A Pilot Trial of a Network Intervention for Youth After Incarceration: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Pilot Trial of a Network Intervention for Youth After Incarceration (NCT03556618), a non-randomized na study. The primary outcome is Frequency of Past-month (30-day) Marijuana Use.

2. Clinical Question

The study rationale is that community reentry may be an opportunity to improve social support and connections to health and behavioral health services. The investigators hypothesize that a reentry coach can help youth strengthen supportive relationships and address barriers to care. These are the stated rationale and hypothesis, not findings from the posted results. The registry record does not report an outcome estimate demonstrating whether the program changed marijuana-use frequency or any other outcome.

3. Trial Design

This was a parallel, non-randomized pilot trial with no masking. The registry lists the phase as NA, enrollment as 19, and status as terminated. The record lists the start date as 2020-03-02 and the primary completion date as 2021-12-16. The sponsor is the University of California, Los Angeles.

The intervention was the Whole Person Care (WPC) Reentry Program. The registry describes the intervention arm as receiving post-release WPC community health worker services, while the control arm received pre-release services only and did not receive the post-release community health worker intervention. The control description specifies youth exiting the adult jail system ages 18-24. The intervention description is an adaptation of an adult reentry model, developed in partnership with the LA County Health Agency. The registry’s description of the intervention is incomplete, so further details about its delivery are not reported in the registry record.

Because allocation was non-randomized, the groups should not be treated as exchangeable by design. Differences in participant characteristics, circumstances, or access to services could affect outcomes independently of the intervention. The registry record does not report how allocation was determined or whether any statistical adjustment was planned to address baseline differences. It also does not report a detailed protocol, the reason the trial was terminated, or whether recruitment and follow-up proceeded as originally intended.

The registry lists 20 outcome measures and zero analyses. It does not report an analysis plan, an intervention-effect estimate, or outcome results for the primary comparison. The record’s primary-outcome population description states that no participants were in the intervention arm. Consequently, the registry entry does not support a numerical interpretation of the primary between-arm contrast.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Overall Study

Analysis population for the primary outcome, as defined in the registry: No participants were in the intervention arm of the study

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: 0 participants received the post-release WPC reentry intervention.

6. Primary Endpoint

The registry lists the primary outcome as Frequency of Past-month (30-day) Marijuana Use, measured over 3 months post-release.

The primary endpoint is frequency of past-month marijuana use, recorded as the number of days and assessed at 3 months post-release. It is described as a self-reported measure. The endpoint focuses on how often marijuana use occurred during the specified recall period, rather than whether a participant used marijuana at any time or on the amount used on a given day.

Using a mean for this continuous measure can describe the average reported frequency within an analysis group. A standard deviation, if reported, would describe how much individual reports vary around that mean; it would not by itself show how precisely the mean has been estimated. A comparison of group means could describe an average difference in reported days, but interpretation would depend on the participants included, missing responses, and the analysis method.

As a self-reported measure, the endpoint reflects participants’ reports and may be affected by recall or reporting. The registry record does not report the exact questionnaire wording, the data-collection method, or procedures for confirming reports. It also does not provide a mean, standard deviation, confidence interval, or test result for this outcome. Most importantly, the primary outcome description says no participants were in the intervention arm. Without outcome data from that arm, the record cannot show a primary between-arm estimate or its precision.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does the mean represent? The primary measure is continuous and is summarized by a mean according to the registry. In general, a mean is the arithmetic average of the observed values in the analysis group. It gives a single description of the group’s average reported frequency, but it does not show the spread of individual responses or whether the group is representative of the intended population. The registry identifies standard deviation as the measure of dispersion. In general, standard deviation describes variation among individual observations; it is not the same as the uncertainty around the estimated mean.

The endpoint is self-reported frequency of marijuana use in days during the past-month (30-day) period, assessed at 3 months post-release. The registry record does not provide the observed mean or standard deviation. Nor does it report a primary outcome comparison. The population description says no participants were in the intervention arm, and the record lists zero analyses. As a result, the usual interpretation of a mean difference between arms cannot be applied to the posted primary outcome information.

How would an uncertainty interval be read? In general, a confidence interval gives a range of values compatible with the data and the method used, while reflecting sampling uncertainty. A narrower interval generally indicates greater precision under the model and assumptions used; a wide interval indicates less precision. An interval is not a guarantee that the true effect lies within its bounds, and it does not correct for bias from non-randomized allocation, missing data, or measurement error. No confidence interval for the primary comparison is reported in the registry record.

