Violence and Stress Assessment (ViStA) Project to Improve Post Traumatic Stress Disorder Management in Primary Care: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Violence and Stress Assessment (ViStA) Project to Improve Post Traumatic Stress Disorder Management in Primary Care (NCT01401101), a randomized phase 2 study. The primary outcome is PTSD Symptoms.

2. Clinical Question

The trial’s stated purpose was to evaluate a PTSD care-management program intended to improve care processes and outcomes for PTSD among patients seeking primary care. The registry identifies the primary outcome as PTSD symptoms measured at baseline, at 0 months. That timing matters: the posted means describe symptom severity at the start of the measurement period, not a change during follow-up or an effect of receiving care management.

The outcome summaries report a mean CAPS score of 71.1 for PCM and 71.0 for TAU. Their respective 95% confidence intervals are 67.9 to 74.3 and 67.9 to 74.2. The registry also reports a linear regression comparison with p = 0.97, but does not report the regression coefficient or its confidence interval. The record therefore gives a test result, but not an estimated adjusted contrast that can be interpreted in the score’s units.

3. Trial Design

The ViStA Project is registered as a randomized, parallel-group, phase 2 trial. Its masking designation is triple. The registry lists enrollment as 404 and status as completed. The study began in 2010-06, and primary completion is recorded as 2014-02. The registry identifies RAND as the sponsor and stress disorders, post-traumatic as the condition.

The brief summary describes a trial of PTSD Care Management intended to detect, treat, and improve PTSD care processes and outcomes for patients seeking primary care from federally qualified health centers. The PCM intervention is described as having six components, including patient education, screening with written feedback to primary-care clinicians, clinician education on practice guidelines, and structured feedback between primary-care and mental-health clinicians. The remaining component descriptions are incomplete in the registry record.

The registry describes a Minimally Enhanced Usual Care condition that includes clinician education and patient screening without written feedback. However, the primary outcome lists Treatment-as-Usual as the comparison group, while the intervention listing uses MEU. The record does not clarify whether these labels refer to the same comparator or explain the apparent difference. It is therefore safest to retain the outcome’s stated PCM-versus-TAU labels when describing the posted endpoint results, while noting the separate MEU description.

The primary endpoint concerns assessment completers and is recorded at baseline. This is a continuous outcome summarized by group means and 95% confidence intervals. The registry reports a linear regression analysis for the comparison, but does not give its coefficient, model covariates, or confidence interval. Details of the randomization procedure, allocation concealment, masking implementation, and statistical analysis plan are not reported in the registry record. The designation of the trial as randomized and triple masked does not by itself provide those operational details.

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: all patients who completed the assessment

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: We randomized 206 patients to the PCM condition and 198 to the ECE conditions. However, only 355 patients of the 404 patients randomized completed the baseline survey, So, 49 patients have missing data in the evaluation.

6. Primary Endpoint

The registry lists the primary outcome as PTSD Symptoms, measured over 0 months (baseline).

The primary endpoint is PTSD symptom severity measured with the Clinician-Administered PTSD Scale (CAPS). The registry describes the score as the sum of frequency and intensity ratings across each of the 17 symptom items. Each item rating ranges from 0 to 4, and the possible total score ranges from 0 to 136; a higher score indicates greater symptom severity. The unit is CAPS scores, and the endpoint is recorded at 0 months, identified as baseline.

A clinician-administered symptom scale provides a defined way to quantify severity rather than relying on an unstructured description. Summarizing the score as a group mean gives a measure of average symptom burden among participants who completed the assessment. The 95% confidence interval around each mean conveys uncertainty in that group’s estimated average; it is not an interval for an individual participant’s score and is not itself a comparison between groups.

Here, the registry reports mean baseline scores of 71.1 for PCM and 71.0 for TAU. The endpoint’s baseline timing limits what these values can say: they characterize the groups at the recorded starting assessment, rather than symptom change or outcomes after the care-management program. The registry does not post a secondary outcome result in this record, and the primary endpoint description does not include a later assessment time.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous: it is a numerical symptom score, summarized with a mean. The registry gives a mean and a 95% confidence interval for each group. A group mean describes the average score among the participants included in that group’s assessment summary. It does not show the full distribution of scores; participants with very different scores can contribute to the same mean.

