Social-LEAF Life Enhancing Activities for Caregivers: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Social-LEAF Life Enhancing Activities for Caregivers (NCT05274074), a randomized na study. The primary outcome is Patient Reported Outcome Measurement Information System (PROMIS )Positive Affect.

2. Clinical Question

The endpoint is a self-reported measure of momentary positive affective experiences over the past 7 days. Higher scores indicate better positive affect. The statistical question is about the difference in average change between the groups at the stated follow-up, not whether every participant experienced the same change. The registry record also lists measures of social networks, social isolation, satisfaction with role activities, positive aspects of caregiving, and loneliness as secondary outcomes. These measures provide context about the broader outcomes the study assessed, but the primary comparison is the Week 6 PROMIS Positive Affect result.

3. Trial Design

NCT05274074, titled Social-LEAF Life Enhancing Activities for Caregivers, is a completed randomized behavioral study sponsored by the University of Rochester. Its official title is Improving Care Partner Outcomes Through Positive Connections. The listed condition is Social Connectedness. The study started on 2022-07-28, and its primary completion date is 2023-07-23.

The design is parallel, with random allocation and no masking. The registry lists an enrollment of 58. The two groups were Intervention and Wait-List Control. The intervention was Social LEAF, an adaptation of the Life Enhancing Activities for Family Caregivers program focused on social relationships and loneliness. The control group waited 6 week before receiving the intervention. This means the Week 6 primary comparison is between participants assigned to begin Social LEAF and those assigned to wait during that period.

The primary outcome was change from baseline to Week 6 in PROMIS Positive Affect. The group results are reported as least-squares means with 95% confidence intervals, and the between-group result is reported as a regression mean difference with its confidence interval and p-value. The primary outcome description says the measure has 15 items and a possible raw-score range of 15-75. The registry lists six outcome measures and six analyses, and five secondary outcomes are posted. The named secondary measures concern social networks, social isolation, role-activity satisfaction, positive aspects of caregiving, and loneliness.

The registry record does not report the allocation-generation procedure, concealment methods, or other details about how randomization was implemented. It also does not report masking, which is listed as none. A detailed protocol, sample-size justification, interim-analysis plan, or complete statistical-analysis plan is not reported in the registry record. The stated enrollment should therefore be read as the listed enrollment, not as evidence about how the study size was chosen or whether a particular power target was met.

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

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Caregivers of persons with Lewy-body dementia were randomized to intervention and wait-list control groups. Nine participants did not complete either baseline or the 6-week measure.

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 Patient Reported Outcome Measurement Information System (PROMIS )Positive Affect, measured over Week 6.

The primary endpoint is change in the Patient Reported Outcome Measurement Information System Positive Affect measure from baseline to Week 6. The measure asks about momentary positive affective experiences over the past 7 days. It contains 15 items with five response choices, from “Not at all” to “Very much.” Responses are summed into a raw score ranging from 15-75 units on a scale. Higher scores indicate better positive affect.

Positive affect is relevant to this study because the intervention is intended to address social relationships and loneliness among caregivers. A self-reported measure can capture participants’ own account of their recent affective experiences. The endpoint is continuous: it records a score rather than placing each participant into a yes-or-no outcome category. The registry reports least-squares means and 95% confidence intervals for the groups, as well as a regression estimate of the net mean difference. These summaries describe average change and the precision of the estimated between-group comparison.

The endpoint does not directly measure every aspect of social connection or caregiving. The registry lists separate secondary measures for social networks, social isolation, satisfaction with role activities, positive aspects of caregiving, and loneliness. The primary outcome should therefore be interpreted specifically as a measure of positive affect, not as a comprehensive measure of caregiver well-being or social connection.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does a least-squares mean describe?

The primary outcome is continuous, meaning it is measured on a numerical scale rather than as a category. A least-squares mean is a model-based estimate of an average. In general, regression can estimate group means or differences while accounting for variables included in the model. The registry record identifies the group summaries as least-squares means, but the detailed model specification and any covariates are not reported in the registry record. The estimates should therefore be interpreted as the reported model-based summaries, without assuming which additional adjustments were made.