What does a significance test tell a reader? In general, a p-value describes how unusual data at least as incompatible with a specified null hypothesis would be under the test’s assumptions, if that null hypothesis were true. It is not the probability that the null hypothesis is true, and it does not measure the importance of an effect. It should be read alongside the estimated effect and its uncertainty. The registry record does not report a primary-outcome p-value or test. It also does not report a statistical analysis plan specifying which tests would have been used.

Why does non-randomized allocation matter? Random assignment, when implemented as intended, helps balance both measured and unmeasured factors across groups on average. This trial is listed as non-randomized. In general, the groups may therefore differ before the intervention in factors that also influence outcomes. Statistical adjustment can address some measured differences, but cannot guarantee removal of confounding, particularly when relevant factors are unmeasured or poorly recorded. The registry record does not report how participants entered each arm, baseline balance, covariate adjustment, or other methods intended to address confounding. A between-group difference, if reported, would need to be interpreted with that limitation in mind.

What does the record say about planning calculations? The registry describes a planning illustration based on a fraction of an observed effect, with a two-sided significance level of 0.05, equal allocation, and a normal approximation. It states that the calculation is a planning illustration rather than the trial’s own design. The record does not include the numerical planning outputs in the registry record for interpretation, and it does not report an observed primary effect from which to assess such a calculation. A planning sample size is not observed power and is not evidence that a study was adequately powered. No sample-size justification for the pilot is reported in the registry record.

What cannot be assessed from the posted analysis information? The registry lists zero analyses and does not report methods for handling missing observations, repeated measurements, departures from assumptions, or adjustment for baseline values. It does not specify an analysis population, such as whether all enrolled participants or only those completing follow-up would be included. The primary-outcome population description is particularly consequential because it states that no participants were in the intervention arm. Without an analysis population and outcome data for both arms, neither a comparative estimate nor its precision can be evaluated.

These explanations are general statistical guidance, not a description of methods confirmed to have been used in this trial. The statistical methods actually used beyond the registry’s stated planning assumptions are not reported in the registry record. Accordingly, the primary outcome cannot be independently interpreted as a treatment-effect estimate from the registry information.

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("Control")
n   <- c(19)
m   <- c(7.4)
sp  <- c(10.9)
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  Control  19  7.400  10.900  2.146  12.654

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 20 outcome measures, including the primary measure of past-month marijuana-use frequency and secondary outcomes covering marijuana use, alcohol use, recidivism, receipt of behavioral health services, and mental health. Several outcome labels appear more than once in the listed secondary outcomes. The record lists zero analyses and does not identify which outcome comparisons, time points, or tests were actually conducted.

When a study examines multiple outcomes or makes multiple comparisons, the chance of obtaining at least one apparently notable result can increase. In general, a prespecified testing strategy or multiplicity adjustment can help readers distinguish confirmatory analyses from exploratory ones. The registry record does not report whether the investigators planned such a strategy or used an adjustment. With no analysis results posted, the impact of multiplicity on any findings cannot be assessed.

Missing-data handling is not reported in the registry record. It does not state how missing outcome responses would be treated, whether follow-up completion differed by arm, or whether any sensitivity analyses were planned. These details matter because an analysis based only on observed responses can be biased if the availability of responses is related to participant characteristics or outcomes.

The analysis populations are also not specified. The primary-outcome description states that no participants were in the intervention arm, while the registry lists enrollment as 19. Those entries do not establish which participants contributed data to other outcomes or analyses. The record does not report a rule for including participants, handling non-adherence, or defining the analysis set. Without these details and outcome data, neither missingness nor the role of analysis-population choices can be evaluated.

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’s adverse-event entries list the Whole Person Care (WPC) Reentry Program group with 0 at risk for serious adverse events and 0 serious adverse events affected. The Control group is listed with 19 at risk and 0 serious adverse events affected. For other adverse events, the WPC group is listed with 0 at risk and 0 affected, while the Control group is listed with 19 at risk and 0 affected. Deaths are listed as 0 in both groups.

These figures are registry counts, not comparative risk estimates. The WPC group’s zero at-risk entry means that the record does not give an exposed intervention-arm population for interpreting its adverse-event count. The entries do not establish that serious or other adverse events could not occur, and the control-arm count does not by itself establish the safety profile of the intervention.

The registry record does not list serious adverse-event terms. It also does not report the period of safety monitoring, event-collection procedures, event severity beyond the serious/non-serious categories, or a statistical comparison. Given the limited at-risk information, particularly for the intervention group, these entries should be read as the posted counts only and not as evidence of comparative safety.

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

The registry record describes a pilot intervention intended to support youth during reentry after incarceration, with the primary outcome focused on self-reported frequency of marijuana use at 3 months post-release. That description clarifies the study’s question and rationale. It does not demonstrate that the intervention changed marijuana use, treatment access, recidivism, or mental health.