What do the confidence intervals describe?

A confidence interval is a range of values compatible with the data and the method used to estimate a quantity. In repeated use of the same method under its assumptions, confidence intervals at a stated confidence level are designed to cover the underlying quantity at that rate. This general interpretation concerns the method over repeated samples; it does not mean there is a 95% probability that a particular fixed value lies inside the interval after it has been calculated.

The intervals reported for this outcome are attached to separate group means: 67.9 to 74.3 for PCM and 67.9 to 74.2 for TAU. They are not the confidence interval for the contrast. A direct group comparison needs an estimate of the contrast and its uncertainty, derived using the comparison method. That estimate and interval are not reported in the registry record. The visual or numerical overlap of separate mean intervals is not a substitute for the model-based comparison.

What does the regression p-value mean?

The reported method is linear regression, and the registry gives p = 0.97 for the PCM-versus-TAU analysis. In general, linear regression models a continuous outcome as a function of one or more explanatory variables. A group comparison can be represented as a coefficient for group membership, but the registry does not report that coefficient. It also does not report covariates or other model specifications. The p-value alone therefore does not reveal the estimated score contrast, its direction, or its precision.

A p-value evaluates compatibility with a null hypothesis under the model and its assumptions. It is not a measure of effect size, does not describe the probability that chance alone caused the finding, and does not prove that there is no meaningful difference. Interpretation also depends on the analysis plan, outcome definition, and data quality. Those details are not fully available in the registry record.

Why are no recalculated comparison statistics available?

A simple unadjusted comparison can sometimes be recalculated from group summary statistics when the necessary information is posted. The registry record indicates that values are missing or not estimable for a two-arm comparison of this continuous endpoint. Accordingly, no recalculated contrast, confidence interval, or p-value is reported. The group means and their intervals remain descriptive summaries, not a substitute for the missing comparison estimate.

Why does over-dispersion matter in general?

Over-dispersion is a general concern for count outcomes when the observed variability is greater than a model’s assumptions allow. A continuous CAPS score is not a count endpoint, and the registry’s primary analysis is described as linear regression. Over-dispersion is therefore not a feature that can be assessed from the posted primary endpoint summaries. More generally, choosing a model that reflects the outcome’s distribution and variability is important because model assumptions affect standard errors, confidence intervals, and tests.

What do planning illustrations mean?

Sample-size planning illustrations are not observed power and do not report what the trial achieved. In general, such illustrations ask how many participants per arm might be needed under stated assumptions to detect a specified effect with a chosen significance level and power. The registry’s stated illustration assumptions use a two-sided significance level of 0.05, equal allocation, a normal approximation, and an effect defined as a fraction of the observed effect. Those are planning assumptions, not details of the trial’s own design justification. No planning result should be treated as evidence that the trial had adequate power, and a planning illustration does not replace an estimated effect and confidence interval.

The registry does not report the protocol’s sample-size justification, interim analyses, detailed statistical plan, regression coefficient, or contrast interval. These omissions limit independent assessment of the analysis and its precision. They do not change the meaning of the reported mean scores or p-value, but they restrict what can be concluded beyond those posted summaries.

10. Analyses Reported by the Sponsor

The registry reports a linear regression analysis for the PCM and TAU comparison, with p = 0.97. It does not report the regression coefficient or a confidence interval for the comparison. The posted group means and their separate confidence intervals do not contain enough information to reconstruct the regression result or a direct unadjusted contrast with its uncertainty. The registry also indicates that values are missing or not estimable for a two-arm comparison of this continuous endpoint, so no recalculated comparison is available.

Accordingly, the registry’s reported regression result is the only posted inferential comparison to describe. The p-value should be read as a test result under an analysis whose full specification is not reported, rather than as an estimate of the difference in CAPS points. The baseline means remain useful descriptive information, but they cannot fill the gap left by the absent regression coefficient and interval.