The arm-level results describe change from baseline to Week 6. A negative mean change indicates a lower average score at follow-up relative to baseline, while a positive change would indicate a higher average score. Since higher PROMIS Positive Affect scores indicate better positive affect, the sign of a change has a direct scale interpretation. Still, a group mean does not imply that every participant changed in the same direction. Individual responses may vary around the group estimate, and the registry record does not report individual-level distributions in the registry record.

How should the confidence intervals be read?

A confidence interval expresses uncertainty around an estimate under the statistical method used. In general, a 95% confidence interval is generated by a procedure that would cover the target parameter in 95% of repeated samples when its assumptions hold. It is not a range that assigns a 95% probability to the specific parameter after the data have been observed. The arm-level intervals are -5.1 to 1.7 for control and -3.8 to 3.1 for intervention. The interval for the regression mean difference is -3.4 to 6.2.

For a difference, zero represents no between-group difference. The interval from -3.4 to 6.2 includes zero, so the data are compatible with no difference as well as with a range of differences on either side. The interval is also wide enough that the point estimate alone should not be treated as a precise measure of the magnitude. Confidence intervals describe statistical uncertainty under the model; they do not correct for missing data, measurement limitations, or unreported design details.

What does the reported p-value add?

The regression result gives p = 0.57. In general, a p-value measures how compatible the observed data are with a specified null model, conditional on the model assumptions. It is not the probability that the null is correct, and it is not a measure of the size or clinical importance of an effect. The p-value is consistent with the confidence interval’s inclusion of zero. It does not establish that the groups are identical; rather, the result does not provide strong statistical evidence against the null of no between-group difference.

Statistical significance and practical importance are different questions. A confidence interval can help show which effect sizes remain compatible with the data, but deciding what size of difference would matter requires a meaningful threshold or context. A threshold for clinically important change is not reported in the registry record. No conclusion about clinical importance can therefore be drawn from the estimate and p-value alone.

Why is over-dispersion relevant in general?

For a continuous outcome, variability describes how widely individual measurements or changes are spread around an average. In general, a model that understates variability can make uncertainty appear too small, while a model that accommodates variability more appropriately can produce wider uncertainty estimates. Over-dispersion is most commonly discussed for count outcomes, when observed variability exceeds what a model assumes. The primary endpoint is continuous, and the registry record describes confidence intervals but does not report a dispersion statistic or an over-dispersion assessment. It would not be appropriate to claim that over-dispersion was present or that a particular correction was used.

How do the groups and analysis relate?

The study is randomized, parallel, and unmasked. Randomization is intended, in general, to create groups that are comparable on average at assignment, although it does not guarantee exact balance in a particular trial. The posted comparison uses a regression estimate of the net mean difference. The registry record names the analysis method as linear regression but does not report further model details in the registry record described for the primary result. The regression estimate and its interval are the main quantities for interpreting the randomized comparison; comparing each group’s estimate separately is not a substitute for the between-group analysis.

The arm-level figures are based on n = 25 for wait-list control and n = 24 for intervention. These values describe the group counts associated with the posted outcome summaries. The primary outcome description also notes that nine participants did not complete either baseline or the 6-week measure. The exact relationship between those omissions and the analysis counts, the missing-data method, and the analysis population are not reported in the registry record. Those details affect interpretation of the result and cannot be inferred from the reported means or the trial’s listed enrollment.

What are planning calculations, and what are they not?

In general, sample-size calculations estimate how many participants may be needed under specified assumptions to detect a chosen effect with a chosen level of statistical power. Such calculations depend on assumptions about the effect size, variability, allocation, significance level, and analysis approach. A planning illustration based on an observed effect is not evidence that the trial was designed with that effect in mind, and it is not observed power. The registry record does not report the study’s own sample-size justification or planning assumptions.

The calculation description associated with the posted planning material states assumptions of a two-sided significance level of 0.05, equal allocation, and a normal approximation, with the target effect expressed as a fraction of the observed effect. These are planning assumptions, not features that can be taken as the trial’s original design plan. In general, planning results based on an observed estimate can be unstable when that estimate is uncertain. Here the confidence interval for the mean difference is broad and includes zero, so any planning illustration tied to the observed estimate should be interpreted cautiously. It does not change the reported Week 6 result or establish the trial’s power.