The primary outcome information does not include an intervention-arm population. The registry also lists zero analyses and reports no primary outcome estimate, uncertainty interval, or test. Therefore, the posted information cannot establish the direction or size of a primary outcome difference, how precisely it was estimated, or whether an observed difference would be compatible with chance under a specified model.

Equally, missing comparative results do not establish that the program had no effect. The absence of an estimate is a limitation of the available record, not a null finding. No conclusion about efficacy, ineffectiveness, or equivalence should be drawn from the registry information alone.

The non-randomized design further limits causal interpretation. In general, group differences can reflect pre-existing differences as well as any influence of an intervention. The record does not report allocation procedures or adjusted outcome analyses that could help readers assess this concern. The trial’s terminated status and the missing reason for termination also leave uncertainty about how the study ended and what follow-up was completed.

The secondary outcomes listed in the record identify additional areas of interest, but their names are not results. Without outcome values, analysis details, and information about missing data, they cannot support conclusions about service receipt, substance use, recidivism, or mental health. The sound interpretation is that the record documents a pilot study and its intended questions, while leaving the central outcome evidence unavailable for assessment.

14. Why This Trial Matters Statistically

This trial is statistically important as an example of why a registered research question and an interpretable outcome analysis are different things. The record identifies a relevant primary measure and a clearly described post-release comparison, but the primary-outcome population entry says no participants were in the intervention arm. Without participants represented in both arms for that endpoint, a between-arm estimate cannot be interpreted from the posted record.

The non-randomized allocation also calls for careful distinction between association and causal effect. In general, outcomes in intervention and control groups may differ for reasons other than the intervention. Transparent reporting of allocation, baseline characteristics, analysis choices, and uncertainty is needed for readers to judge how much a group contrast can support a causal interpretation. Those details are not reported in the registry record.

The record also illustrates the importance of reporting the analysis itself, not only the outcome names. Although 20 outcome measures are listed, the record reports zero analyses. Without estimates and uncertainty, readers cannot assess the magnitude, precision, or consistency of outcomes, or understand how multiple comparisons were addressed.

For clinical researchers and biostatisticians, the distinction between a planning calculation and observed evidence is also important. The registry describes sample-size assumptions as a planning illustration, not as a feature of the trial’s own design. Such calculations cannot substitute for reported results, and they are not observed power. Overall, this record makes the study’s intended question visible but does not provide the results needed to evaluate the primary comparison.

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.

Several limitations specific to this trial constrain interpretation of the registry record. The study is listed as non-randomized and unmasked. The registry does not report how allocation was determined, what characteristics differed between groups, or whether an adjustment strategy was used. Any apparent group comparison would therefore require caution about confounding, even if estimates were available.

The primary outcome is self-reported marijuana-use frequency. The registry does not report the questionnaire wording, the data-collection procedure, or any validation method. The record also states that no participants were in the intervention arm for the primary outcome, leaving no posted basis for a primary between-arm estimate. It lists zero analyses and does not provide outcome values for this or the secondary measures.

The registry lists enrollment as 19, but does not report the outcome-specific analysis populations, follow-up completeness, or missing-data methods. It does not state why the trial was terminated or whether the listed primary completion date represents completion of all planned data collection. The reason for termination and any changes to the planned study are not reported in the registry record.

The intervention description is incomplete, and the record does not report detailed information about service delivery, adherence, or exposure. The timing and procedures for adverse-event monitoring are also not reported. These gaps limit assessment of what participants received and how completely outcomes and safety events were captured. Taken together, the available record supports a description of the planned intervention and question, but not a detailed evaluation of implementation or comparative outcomes.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: A Pilot Trial of a Network Intervention for Youth After Incarceration — NCT03556618.
• Registry record last updated 2024-03-27; status last verified 2024-02.
• Results first posted 2024-03-27.
• 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 describes NCT03556618, A Pilot Trial of a Network Intervention for Youth After Incarceration, sponsored by the University of California, Los Angeles. It lists a parallel, non-randomized design with no masking, enrollment of 19, and terminated status. The start date is 2020-03-02 and the primary completion date is 2021-12-16.

The intervention is the Whole Person Care Reentry Program, with post-release community health worker services contrasted with control services limited to the pre-release period. The primary outcome is self-reported past-month marijuana-use frequency in days at 3 months post-release. The primary-outcome population description states that no participants were in the intervention arm. The registry lists 20 outcome measures and zero analyses, and does not report a primary outcome estimate or the reason for termination. Thus, the record describes the study question and design but does not provide an interpretable primary comparison.