No discrepancy is flagged between a recalculation and the reported analysis; no recalculation is available to compare. The registry record does not explain whether or how covariates were included in the regression. It is therefore not possible to assess how the reported test relates to a hypothetical unadjusted analysis, or to reproduce the sponsor’s analysis from the posted summaries.

11. Multiplicity, Missing Data and Analysis Populations

The registry lists three outcome measures and three analyses, while no secondary outcome result is posted in this record. The listed primary endpoint is baseline PTSD symptoms. The record does not describe a multiplicity adjustment, a hierarchy of outcomes, or how multiple analyses were handled. Such procedures are not reported in the registry record, so it is not possible to determine whether the reported p-value was adjusted or how it fits into a broader testing strategy.

The primary outcome population is described as all patients who completed the assessment. The posted group summaries include 184 PCM assessment completers and 171 TAU assessment completers. These are endpoint-specific analysis counts; they should not be treated as the full randomized population or as an account of all participants’ outcome status. The registry lists enrollment as 404, but does not explain the relationship between enrollment and the endpoint assessment population.

The record does not report how many participants lacked the baseline assessment, why assessments may have been unavailable, whether missing outcomes were imputed, or whether any sensitivity analyses were conducted. It also does not give an intention-to-treat analysis population or a detailed account of exclusions. These details are important because an analysis limited to assessment completers may differ from an analysis of all randomized participants if completion is related to group assignment or outcome values. Whether that occurred cannot be determined from the registry record.

The baseline timing is relevant to missing-data interpretation as well. The posted endpoint is not described as a change score or later follow-up measure, and the record does not provide a sequence of outcome measurements with which to assess longitudinal missingness. The absence of those details does not demonstrate that missing data biased the result; it means the potential cannot be evaluated from the reported information.

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.

Most frequent non-serious adverse event terms

The registry reports serious adverse events among participants at risk as 0 for PCM and 0 for TAU. It reports other adverse events as 20 for PCM and 23 for TAU. The number at risk is recorded as 206 in PCM and 198 in TAU for both serious and other adverse events. These are posted event counts and at-risk figures, not estimates of comparative risk.

The registry does not provide serious adverse event terms, and death counts are not reported. It also does not provide a definition of the “other” category, a breakdown of its events, event severity, timing, or a formal statistical comparison. Without those details, the counts cannot show whether event types or patterns differed meaningfully between groups. Zero reported serious events in the posted figures should be read as the recorded count, not as proof that serious events were impossible or that all safety concerns were excluded.

These safety summaries are separate from the primary baseline CAPS endpoint. The registry does not describe the safety counts as evidence about symptom change or effectiveness. They are descriptive figures whose interpretation is limited by the level of detail posted.

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

The result establishes what the registry reports about the baseline assessment: mean CAPS scores were 71.1 for PCM and 71.0 for TAU, with the posted group-specific 95% confidence intervals. It also establishes that the registry reports a linear regression comparison with p = 0.97. These findings describe the recorded baseline scores and the reported test; they do not estimate a change in symptoms after the intervention.

The p-value does not show that the groups were equivalent, and it does not quantify the size of a difference. The absence of a reported regression coefficient and confidence interval means the precision of the direct comparison cannot be read from the registry record. A conclusion about equivalence would require a specified equivalence framework and margin, which are not reported. Similarly, a non-small p-value alone cannot establish that the groups had no difference.

The result does not show whether PCM improved PTSD care processes, reduced symptom severity, or changed later outcomes. Although the study summary describes those aims, the posted primary endpoint is measured at baseline. The registry record does not include a reported follow-up primary outcome result in the information. The baseline data cannot be used as a substitute for a post-intervention comparison.

The posted counts also do not establish a comparative safety profile. They report no serious adverse events in the two listed groups and report other adverse events in each, but do not include event details or a formal comparison. Deaths are not reported. These omissions limit interpretation without showing that a safety problem occurred or did not occur.

