Smoke-free Home Intervention in Permanent Supportive Housing: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Smoke-free Home Intervention in Permanent Supportive Housing (NCT04855357), a randomized na study. The primary outcome is Proportion of Resident-participants Who Adopt a Smoke-free Home Voluntarily.

2. Clinical Question

3. Trial Design

This was a randomized, parallel, community-based cluster trial with a wait-list control. The registry record identifies the design as cluster-randomized, with participants residing across 20 permanent supportive housing sites in the San Francisco Bay Area. It lists enrollment as 452. The brief summary describes a goal of 400 residents; the record does not explain the relationship between that goal and final enrollment.

The intervention combined resident counseling and staff training. The resident component is described as a one-hour, one-on-one counseling session. The wait-list group received usual care, which the record characterizes as having no smoke-free home adoption intervention or referrals to smoking cessation resources. That group could be offered the intervention after the intervention group completed the 6-month follow-up.

Masking is listed as none. The record gives the study start as 2022-01-24, primary completion as 2025-03-31, and status as completed. The listed phase is NA. It does not report how sites were assigned, whether assignment was stratified, or what steps were used to limit differences between sites. Detailed descriptions of the intervention and control arms are incomplete in the registry record, so further implementation details are not reported in the registry record.

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 study is designed as an intent-to-treat model so all resident-participants who completed the baseline assessment will be included in the outcome measures. Trained location staff-participants who were enrolled in the study were not included in any analysis but were consented to participate in the study and included in Participant Flow, Baseline, and Adverse Event tables.

Baseline

Month 6

Analysis population for the primary outcome, as defined in the registry: This study is designed as an intent-to-treat model so all resident-participants who completed the baseline assessment will be included in the denominator of the outcome measures.

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 Proportion of Resident-participants Who Adopt a Smoke-free Home Voluntarily, measured over 6 months.

The primary endpoint is the proportion of resident-participants who self-reported voluntarily adopting a smoke-free home for at least 90 days by the 6-month follow-up. It is a binary outcome for each participant: the participant either meets the stated adoption definition or does not. The group-level proportion expresses how common the reported outcome was among the participants included in the denominator.

The endpoint is relevant to the intervention’s stated goal of increasing voluntary adoption of smoke-free homes. A self-reported measure can capture adoption as experienced by residents, but it also depends on participants completing follow-up and accurately reporting their home practices. The registry record does not report how self-reports were verified, how missing follow-up outcomes were handled, or whether any additional criteria were used to determine adoption.

The record describes an intent-to-treat approach in which all resident-participants who completed the baseline assessment would be included in outcome denominators. It does not report the number completing baseline or provide an observed endpoint proportion. The primary outcome result is therefore not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

Cluster randomization. In a cluster-randomized trial, groups rather than isolated individuals are assigned to study conditions. Here, the registry identifies permanent supportive housing sites as the setting for a cluster-randomized study, with 20 sites described. This design can fit an intervention delivered through a community or housing setting. It also affects statistical analysis: people in the same site may share staff, surroundings, and local practices, so their outcomes may be correlated. Treating all participants as entirely independent can make uncertainty estimates too narrow. The registry record does not report the model or method used to account for clustering.

Outcome proportions and contrasts. The primary endpoint is a proportion: the count of residents meeting the self-reported smoke-free home definition relative to the relevant resident denominator. A comparison could be expressed using a difference or another measure of relative effect, but the registry record does not report an estimated contrast. No particular effect measure or adjustment strategy is reported in the registry record.

Uncertainty. A confidence interval describes the range of effect estimates compatible with the data and the statistical method, under its assumptions. It communicates precision as well as the direction and scale of an estimate. A p-value addresses how surprising data would be under a specified null model; it is not a measure of the probability that an intervention is effective. Neither confidence intervals nor p-values for the primary endpoint are reported in the registry record. In a clustered trial, uncertainty calculations need to reflect the assignment structure rather than treating every participant as an independent unit.