10. Analyses Reported by the Sponsor

The sponsor-reported primary analysis is linear regression, with a net mean difference of 1.4 units, a 95% confidence interval from -3.4 to 6.2, and p = 0.57. This is the registry’s own reported between-group analysis and is the appropriate result to cite when describing the sponsor’s analysis. Its positive point estimate is in the direction of higher positive affect in the intervention group relative to wait-list control, but the interval includes zero and the reported p-value does not provide strong evidence of a difference.

The group-level least-squares means are -1.7 for wait-list control and -0.3 for intervention. A separate unadjusted recalculated between-group result is not reported in the registry record. The record does not flag a discrepancy between the sponsor analysis and a recalculation. The detailed regression specification, including any covariate adjustment, is not reported in the registry record, so the sponsor’s model cannot be independently reconstructed from the information. The sponsor analysis should not be replaced by an independently inferred value based only on the group summaries.

11. Multiplicity, Missing Data and Analysis Populations

The registry lists six outcome measures and six analyses, with five secondary outcomes posted. Multiple outcomes create a multiplicity issue: when many hypotheses are tested, the chance of finding at least one apparently unusual result can increase. In general, an analysis plan may address this through a prespecified hierarchy, adjustment, or a clear distinction between primary and exploratory outcomes. The registry record does not report a multiplicity-adjustment method or a testing hierarchy. The primary result should be read as the designated primary outcome, while secondary results should not be treated as confirmatory without information about their analysis plan.

The primary outcome description states that nine participants did not complete either baseline or the 6-week measure. The registry record does not report why measurements were missing, whether the missingness differed by group, how missing values were handled, or whether a sensitivity analysis was conducted. In general, missing-data methods rely on assumptions about why data are absent. Different assumptions can affect estimated group means and the comparison between them. Without the method and analysis-population details, the impact of missing observations cannot be assessed from the posted primary result alone.

The arm-level outcome summaries are associated with n = 25 for wait-list control and n = 24 for intervention. The registry record does not explain the precise analysis population or specify whether all randomized participants were included in the primary analysis. It also does not report the treatment of participants who did not provide the required outcome data. These omissions limit assessment of how closely the analysis follows the randomized assignment and how robust the result is to missingness.

A complete statistical plan, including prespecified handling of missing data, multiplicity, and analysis populations, is not reported in the registry record. This does not establish that such plans were absent; it means the available registry information does not document them. Interpretation should accordingly focus on the reported estimate, interval, and p-value while recognizing that these analysis details remain uncertain.

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 reports zero serious adverse events in the wait-list control group among 29 at risk and zero in the intervention group among 29 at risk. It also reports zero other adverse events in each group among 29 at risk, and zero deaths in both groups. No top serious-event terms are listed.

These figures describe what was recorded for the groups and events listed in the registry. A count of zero means that no event of the specified category was reported among those at risk in that group; it does not establish that the intervention has no safety concerns. The registry entries do not describe event definitions, surveillance procedures, reporting thresholds, or follow-up beyond the information attached to these figures. The adverse-event at-risk counts also should not be assumed to match the primary outcome analysis counts, since the registry lists different denominators for safety and for the primary endpoint summaries.

Safety counts are descriptive and do not by themselves estimate comparative risk precisely. With no reported events in either group, the posted figures do not provide an observed event contrast to interpret. They also cannot rule out uncommon events or events not captured under the registry’s reporting procedures. The appropriate reading is limited to the recorded event counts and the available at-risk figures.

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

The Week 6 primary result is a regression mean difference of 1.4 units in PROMIS Positive Affect, with a 95% confidence interval from -3.4 to 6.2 and p = 0.57. The point estimate is positive, which is in the direction of higher change in the intervention group relative to the wait-list control group. But the confidence interval includes zero and a range of values on either side. The result does not establish a clear between-group difference, nor does it prove that the groups were identical.

The result is specific to the reported measure, time point, and analysis. It concerns change in self-reported positive affect from baseline to Week 6; it is not a direct estimate of loneliness, social isolation, caregiving burden, or every broader outcome relevant to caregivers. The registry lists those topics among secondary outcomes, but their existence does not make the primary endpoint a measure of all of them. The result also does not describe what happened after the control group received Social LEAF following its 6 week waiting period.

