Treating Violence-Prone Substance Use Disorder Patients: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Treating Violence-Prone Substance Use Disorder Patients (NCT00700973), a non-randomized phase 2, phase 3 study. The primary outcome is Addiction Severity Index Legal Composite.

2. Clinical Question

3. Trial Design

The registry record describes a completed, parallel-group study with non-randomized allocation and no masking. The two arms were substance use disorder usual care and the Interpersonal Violence Prevention Intervention. The listed phases are Phase 2 and Phase 3. Enrollment is reported as 141.

Non-randomized allocation is central to interpreting the comparison. Without random assignment, the reasons participants entered one arm rather than the other are not established in the registry record. Groups may therefore have differed in relevant characteristics before intervention, whether measured or not. A difference observed after treatment could reflect those pre-existing differences, the intervention, other aspects of care, or a combination. The arm comparison cannot by itself separate these explanations.

The record identifies the sponsor as the US Department of Veterans Affairs. The study start is listed as 2009-02, and primary completion as 2012-01. Its status is completed. The description says the project was intended to help substance use disorder patients who perpetrate interpersonal violence against other adults, but it does not provide further details about recruitment, sites, eligibility, or the intervention protocol.

The primary outcome was planned for assessment one year post-intervention. The registry record lists one outcome measure but no analysis and no outcome result. It therefore does not show the arm-specific means, standard deviations, estimated difference, or uncertainty for the registered endpoint. The design information describes what was intended to be studied; it does not supply evidence of an intervention effect.

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

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 Addiction Severity Index Legal Composite, measured over One year post-intervention.

The registered primary endpoint is the Addiction Severity Index Legal Composite, recorded in units on a scale. It is a continuous measure, and the registry record identifies the summary measure as a mean with standard deviation. Scores range from 0 to 1; higher scores indicate more severe legal problems. The stated assessment time is one year post-intervention.

A legal-problem composite is relevant to this study’s focus because it quantifies the severity of problems in the legal domain for the target population. A continuous scale can represent variation across participants rather than reducing the outcome to a simple yes-or-no category. The mean describes the group’s average score, while the standard deviation describes the spread of scores around that average. These summaries address different features of the data and should not be treated as interchangeable.

The registry record does not report the endpoint’s observed means or standard deviations, the number analyzed for this outcome, or an estimate comparing the arms. It also does not report further details about how the composite was scored or how endpoint data were collected. The score’s stated direction helps explain what higher values mean, but without results it cannot show whether scores changed or differed between the groups.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry record identifies a continuous primary outcome summarized by a mean and standard deviation. It does not report an inferential analysis, an effect estimate, or a confidence interval. The concepts below explain how such information is generally interpreted; they do not describe analyses documented for this study.

What does a mean describe?

For a continuous measure, the mean is the arithmetic average of the observed scores in a group. It provides a concise description of the group’s central level on the scale. Here, the scale ranges from 0 to 1, and higher values indicate more severe legal problems. A mean alone does not show how similar or different individual scores were. It also does not show whether an apparent group contrast is precise or attributable to the intervention.

Why report a standard deviation?

A standard deviation describes the spread of individual values around a group mean. A smaller spread indicates scores are more clustered around the mean; a larger spread indicates more variability. It is not the same as the standard error, which describes uncertainty in an estimated mean. Standard deviations for the outcome are not reported in the registry record, so the endpoint’s observed variability cannot be assessed.

What would a group comparison estimate?

A comparison could express how far apart the group means are on the endpoint scale. Such an estimate should be read with its uncertainty interval, if one is reported. The estimate describes the observed contrast under the analysis used; its interpretation depends on study design, data quality, and assumptions. No group contrast or uncertainty interval is reported for this study.

Why does allocation matter?

In a randomized study, assignment by chance is intended to make treatment groups comparable on average at baseline. This study is listed as non-randomized, so that protection against selection-related imbalance does not apply. Participants may have entered arms for reasons related to their initial circumstances or expected outcomes. A raw contrast could therefore reflect differences that existed before intervention. Statistical adjustment can sometimes address measured differences, but it cannot automatically remove unmeasured confounding. The registry record does not report an adjusted analysis or the variables that might have been considered for adjustment.