Over-dispersion and clustering. In general, over-dispersion means that observed variation is greater than a statistical model expects. For outcomes measured as proportions, this can arise when individuals within sites tend to have related outcomes. Accounting for such dependence is important because the effective information in a clustered dataset may differ from what an independent-person analysis assumes. The registry record does not report a dispersion estimate, a cluster correlation estimate, or the analytical method used to address these issues.

Analysis population. The primary outcome description says the study was designed as intent-to-treat and that all resident-participants completing baseline would be included in outcome denominators. This describes the intended population rule; it does not establish how many participants were actually included in an analysis. The number completing baseline, the number with a recorded 6-month outcome, and any departures from the stated rule are not reported in the registry record.

Planning illustrations. The sample-size assumptions describe planning illustrations based on the observed effect, with two-sided significance level 0.05, equal allocation between the two arms, and a normal approximation. The illustrations are not the trial’s original design justification, and they should not be read as observed power. The record does not report a sample-size justification for the trial itself. The analysis note cautions that a simple individual-level re-analysis would be misleading in this cluster-randomized design.

Analysis reporting. The record identifies no analyses. It does not report whether models were adjusted for baseline measures, site characteristics, or other covariates; whether an interim analysis was planned or conducted; or how the analysis handled site-level variation. Those methods are not reported in the registry record. Without the sponsor’s cluster-aware analysis results, readers cannot assess the estimated effect or its statistical uncertainty.

10. Multiplicity, Missing Data and Analysis Populations

The registry record lists a primary endpoint concerning voluntary smoke-free home adoption and a secondary outcome concerning abstinence. It also states that there are two outcome measures, but it does not report analyses. No multiplicity adjustment, hierarchy among tests, or approach to interpreting multiple outcomes is reported in the registry record.

In general, multiplicity arises when several outcomes or comparisons are tested. Looking across multiple tests can increase the chance that at least one result appears notable by chance. A prespecified primary endpoint can help focus interpretation, but the registry record does not give a statistical plan describing how the primary and secondary outcomes would be analyzed together. It does not report whether subgroup analyses or other additional comparisons were planned.

The endpoint description states that all resident-participants who completed baseline would be included in the denominator under an intent-to-treat approach. This does not explain how missing 6-month outcome information would be treated. The numbers with missing follow-up data, reasons for missingness, and any imputation or sensitivity analyses are not reported in the registry record. Nor is it reported whether participants who did not complete baseline were excluded from the stated outcome population or how any other departures from the analysis population were handled.

These omissions limit assessment of whether the reported endpoint, if analyzed, would represent the intended participant population and how robust the result might be to missing data or multiple testing. No conclusions about those procedures can be drawn from the registry record.

11. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

The registry record lists serious and other adverse event counts for resident and staff groups in the intervention and wait-list conditions. For resident participants, the serious-event count is 0 among 191 at risk in the intervention group and 0 among 209 at risk in the wait-list group. For staff participants, the serious-event count is 0 among 35 at risk in the intervention group and 0 among 17 at risk in the wait-list group. Other adverse event counts are also listed as 0 in each of these groups. The record lists no top serious-event terms.

Deaths are reported separately: 7 among resident participants in the intervention group and 6 among resident participants in the wait-list group; no deaths are listed among staff participants in either group. The registry record does not state whether deaths were considered related to study participation or provide further context about their causes. The adverse-event counts alone should not be interpreted as establishing causality or as a complete account of safety. The record does not describe the event collection period, reporting procedures, or whether all events were captured in the same way across groups.

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

The registry record describes a trial intended to assess voluntary smoke-free home adoption among formerly homeless adults residing in permanent supportive housing. The intervention paired resident counseling with staff training, and the comparison was a wait-list control receiving usual care. The primary outcome was defined as self-reported adoption lasting at least 90 days at the 6-month follow-up.

That information clarifies what the study set out to examine, but it does not show what happened on the primary outcome. The registry record does not report group-specific proportions, a comparative estimate, or its uncertainty. It therefore does not support a statement about whether adoption was more or less common in either group, or how large or precise a difference might have been.