Finally, interpretation is constrained by incomplete analysis and population details. The registry does not report the regression specification, the sample-size justification, missing-data procedures, or a detailed multiplicity plan. It also uses TAU for the outcome comparator while separately describing an MEU condition. These limitations call for a narrow reading: the registry posts baseline group summaries and a regression p-value, not a complete account of treatment effects or the analysis needed to reproduce them.

14. Why This Trial Matters Statistically

This trial illustrates why the timing and definition of an endpoint matter as much as the name of the intervention. PTSD symptoms are the primary outcome, but the registry records that outcome at baseline. Baseline scores can describe the participants’ measured starting symptom severity; they cannot establish how symptoms changed after care management. Keeping that distinction clear prevents an initial group comparison from being mistaken for a treatment-effect estimate.

It also shows why group means and their confidence intervals should be distinguished from a contrast estimate. The reported intervals quantify uncertainty around separate group means. The registry’s regression p-value gives an inferential result, but without a coefficient and interval it does not show the size or precision of the comparison in CAPS points. Reporting all of these quantities together would support a fuller interpretation; the posted record does not include all of them.

The record further highlights the value of consistent group labels. It describes MEU as a condition but labels the primary outcome comparator TAU. Without clarification, readers cannot tell from the registry record whether those labels refer to the same care condition. Naming the comparator consistently matters for understanding what contrast an analysis represents.

Finally, the outcome population is defined as assessment completers, while the registry also reports overall enrollment. Those details serve different purposes. A clear account of missing assessments and the analysis population would help readers assess how the endpoint summaries relate to the randomized trial. This is not a claim that the reported result is biased; it is a reminder that statistical interpretation depends on knowing who contributed data and how the comparison was estimated.

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 important endpoint limitation is its timing: PTSD symptoms are reported at baseline, not as a change or later outcome. The reported means therefore do not evaluate the effect of PCM on subsequent symptoms. The registry’s broader study aims include care processes and outcomes, but the posted primary result does not supply a follow-up treatment-effect estimate.

The inferential comparison is incomplete for independent interpretation. The registry gives the method as linear regression and reports p = 0.97, but does not report the coefficient, its confidence interval, the model covariates, or other specification details. Values are indicated as missing or not estimable for a two-arm recalculation of this continuous endpoint. As a result, the comparison’s estimated magnitude and precision cannot be reconstructed from the posted group summaries.

The analysis population is restricted by the endpoint description to patients who completed the assessment. The registry does not report the missing-assessment count or reasons, imputation, sensitivity analyses, or the relationship between those completing the endpoint and the full randomized population. The record also does not report the protocol’s sample-size justification, interim analyses, or detailed statistical plan. Its planning assumptions should not be mistaken for the trial’s own design rationale or evidence of observed power.

There is also a comparator-label ambiguity: the outcome lists TAU, while the intervention description lists MEU and describes its components. The registry record does not clarify the relationship between those names. Safety reporting is limited to counts, without event terms for serious events, detail on other events, or death counts. These omissions narrow what can be concluded from the registry; they do not establish that any unreported procedure or event did or did not occur.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Violence and Stress Assessment (ViStA) Project to Improve Post Traumatic Stress Disorder Management in Primary Care — NCT01401101.
• Registry record last updated 2016-09-02; status last verified 2016-07.
• Results first posted 2016-09-02.
• 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 completed ViStA Project is registered as a randomized, triple-masked, parallel, phase 2 trial sponsored by RAND. It lists enrollment as 404 and describes a PTSD Care Management intervention for patients seeking primary care from federally qualified health centers. The primary endpoint is baseline CAPS symptom severity among assessment completers.

The registry reports mean scores of 71.1 for PCM and 71.0 for TAU, with group-specific 95% confidence intervals, and a linear regression p-value of 0.97. It does not report the regression coefficient or its confidence interval, and the record indicates that a two-arm recalculation is not available. The baseline endpoint does not establish post-intervention change. Missing-data procedures and full model details are not reported in the registry record. The outcome’s TAU comparator label is not reconciled with the separate MEU description.