Mindfulness for Anger in Veterans With PTSD: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Mindfulness for Anger in Veterans With PTSD (NCT02882802), a randomized na study. The primary outcome is State Anger Scale.

2. Clinical Question

3. Trial Design

This completed study is a randomized, parallel-group behavioral trial sponsored by the VA Office of Research and Development. The registry reports enrollment of 61 participants and phase as NA. The trial began on 2017-12-01, and primary completion was recorded as 2023-01-31. Masking is listed as none. That means the registry does not describe blinded treatment assignment; it does not, by itself, establish whether any particular assessment or analysis was conducted without knowledge of group assignment.

The two interventions were Mindfulness Based Stress Reduction and the Trauma Recovery Education Class. Both are described as group-based behavioral approaches, although the intervention descriptions in the registry record are incomplete. The summary presents mindfulness as a potential way to support regulation of difficult emotions and reduce physiological reactivity. The education class is described as providing information on PTSD and traumatic reactions. These are descriptions of the interventions and rationale, not evidence of comparative effects.

The primary outcome was measured at baseline, after 3 weeks of treatment, after 6 weeks of treatment, within 8 weeks following completion of either treatment, and within 5 months after the post-treatment assessment. The record notes that not all participants completed assessments at all time points. The trial therefore planned repeated assessments, but the record does not provide the number of observations available for each group at each time point.

The registry lists 16 outcome measures and 14 analyses. It does not explain how those measures or analyses relate to a prespecified testing hierarchy. The allocation method beyond randomized assignment, details of treatment delivery, adherence, and the statistical analysis plan are not reported in the registry record. The posted primary outcome results and the analysis comparing groups are also not reported, so the design can be described but its efficacy findings cannot be evaluated from this 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.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Not all participants completed assessments at all time points.

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 State Anger Scale, measured over Baseline, after 3 weeks of treatment, after 6 weeks of treatment, within 8 weeks following the completion of either of the two treatments (i.e., post-treatment), and within 5 months after completing the post-treatment assessment.

The primary endpoint is the State Anger Scale, a self-report measure of overall state anger using the State-Trait Anger Expression Inventory-2. Its score range is 15-60, with higher scores indicating greater state anger. A continuous score preserves distinctions across the scale rather than reducing participants to categories such as having or not having anger. This can make changes in measured anger visible as differences in scores, provided the results and analysis are reported.

The registry lists the measure at baseline, after 3 weeks of treatment, after 6 weeks of treatment, within 8 weeks following treatment completion, and within 5 months after the post-treatment assessment. These repeated measurements can describe the course of reported state anger over time. They also raise analytic questions about how repeated observations, differences at baseline, and incomplete follow-up are handled. The registry record does not report those analysis details.

Self-report is relevant because the endpoint concerns a participant's reported state of anger. It is not the same as a direct count of aggressive acts or an independent assessment of behavior. The registry summary discusses anger and aggression as related concerns, but the primary outcome specified in the record is state anger. No primary outcome means, standard deviations, group contrasts, confidence intervals, or p-values are reported in the registry record. The endpoint's definition and schedule are available, but the magnitude and precision of any treatment-group difference are not.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

Statistical methods determine how measurements are converted into a comparison and how uncertainty is represented. The registry identifies a randomized parallel-group design and a continuous primary measure summarized as a mean with standard deviation. However, it does not report the statistical method used for the primary outcome, the effect estimate, or its uncertainty. The following concepts are general explanations, not claims about the method used in this trial.

What does a mean describe?

For a continuous scale, the mean describes the arithmetic average of observed scores in a group. It is useful for describing the center of a distribution, but does not show how scores are spread or whether the distribution is symmetric. A standard deviation describes dispersion among observed scores. It is not the same as the uncertainty around a mean or treatment contrast: that uncertainty also depends on how much information is available and on the analysis model.

A mean difference compares group averages on the scale of measurement, which can be easier to interpret than a standardized quantity when the score's units are meaningful. A change-from-baseline comparison and a comparison of scores at a follow-up visit answer related but not identical questions. An adjusted analysis may account for baseline scores or other prespecified variables, while an unadjusted comparison does not. The registry record does not report which form of comparison was used.

How can repeated measurements be analyzed?

Repeated scores from the same participant are related: they are not independent observations. A statistical model for repeated measurements can account for this within-participant relationship and may estimate group differences at particular visits, an overall group pattern over time, or a group-by-time interaction. Those targets answer different questions. For instance, a difference at a particular follow-up visit is distinct from evidence that the groups followed different trajectories across the assessment schedule. The registry record does not report a repeated-measures model, a chosen contrast, or a treatment-by-time test.

