ACT for Life: a Brief Intervention for Maximizing Recovery After Suicidal Crises: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for ACT for Life: a Brief Intervention for Maximizing Recovery After Suicidal Crises (NCT02751983), a randomized na study. The primary outcome is Client Satisfaction Questionnaire - 8.

2. Clinical Question

In statistical terms, this is a pilot study question about a post-treatment satisfaction threshold, not a direct test of whether suicide-related outcomes or functional recovery improved. The registry describes random allocation to the two conditions, but the primary outcome definition is specifically about satisfaction with ACT for Life. Its interpretation therefore depends on who was eligible to complete the questionnaire, who completed it, and how those data were analyzed. The registry identifies the population with post-treatment data as participants who attended at least one ACT for Life session; it does not give an outcome estimate for that population.

3. Trial Design

The registry describes ACT for Life as a randomized, single-masked, parallel-group study with 70 participants enrolled. The two conditions were treatment as usual plus ACT for Life and treatment as usual alone. The record does not state who was masked, so the masking description cannot establish whether participants, clinicians, outcome assessors, or analysts were unaware of assignment. The study phase is listed as not applicable.

The intervention was categorized as behavioral, and the comparator as another type of intervention. The registry says that the ACT condition allowed participants to continue treatment as usual. The treatment-as-usual condition included inpatient and outpatient mental health care. Detailed information about intervention delivery, the exact comparator experience, treatment adherence, and variation in care is not reported in the registry record.

The stated study purpose was an initial pilot to inform revisions to the treatment manual and research design for a future evaluation of efficacy. The registry summary frames inpatient psychiatric care as an opportunity to provide recovery-oriented treatment, while noting the proposed intervention was intended to be feasible during a typical inpatient stay. These aims place the study in a development and feasibility context. They do not establish that the trial was designed or powered to deliver a definitive efficacy comparison.

The registry reports a start date of 2016-11-15, primary completion on 2018-08-09, and a completed status. It lists suicide and psychiatric rehabilitation as the conditions. The specific randomization procedure, allocation concealment, planned group sizes, site count, eligibility criteria, and protocol deviations are not reported in the registry record. Safety listings show 35 participants at risk in each condition, but that information alone does not establish the endpoint analysis population or the number with completed satisfaction assessments.

The primary outcome was assessed after treatment, within 0-7 days after treatment completion. The record also lists secondary measures covering psychological distress, valued living, psychosocial functioning, global health, satisfaction with social roles and activities, and suicide severity. It lists nine outcome measures overall, but does not report statistical estimates for them 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.

Baseline and Randomization

Treatment

Reasons for not completing this period:

Post-Treatment Assessment

Reasons for not completing this period:

One-Month Follow-Up Assessments

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Post-treatment data were collected from participants who engaged in at least one ACT for Life session. 2 of the 35 ACT participants discharged from the hospital prior to receiving any treatment. 3 participants discharged prior to post-treatment assessment and were lost to follow-up.

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 Client Satisfaction Questionnaire - 8, measured over Post-treatment (0-7 days after treatment completion).

The primary outcome is a thresholded count based on the Client Satisfaction Questionnaire - 8. The questionnaire is a self-report measure of participant satisfaction with ACT for Life. Its scores range from 8 to 32, with higher scores indicating greater satisfaction. For this study, scores of at least 24 were defined as acceptable, and the registry describes the endpoint as the number of participants meeting that threshold. The assessment window was post-treatment, from 0-7 days after treatment completion.

A thresholded endpoint can make a study question easy to state: how many participants met the study's definition of acceptable satisfaction? It also discards information contained in the full score. Two participants with scores on opposite sides of the threshold are classified differently even if their scores are close, while scores well apart on the same side are grouped together. The resulting count answers a question about meeting this chosen criterion, not the average satisfaction score or the distribution of questionnaire scores.

The measure is relevant to an intervention-development study because participant experience can inform acceptability and later refinement. However, satisfaction is not itself a measure of symptom change, suicide risk, or functional recovery. The registry lists several other measures that address related domains, but does not report their results. The count of participants meeting the satisfaction threshold is also not reported in the registry record, so neither the observed proportion nor its precision can be described.