What does a confidence interval contribute?

In general, a confidence interval communicates uncertainty around an estimated effect under a specified statistical model. It is not a guarantee that the true effect lies within the interval, nor does it address bias caused by design or measurement. Its width helps readers judge precision, while its location helps assess which effect sizes are compatible with the data. No interval is reported for the primary endpoint, so precision cannot be evaluated.

How should p-values be read?

In general, a p-value measures how incompatible the observed data are with a specified null model, under the assumptions of the test. It is not the probability that the null hypothesis is true and does not measure the size or importance of an effect. The registry record reports no p-value or test for the primary outcome. There is therefore no basis for describing the endpoint as statistically significant or not statistically significant.

What do the planning assumptions mean?

The record describes sample-size planning illustrations based on the observed effect, using a two-sided significance level of 0.05, equal allocation between arms, and a normal approximation. These are planning assumptions, not evidence about the observed endpoint. Planning calculations ask what sample size might be needed under stated assumptions; they do not establish the precision or validity of results from the completed study. They are not observed power. The registry record does not report the primary outcome effect used as the basis for these illustrations, nor does it report a trial-specific sample-size justification.

For continuous outcomes, normal-approximation planning generally relies on assumptions about the distribution and variability of the measure and the effect to detect. If outcome values are strongly skewed or contain influential extremes, an analysis or planning approach based on a simple normal approximation may not represent the data well. This is a general consideration, not a reported feature of this endpoint: distributional diagnostics are not reported in the registry record.

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("Arm 1", "Arm 2")
n   <- c(68, 68)
m   <- c(0.038, 0.012)
sp  <- c(0.049, 0.049)
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  Arm 1  68  0.038  0.049  0.026  0.050
CARM  Arm 2  68  0.012  0.049  0.000  0.024

11. Multiplicity, Missing Data and Analysis Populations

The registry record lists one primary outcome measure, the Addiction Severity Index Legal Composite, and zero analyses. It does not report a statistical analysis plan, a hierarchy of outcomes, or a multiplicity adjustment. When several outcomes or repeated tests are examined, the chance of at least one false-positive finding can increase; general approaches to controlling that risk include prespecifying a primary comparison or adjusting the testing procedure. The record does not establish whether or how such procedures were used.

The registry record also does not report missing-data counts, reasons for missingness, or methods for handling missing outcome values. Missingness can affect interpretation if the people with observed outcomes differ systematically from those without them. Complete-case analysis, imputation, and model-based approaches make different assumptions, and none should be attributed to this trial without documentation. The number enrolled does not establish the number with outcome data at the one-year assessment.

Analysis populations are not described. The record does not say whether analyses were intended to follow assigned groups, include only participants who received the intervention, or use another definition. Because allocation was non-randomized, the exact definition of the analyzed groups and any adjustment strategy would be especially important for interpreting a comparison. These details are not reported in the registry record.

12. Safety Results

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

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 adverse event counts of 0 among 71 participants at risk in Arm 1 and 0 among 70 participants at risk in Arm 2. It also lists other adverse event counts of 0 among 71 participants at risk in Arm 1 and 0 among 70 participants at risk in Arm 2. These are the reported counts; they do not provide a full account of safety monitoring or establish that no events occurred outside the record’s reporting.

The deaths field is not reported for either arm. The record does not list serious adverse-event terms, and the listed top serious-event terms are empty. Information about event definitions, ascertainment procedures, follow-up completeness, severity grading, or whether events were judged related to an intervention is not reported in the registry record.

Counts at risk are not the same as a complete description of safety. They do not show how long participants were observed, whether all participants had the same opportunity for event detection, or how missing safety information was handled. The zero counts should therefore be read narrowly as the figures recorded for the specified categories, rather than as proof that treatment posed no risk.

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

The record documents a study intended to address interpersonal violence among people with substance use disorder. It compares a behavioral intervention with usual care and specifies a legal-problem composite as the primary outcome one year post-intervention. The outcome’s scale and direction are described, and the study is marked completed.

What the record does not provide is the primary endpoint result. Without arm-level means, variability, or a comparative estimate, it is not possible to say whether the intervention arm had higher or lower scores, how large any difference was, or how precisely it was estimated. The record therefore does not support a conclusion that the intervention did or did not change legal-problem scores.