Statistical uncertainty is substantial relative to the point estimate, as reflected in the interval. A p-value does not tell whether a difference would be important to participants, and the registry record does not report a threshold for meaningful change. The findings should not be translated into a treatment recommendation or a claim that the intervention does or does not work. They describe the posted statistical comparison and its precision.

The primary outcome description notes nine participants who did not complete either the baseline or 6-week measure. The registry record does not report how those missing measurements were handled. This limits assessment of the analysis population and the potential influence of missing data. The posted result is best understood alongside this uncertainty, the unmasked design, and the absence of detailed model and analysis-plan information in the registry record.

14. Why This Trial Matters Statistically

This trial raises useful statistical questions because it studies a continuous patient-reported outcome in a randomized, parallel-group design. Its primary estimate is a mean difference, which preserves information about the direction and size of average change rather than reducing the outcome to a simple event count. The associated confidence interval makes uncertainty visible and shows why a point estimate should not be read in isolation.

The result also illustrates the distinction between a numerical estimate and evidence of a clear difference. The reported mean difference is 1.4, but its 95% confidence interval ranges from -3.4 to 6.2 and p = 0.57. The interval includes zero and values in either direction. A reader therefore needs to consider both the estimate and its precision, rather than interpreting the sign alone as a conclusion.

Caregiver outcomes may include social connection, isolation, positive aspects of caregiving, role satisfaction, and affect. The registry lists measures covering these areas, but the multiplicity of outcomes makes prespecification and transparent analysis plans important. The record lists six outcome measures and six analyses and does not report how multiplicity was handled. It also does not document the missing-data approach, despite noting incomplete baseline or Week 6 measurements.

Finally, the trial record illustrates why registry results must be interpreted within their reporting limits. The design and primary comparison are identifiable, while detailed model specifications, analysis populations, and the study’s own sample-size justification are not reported in the registry record. Clear separation of reported findings from unresolved methodological details is essential for careful statistical reading.

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 primary result is limited by the breadth of its confidence interval, which includes zero and values favoring either group. The estimate is therefore not precise enough to determine the direction or magnitude of a between-group difference with confidence. The registry record does not report a threshold for a meaningful change in PROMIS Positive Affect, so statistical estimates cannot be translated into a judgment about practical importance.

The primary outcome description notes that nine participants did not complete either baseline or the 6-week measure. The registry record does not report the reasons for missing data, how missing values were handled, or whether a sensitivity analysis was conducted. Although group outcome summaries have associated counts of n = 25 and n = 24, the analysis population and its relation to all randomized participants are not specified in the registry record.

The study is listed as unmasked. The record does not describe whether outcome collection or analysis included any safeguards against awareness of assignment. Since the primary endpoint is self-reported, interpretation should recognize that participants knew or may have known their assigned group, without assuming what effect that had on responses.

The registry names linear regression but does not report the detailed model specification, covariates, or diagnostics. It does not report the original sample-size justification, an interim-analysis plan, or a multiplicity strategy. The record also does not provide details about randomization implementation or the methods used to monitor adverse events. These are limitations of the available reporting, not proof that particular procedures were absent. The results are specific to the posted Week 6 outcome and do not establish what occurred at later times or after the wait-list group received the intervention.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Social-LEAF Life Enhancing Activities for Caregivers — NCT05274074.
• Registry record last updated 2025-03-03; status last verified 2025-02.
• Results first posted 2025-03-03.
• 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

NCT05274074 is a completed, randomized, parallel behavioral study sponsored by the University of Rochester. Social LEAF was compared with a wait-list control among caregivers of persons with Lewy-body dementia. The control group had a 6 week waiting period before receiving the intervention, and the study was unmasked.

The primary endpoint was change from baseline to Week 6 in PROMIS Positive Affect. The reported regression mean difference was 1.4 units, with a 95% confidence interval from -3.4 to 6.2 and p = 0.57. The interval includes zero, indicating substantial uncertainty about the direction and size of the difference. The registry lists five secondary outcomes and notes that nine participants did not complete either baseline or the 6-week measure. Details of missing-data handling, multiplicity, and the full analysis plan are not reported in the registry record.