mean change is -0.91 kg in the in-person arm and -2.92 kg in the online arm, with standard deviations of 4.83 kg and 4.04 kg, respectively. The corresponding outcome counts are 11 and 8.

The stated study purpose is to test the feasibility and acceptability of interactive counselor-led online family skills training. The registry lists secondary outcomes concerning BMI, eating behaviors, social support, and family relationships. It reports zero analyses and notes that values are missing or not estimable for a two-arm comparison of the continuous endpoint. No comparative estimate, confidence interval, or statistical test is reported. Safety counts list zero serious adverse events, zero other adverse events, and zero deaths in both arms. The record does not report formal feasibility criteria, a statistical analysis plan, or methods for handling missing data.