The non-randomized design further limits what a comparison could establish. Even if group outcome values were available, differences in participant characteristics or other factors could contribute to observed contrasts. The record does not report an adjustment analysis that would clarify whether measured baseline differences were addressed, and statistical adjustment cannot guarantee removal of unmeasured confounding.

The safety counts are also limited. Zero serious and other adverse events are recorded for each arm among the listed participants at risk, but deaths are not reported and details of safety ascertainment are absent. These figures should not be treated as comprehensive proof of safety.

Accordingly, the study record is informative about the question, design, endpoint, and recorded adverse-event counts, but it does not provide the outcome evidence needed to judge the comparative endpoint findings. The distinction between a completed study and a reported result matters: completion status does not itself reveal what the data showed.

14. Why This Trial Matters Statistically

This trial is statistically notable because its non-randomized design makes the distinction between association and causal effect especially important. A comparison between intervention and usual-care groups may be affected by how participants came to be in each arm. Readers need to know the baseline characteristics, analysis population, and adjustment methods to understand the extent to which an observed difference might reflect treatment rather than pre-existing group differences. Those details are not reported in the registry record.

The endpoint is a continuous measure with an explicitly stated direction. This supports clear interpretation of what a higher score means, but meaningful statistical interpretation still depends on observed means, variability, and an estimate of the between-group contrast. Without those results, neither the magnitude nor precision of the primary outcome can be assessed.

The record also illustrates why registration details and outcome reporting serve different purposes. The design and endpoint entries describe the planned research question, while completed-study results would be needed to evaluate findings. A completion status and enrollment figure cannot substitute for an outcome analysis. Likewise, the recorded adverse-event counts answer a limited safety-reporting question and do not resolve the primary endpoint.

Finally, planning calculations should not be confused with evidence from the completed study. A calculation based on an assumed effect can illustrate sample-size requirements under specified conditions, but it cannot demonstrate that the study had adequate observed precision or that a result is reliable. In this record, the absent outcome analysis leaves those empirical questions unanswered.

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 principal limitation of the registry record for interpretation is that it contains no primary outcome analysis or result. Arm-specific means, standard deviations, numbers analyzed, effect estimates, confidence intervals, and p-values are not reported. As a result, the magnitude, direction, and precision of the registered endpoint comparison cannot be evaluated.

The non-randomized allocation means the arms are not a like-for-like control comparison. The record does not describe why participants received one condition rather than the other, whether baseline characteristics were measured, or whether an adjusted comparison was conducted. Any causal interpretation would need to account for possible confounding, including factors not measured in the study.

Further details needed to assess the study are not reported in the registry record, including intervention content and delivery, recruitment and eligibility procedures, endpoint collection methods, follow-up completeness, missing-data handling, and analysis-population definitions. The record also does not describe a statistical analysis plan or a trial-specific sample-size justification. The planning assumptions listed for illustrations do not replace those details.

Safety interpretation is constrained by the limited adverse-event information. Counts are recorded for serious and other adverse events, but the deaths field is not reported, and event ascertainment, duration of observation, and completeness of reporting are not described. These limitations prevent the recorded counts from serving as a comprehensive safety assessment.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Treating Violence-Prone Substance Use Disorder Patients — NCT00700973.
• Registry record last updated 2015-04-27; status last verified 2014-02.
• Results first posted 2014-09-11.
• 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, parallel, non-randomized study of an Interpersonal Violence Prevention Intervention compared with substance use disorder usual care. It lists Phase 2 and Phase 3, enrollment of 141, and identifies the US Department of Veterans Affairs as sponsor. The study start is listed as 2009-02, with primary completion in 2012-01.

The primary outcome is the Addiction Severity Index Legal Composite, measured one year post-intervention. It is a continuous scale from 0 to 1, with higher scores indicating more severe legal problems. The registry record lists one outcome measure but zero analyses and reports no outcome results.

For safety, zero serious and zero other adverse events are recorded in each arm among the listed participants at risk; deaths are not reported. The non-randomized design and missing outcome analysis limit conclusions about comparative effectiveness and precision.