Some analyses use only one selected follow-up measurement, while others incorporate multiple measurements. Selecting a single time point can be straightforward to communicate, but it may discard information from the rest of the schedule. Using multiple measurements can improve the use of available data under suitable assumptions, but the model must represent the correlation and missingness appropriately. No such model details are reported in the registry record.

What do confidence intervals and p-values contribute?

A confidence interval expresses uncertainty around an estimated contrast. Its width reflects both the variability in the outcome and the information available under the analysis. A narrow interval indicates greater precision than a wide interval, but interpretation still depends on the measurement and the question being asked. A p-value is not the probability that a treatment works, nor does it quantify the size of a difference. It is interpreted in relation to a statistical model and a prespecified hypothesis. Neither confidence intervals nor p-values for the primary outcome are reported in the registry record.

Statistical significance and practical importance are different considerations. A small estimated contrast can be statistically distinguishable from a null value while having limited practical importance, and an imprecise estimate can leave substantial uncertainty even if it is not statistically significant. Interpreting the score difference would require the actual estimate, uncertainty, and relevant context. Those results are not reported in the registry record, so no such interpretation is possible.

Why can over-dispersion matter?

General explanation: over-dispersion arises when observed variability is greater than a statistical model assumes. It is especially relevant for count outcomes when a model expects more uniform variation than the data exhibit. If the model underestimates variability, uncertainty can be understated and inferential results can appear more certain than warranted. The primary endpoint in this trial is a continuous self-report scale rather than a count outcome. The registry record does not report a model or a dispersion assessment, so over-dispersion is not an identified feature of the reported primary analysis.

What does the planning illustration mean?

The registry's sample-size assumptions describe 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. These assumptions are not a report of the trial's original design justification. The record does not report the trial's own sample-size justification, its prespecified target effect, or whether an interim analysis was planned or conducted. Planning illustrations estimate participants per arm for a chosen power under specified assumptions; they are not observed power and do not establish that a trial did or did not detect an effect. Any such illustration depends on the effect assumption and analysis simplifications, so it should not be read as a trial result.

The registry does not report enough information to assess model diagnostics, covariate adjustment, handling of repeated observations, or the analysis population. These are central parts of statistical interpretation, not details that can be inferred from a randomized label or from the outcome scale alone.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists 16 outcome measures and 14 analyses, and the primary outcome involves assessments at multiple time points. Testing several outcomes, visits, or contrasts can increase the chance of finding a nominally noteworthy result by chance if each is interpreted independently. General approaches to multiplicity include defining a primary contrast in advance, ordering tests hierarchically, or adjusting inferential thresholds. The registry record does not report a multiplicity strategy, a testing hierarchy, or which contrasts were designated confirmatory.

The primary outcome is not reduced to one comparison in the analysis summary. As a result, there is no single primary estimate in the posted record to interpret alongside the other reported analyses. The registry does not report whether any analyses were exploratory, whether outcome or time-point selection changed, or how multiplicity was addressed. These details should not be assumed from the number of listed outcomes or analyses.

Missing observations are an additional concern because the record states that not all participants completed assessments at all time points. The numbers assessed at each visit, the reasons assessments were missing, and the method used to handle missing data are not reported in the registry record. Complete-case analysis, imputation, likelihood-based methods, and other approaches rely on different assumptions. No approach can be attributed to this trial based on the available record.

The analysis population is also not described. The record does not say whether the primary analysis included all randomized participants, only participants with observed outcomes, or another defined group. Without that information, the population represented by any hypothetical estimate cannot be specified. These reporting gaps limit assessment of both bias and precision.

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.

Most frequent serious adverse event terms

Serious events with the highest arm-level rate: self-injury (3.8%), covid-19 (2.9%).

The registry lists serious adverse events by intervention group. For Mindfulness Based Stress Reduction, 2 participants were affected among 35 at risk; for the Trauma Recovery Education Class, 1 was affected among 26 at risk. Other adverse events are listed as 0 among 35 at risk in the Mindfulness Based Stress Reduction group and 0 among 26 at risk in the Trauma Recovery Education Class group. Deaths are listed as 0 in both groups.

These figures are counts, not a complete description of the events or their timing. The listed serious-event terms include Self-injury at 3.8% and COVID-19 at 2.9%. The registry record does not report the denominator or further context for those term percentages, nor does it provide a detailed account of event timing, severity, relatedness, or participant-level overlap. The terms should not be assigned to a group or interpreted as a rate without that information.

Serious adverse event counts are not a formal comparison of treatment safety. Differences in counts can reflect the number at risk, follow-up, definitions, and chance. The posted figures do not establish causation or comparative risk, and they do not replace a detailed safety analysis. They are also separate from the State Anger Scale outcome and cannot be used to infer whether anger changed.