Even a reported difference would need interpretation in light of the cluster-randomized design, follow-up completeness, self-reported outcome, and the analysis population. In general, cluster-aware methods are important because residents within a housing site may have shared experiences. The registry record does not provide enough analysis detail to evaluate how that dependence was handled.

The listed safety counts are distinct from the primary outcome. Zero serious and other adverse events are recorded in the participant groups, while deaths are listed for resident groups. The record does not explain whether deaths were related to participation. These entries do not establish a causal safety conclusion.

The appropriate reading is therefore descriptive: the registry identifies the research question, study structure, and outcome definition, while the primary outcome findings and analysis methods needed for an effect interpretation are not reported in the registry record.

13. Why This Trial Matters Statistically

This trial raises statistical issues that are important beyond its specific research question. The intervention was delivered in permanent supportive housing and the study is described as cluster-randomized across 20 sites. That structure makes the site, not just the individual resident, relevant to statistical inference. Analyses that ignore clustering can misstate the amount of independent information in the data and give misleading uncertainty estimates.

The primary endpoint is a participant-level proportion, but its interpretation depends on the denominator and follow-up. The registry describes an intent-to-treat denominator based on completing baseline, yet it does not report baseline completion, outcome availability at 6 months, or missing-data methods. These details are central to understanding which participants contribute to a proportion and how representative the reported outcome might be.

The intervention also includes a staff component, while the outcome is reported for residents. This makes the study a community-level implementation question as well as a participant-level outcome question. The registry record does not provide enough information to assess variation in delivery across sites or how staff and resident data were incorporated into the analysis.

Finally, a completed trial record without posted primary outcome analyses illustrates the difference between a registered study question and an interpretable result. Design and endpoint details explain what was intended to be measured; an effect estimate, uncertainty interval, and transparent cluster-aware analysis are needed to evaluate the observed comparison. Those results are not reported in the registry record.

14. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

Several limitations specific to this trial can be identified from the registry record. First, the primary endpoint is self-reported. The record does not describe validation of reported adoption or the procedures used to collect the follow-up information. That leaves uncertainty about how consistently the endpoint was measured across participants and sites.

Second, the stated analysis population is based on participants completing baseline, but the record does not report the baseline or follow-up counts needed to assess how many residents contributed to the outcome. Missing outcome data, reasons for missingness, and sensitivity analyses are not reported in the registry record.

Third, the trial is cluster-randomized, and the record cautions against a simple individual-level re-analysis. However, no sponsor analysis is listed among the registry analyses, and details of any cluster-adjusted model are not reported. The record also does not describe site allocation procedures or whether the analysis accounted for differences among sites.

Fourth, the brief summary describes a goal of 400 residents while listed enrollment is 452; the record does not explain this difference. It also does not report the trial’s sample-size justification, interim analysis procedures, or a full statistical analysis plan. Arm descriptions are incomplete in the registry record. These gaps restrict assessment of implementation, analysis choices, and the precision of the intended comparison.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Smoke-free Home Intervention in Permanent Supportive Housing — NCT04855357.
• Registry record last updated 2026-06-26; status last verified 2026-03.
• Results first posted 2026-05-29.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

18. Record Summary

The registry record describes NCT04855357, “Smoke-free Home Intervention in Permanent Supportive Housing,” sponsored by the University of California, San Francisco. It is listed as a completed, randomized, parallel, unmasked, cluster-randomized community-based trial in permanent supportive housing. The study description identifies 20 sites in the San Francisco Bay Area and lists enrollment of 452.

The intervention involved resident counseling and staff training; the comparator was wait-list usual care. The primary endpoint was self-reported voluntary adoption of a smoke-free home for at least 90 days at 6 months. The record states an intent-to-treat denominator based on completing baseline.

No analyses are listed, and the primary outcome result is not reported in the registry record. Cluster-aware analysis details, missing-data handling, and the trial’s sample-size justification are also not reported in the registry record.