The endpoint population is defined as participants who engaged in at least one ACT for Life session and had post-treatment data collected. That distinction matters: a post-treatment satisfaction result among people who began the intervention would not automatically describe everyone assigned to the ACT condition. The number assessed and the endpoint estimate are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary endpoint is binary at the participant level: a participant either meets the study's acceptable-satisfaction threshold or does not. The underlying questionnaire score is recorded on a scale from 8 to 32, but the registry's primary outcome is the count of participants whose score is at least 24. This changes the statistical question from comparing the full score distribution to describing or comparing the proportion crossing a threshold. The registry does not report the count or an analysis of that count.

Why use a threshold?

In general, a threshold can provide a simple, interpretable criterion for classifying an outcome. It may be useful when a study has a prespecified meaning for an acceptable score. The trade-off is information loss: scores are reduced to two categories, and distinctions among participants in the same category are no longer represented. Results can also depend on the chosen cut point. Here, the registry states that scores at or above 24 were considered acceptable for this study; the rationale for choosing that threshold is not reported in the registry record.

What does a count show?

In general, a count records how many participants meet an outcome definition. Interpreting it requires a denominator: the number of participants eligible for and assessed on the outcome. A count without that denominator cannot establish how common the outcome was in the relevant group. Comparing groups also requires a stated estimand and analysis, such as a difference in proportions or another appropriate measure. The registry does not report the primary endpoint counts, denominators for completed assessments, or an effect estimate.

Randomization and comparisons

In general, random allocation is used to reduce systematic differences between groups at baseline, so a properly analyzed between-group comparison can support causal interpretation under the trial's conditions. Randomization does not remove the need to report how participants were analyzed, how missing observations were handled, and what uncertainty surrounds the estimate. The study is described as randomized and parallel, but its specific allocation procedure and primary statistical model are not reported in the registry record. No inferential test or effect estimate is reported there.

Uncertainty and confidence intervals

In general, a confidence interval expresses the uncertainty around an estimated quantity under a statistical procedure. A narrow interval indicates greater precision than a wide interval, while an interval's location helps show which effect sizes remain compatible with the data and method. It is not a guarantee that the true value lies within the interval. No confidence interval for satisfaction or for a treatment comparison is reported in the registry record, so precision cannot be assessed.

Planning and sample size

In general, sample-size planning asks how many participants would be needed to detect a specified effect under stated assumptions, including a significance level, allocation scheme, and statistical approximation. A planning illustration based on an observed effect is a hypothetical design exercise, not evidence about the result and not observed power. The registry's stated planning assumptions describe a two-sided significance level of 0.05, equal allocation, and a normal approximation, with the effect framed as a fraction of an observed effect. The participant requirements for those planning scenarios are not reported in the registry record. Because the primary outcome estimate is not reported, those planning assumptions cannot, by themselves, establish the effect observed in this trial. A small pilot sample should not be treated as a definitive test merely because a planning calculation can be described.

Over-dispersion and outcome type

In general, over-dispersion means that observed variability exceeds what a statistical model assumes. It is a concern for some count outcomes and can make standard errors too small if the model does not accommodate the extra variability. The primary endpoint is a count of participants meeting a binary criterion, rather than a recurrent-event count for which each participant may contribute many events. The registry does not report a model or dispersion estimate. It would therefore be inappropriate to claim that over-dispersion was tested, present a model-based correction, or infer which statistical method was used.

Recalculation

A recalculated result would be a simple, unadjusted calculation from posted summary statistics, not a replacement for the sponsor's analysis. No primary outcome counts or summary statistics for such a calculation are reported in the registry record. There is therefore no recalculated effect to interpret and no discrepancy between a recalculation and a sponsor analysis to assess. The sponsor's own analysis would take precedence if a discrepancy were reported.

The record's pilot objective also affects the role of statistical methods. A pilot can inform the practicality of collecting measures and refine future research plans. In general, estimates from a pilot can be imprecise, and a future definitive study would need a clearly specified primary comparison and analysis plan. The registry does not report a statistical analysis plan, sample-size justification, interim analyses, or details of any adjustment for baseline variables. Those design and analysis details should not be inferred from the randomized label or from the endpoint definition.