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

The registry record supports a description of the trial's design and planned outcome: a randomized, unmasked, parallel-group comparison of Mindfulness Based Stress Reduction and a Trauma Recovery Education Class, with repeated State Anger Scale assessments. It also reports enrollment of 61 participants, a completed status, and a note that not all participants completed assessments at every time point. These registry entries describe the study, not the outcome of the comparison.

The record does not report group means, standard deviations, changes from baseline, treatment contrasts, confidence intervals, or p-values for the primary endpoint. It therefore cannot show whether measured state anger differed between groups, how large any difference was, or how precisely it was estimated. The rationale for testing mindfulness and the existence of repeated assessments cannot substitute for these results.

The endpoint captures self-reported state anger. It is not itself a measure of aggressive acts, and a difference in scale scores would not automatically establish a difference in aggression or in broader consequences associated with anger. The registry summary discusses both anger and aggression, but the specified primary measure is state anger. Any conclusion about outcomes beyond that measure would require appropriate evidence.

Likewise, the serious adverse event counts are descriptive and do not establish that an event was caused by an intervention. Their interpretation is limited by the absence of details about event timing, attribution, and the context of the listed terms. The registry record cannot support a medical recommendation or a claim that either intervention is superior. It establishes that the comparison was undertaken and completed, while leaving the primary comparative result unreported.

13. Why This Trial Matters Statistically

This trial raises several important statistical issues for clinical research. Its primary measure is continuous and was scheduled repeatedly, so a clear interpretation depends on defining the target comparison: a difference at a particular follow-up, an average difference across visits, or a difference in the pattern over time. Those questions are not interchangeable. Reporting the chosen estimand, model, and contrast is necessary for readers to understand what the analysis represents.

Incomplete assessments matter for repeated outcomes. The registry notes that participants did not all complete every time point, but does not report the amount or pattern of missing data or the method used to address it. Transparent reporting of observed data and missingness is important because conclusions can depend on assumptions about unobserved scores.

The listing of multiple outcomes, analyses, and time points also makes prespecification and multiplicity relevant. Clear identification of confirmatory comparisons helps readers distinguish the primary question from exploratory analyses. Without a reported hierarchy or adjustment approach, the registry record does not permit evaluation of how multiple testing was handled.

Finally, design information and outcome evidence serve different purposes. Randomization can support a causal comparison when the analysis and follow-up are appropriately handled, but it does not disclose the treatment effect. The completed status and serious-event counts likewise do not answer the primary question. Results with estimates and uncertainty, alongside analysis and missing-data details, are needed to evaluate what this trial found.

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.

The most important limitation for interpreting this trial from the registry record is the absence of posted primary outcome results. The State Anger Scale is defined, and its assessment schedule is described, but the group data and comparative estimates are not reported. There is no basis in the record for describing the direction, magnitude, or precision of the primary outcome contrast.

The record also notes incomplete assessment at some time points without reporting how many observations were missing by group and visit, why they were missing, or how they were handled analytically. That prevents assessment of whether the available measurements provide a comparable picture of the randomized groups over time.

The intervention descriptions are incomplete, limiting the detail available about what participants received. The registry does not report adherence, treatment exposure, or whether intervention delivery differed from the intended approach. It also does not provide the detailed eligibility criteria or participant characteristics needed to judge how closely enrolled participants match the broader population of interest.

Masking is listed as none, and the primary outcome is self-reported. This combination can be relevant when considering how treatment awareness might influence reporting, but the record does not report whether outcome collection or analysis included safeguards against such influence. This is a design consideration, not evidence that reported scores were biased.

Multiplicity procedures, the primary analysis population, and the statistical model are not reported. The listed serious events also lack detail on timing, attribution, and event-level context. These limitations constrain interpretation of both the primary outcome and safety figures; they do not establish that the trial was conducted improperly.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Mindfulness for Anger in Veterans With PTSD — NCT02882802.
• Registry record last updated 2026-05-01; status last verified 2026-04.
• Results first posted 2026-05-01.
• 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 a completed randomized, unmasked, parallel-group behavioral trial sponsored by the VA Office of Research and Development. Enrollment was 61, and the listed interventions were Mindfulness Based Stress Reduction and the Trauma Recovery Education Class. The primary endpoint was the State Anger Scale, assessed from baseline through post-treatment follow-up. The record states that some participants did not complete assessments at all time points.

Serious adverse events were recorded for both groups, and deaths were listed as 0 in each group. The registry lists 16 outcome measures and 14 analyses. However, primary State Anger Scale results, comparative estimates, uncertainty measures, and details of the statistical analysis are not reported in the registry record. The study's design and outcome schedule can be described, but the primary comparative finding cannot be determined from the posted registry information.