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("Treatment as Usual Plus ACT")
n      <- c(30)
events <- c(28)
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  Treatment as Usual Plus ACT  30  28  93.3  77.9  99.2  78.7  98.2  78.6  98.0

11. Multiplicity, Missing Data and Analysis Populations

The registry lists nine outcome measures overall. The primary measure is the Client Satisfaction Questionnaire - 8 threshold count, and the listed secondary measures include psychological distress, valued living, psychosocial functioning, global health, satisfaction with social roles and activities, and suicide severity. Results for these outcomes and a complete set of outcome definitions are not reported in the registry record.

In general, testing multiple outcomes can increase the chance of at least one apparently notable result arising by chance. Researchers may address this through a prespecified hierarchy, adjustment procedure, or interpretation that treats secondary analyses as exploratory. The registry record does not report a multiplicity strategy, so it is not possible to determine whether or how the outcome set was handled statistically. No analysis estimates or p-values are reported to evaluate.

The primary endpoint population consisted of participants who engaged in at least one ACT for Life session and had post-treatment data collected. The registry notes that 2 of 35 ACT participants discharged before receiving any treatment, and 3 discharged before post-treatment assessment and were lost to follow-up. It does not state whether these groups overlap, how missing data were handled, or how many participants completed the endpoint assessment. These details are necessary to understand possible selection and missing-data effects.

In general, an analysis of everyone as randomized preserves the original randomized comparison, while an analysis limited to participants who started or completed treatment answers a different question and can be affected by post-randomization selection. The registry does not report an intention-to-treat analysis, a per-protocol analysis, imputation, sensitivity analyses, or a detailed definition of the analysis population. The summary of who contributed primary endpoint data should therefore be distinguished from any broader randomized population.

Interim analyses and stopping rules are not reported in the registry record. The record also does not provide a statistical analysis plan or details on adjustment for multiple comparisons. These omissions limit assessment of how outcome selection, missing assessments, and the analysis population may have influenced reported results.

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 listings report zero serious adverse events, zero other adverse events, and zero deaths in both conditions. Each condition has 35 participants listed at risk for the serious and other adverse event summaries. These are recorded counts in the registry; they are not estimates of comparative risk, and the record does not provide an uncertainty interval or statistical test for safety outcomes.

A zero count means that no event of that listed type was recorded in the stated group and safety summary. In general, zero observed events do not prove that the underlying event risk is zero. The ability to detect uncommon events depends on the amount and duration of observation and on how completely events are identified and reported. The safety observation period, event-collection procedures, and definitions used for serious and other adverse events are not reported in the registry record.

The equal at-risk counts in the safety listings should not be assumed to be the denominators for the satisfaction endpoint. The primary endpoint population was described separately as participants who engaged in at least one ACT session and had post-treatment data. The number with such data is not reported. Safety counts also cannot establish that the two conditions have identical safety profiles, particularly without information on follow-up duration and precision. The listings should be read as descriptive registry entries, not as proof of safety or as a treatment recommendation.

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

The study addresses a practical research question: whether a recovery-oriented intervention can be incorporated into care for Veterans hospitalized after suicidal crises, and whether the experience can inform later study design. The registry describes randomized allocation to ACT for Life plus treatment as usual or treatment as usual alone, and identifies participant satisfaction after treatment as the primary endpoint. The stated pilot aim was to inform revisions to the intervention manual and future research design.

The record does not report the number of participants meeting the satisfaction threshold, a group comparison, confidence intervals, p-values, or estimates for the listed secondary measures. As a result, it is not possible to say from the posted statistical results how much acceptable satisfaction was observed, how precise an estimate would be, or whether groups differed. Missing statistical results should not be interpreted as evidence of either benefit or lack of benefit.

Even with a reported satisfaction result, the primary endpoint would address acceptability as defined by the study, not the full range of clinical outcomes that might matter. The registry lists additional measures related to distress, valued living, psychosocial functioning, global health, social roles, and suicide severity, but their results are not reported in the registry record. A satisfaction threshold alone cannot answer whether these other outcomes changed.

The endpoint population also narrows the scope of what it could describe. Post-treatment data were collected from ACT participants who engaged in at least one session. The registry notes participants who discharged before treatment and participants lost before assessment, but does not report a complete flow of participants through outcome assessment or the method for handling missing data. A result limited to those with observed assessments may not represent every participant randomized to ACT.

The zero event counts in the safety summaries are descriptive and do not demonstrate zero risk or equivalent safety. The record does not provide the observation period or precision of these counts. Overall, the registry documents a completed pilot and its intended endpoint, but not the numerical results necessary for conclusions about treatment effects, satisfaction levels, or clinical outcomes. The intervention's effectiveness is not established by these registry entries.

14. Why This Trial Matters Statistically

This trial is statistically informative as an example of how the question being asked should shape interpretation. The primary endpoint is not the questionnaire's full score but a count of participants meeting a threshold for acceptable satisfaction. That distinction affects both the meaning of the result and the information available for analysis. A threshold may be understandable to readers, but it compresses the scale and makes the chosen cut point central to interpretation.

The record also illustrates why the analysis population matters. The primary outcome was collected among participants who engaged in at least one ACT for Life session, while the study itself was randomized. A post-treatment summary from intervention starters does not automatically answer the same question as a comparison based on everyone randomized. Reporting participant flow, endpoint denominators, and missing-data methods would allow readers to judge how the analysis relates to the randomized design.

The study was described as a pilot intended to guide intervention refinement and future research. That purpose makes feasibility and measurement considerations relevant alongside efficacy. But pilot status does not make missing outcome estimates interpretable: without the primary count and uncertainty, readers cannot evaluate the observed satisfaction result or its precision. Nor should any planning exercise be confused with evidence that a particular effect was established.

Finally, the registry's safety counts show why descriptive zeros require context. They state what was recorded in the listed groups, but without follow-up duration and reporting procedures they do not quantify uncommon risks. Careful distinction among endpoint definition, analysis population, uncertainty, and safety observation is essential when reading early-stage randomized studies. In this record, the design and aims are described more fully than the statistical results.

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 most consequential limitation for statistical interpretation is that the primary outcome count and comparison are not reported in the registry record. There is no estimate, confidence interval, or p-value from which to assess the magnitude or precision of the satisfaction result. Results for the listed secondary outcomes are also not reported, limiting assessment beyond the primary endpoint.

The primary outcome population is restricted to ACT participants who engaged in at least one session and had post-treatment data collected. The registry reports that 2 of the 35 ACT participants left hospital before receiving any treatment, and 3 left before the post-treatment assessment and were lost to follow-up. It does not report the number assessed, the complete participant flow, whether these groups overlap, or how missing values were treated. These omissions prevent evaluation of the extent and potential influence of missing endpoint data.

The registry identifies a single-masked design but does not state who was masked. It does not report the randomization procedure, allocation concealment, site count, baseline characteristics, intervention adherence, or details of the treatment-as-usual experience. These details would help assess implementation and the comparability of the analyzed groups. A statistical analysis plan, model specification, multiplicity strategy, interim analyses, and sample-size justification are also not reported in the registry record.

The primary endpoint measures satisfaction and uses a threshold defined as acceptable for this study. The registry does not report the rationale for the threshold, and the thresholded count does not preserve the full questionnaire score information. The endpoint is not itself a direct measure of suicide risk or functional recovery.

Safety summaries report zero recorded events in the listed categories, but the observation period and ascertainment procedures are not reported. The small pilot context and missing outcome details constrain what can be inferred; they do not establish that an effect is absent or that no safety events occurred outside the recorded summaries.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: ACT for Life: a Brief Intervention for Maximizing Recovery After Suicidal Crises — NCT02751983.
• Registry record last updated 2019-11-13; status last verified 2019-10.
• Results first posted 2019-11-13.
• 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

NCT02751983 is a completed, randomized, single-masked, parallel-group pilot study of ACT for Life, a behavioral intervention added to treatment as usual. The registry reports 70 participants enrolled and describes the study as intended to inform revisions to the intervention manual and future research design.

The primary endpoint was the number of ACT participants with a Client Satisfaction Questionnaire - 8 score of at least 24, measured within 0-7 days after treatment completion. The record says post-treatment data were collected from participants who engaged in at least one ACT session and notes participants who left before treatment or before assessment. The primary endpoint count and statistical comparison are not reported in the registry record.

The registry lists secondary measures concerning distress, valued living, functioning, global health, social roles, and suicide severity. Safety listings record zero serious adverse events, zero other adverse events, and zero deaths in each condition, with 35 participants at risk per group. The safety observation period and detailed statistical analysis methods are not reported in the registry record.