Trauma-Focused Equine-Assisted Therapy (TF-EAT) for Veterans With PTSD: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Trauma-Focused Equine-Assisted Therapy (TF-EAT) for Veterans With PTSD (NCT03068325), a na na study. The primary outcome is Change From Baseline in Clinician-Administered PTSD Scale at 8 Weeks.

2. Clinical Question

In statistical terms, this is a question about change over time within a group receiving an intervention, not a randomized estimate of the intervention’s effect relative to a concurrent control. A change from baseline can describe how participants’ measured scores shifted during the study period. By itself, it cannot determine how those scores would have changed over the same period without the intervention. The registry record does not report a control group, allocation procedure, or a comparative estimate.

The study description frames EAT-PTSD as an approach of interest for veterans who may find other treatment modalities ill-suited, ineffective, or undesirable. That context explains why feasibility and acceptability were study aims, but the record does not provide numerical findings for those aims. The primary outcome listed is symptom severity measured with CAPS-5; it is not a direct measure of feasibility or acceptability. Those questions require their own reported outcomes and methods, which are not reported in the registry record.

3. Trial Design

The registry record describes a completed, single-group study of EAT-PTSD for veterans with PTSD. Enrollment was 63. The study began in 2016-04, had primary completion in 2019-07, and is listed as completed. The intervention is classified as “OTHER,” and the record lists phase as NA.

The model is single group, and allocation is listed as NA. Masking is listed as NONE. These design features mean that the registered study does not describe random assignment between treatment groups or a blinded comparison. With no concurrent control group listed, the design can describe outcomes among participants who received EAT-PTSD, but it cannot by itself separate changes during the study from changes that might have occurred over time for other reasons.

The intervention description calls EAT-PTSD manualized. Its stated aims include increasing awareness of emotions in oneself and others, improving communication, helping regulate emotional responses, supporting critical thinking and problem solving, and increasing confidence and self-efficacy while engaging with horses. The overall study description says that a psychotherapist and equine specialist work together with participants through structured interventions or activities. The registry record does not report further details about treatment delivery, attendance, adherence, or variation in the intervention received.

The listed primary outcome is change from baseline in CAPS-5 at 8 weeks. The registry record identifies one outcome measure but lists zero analyses. It does not report a numerical primary outcome, a statistical estimate, a confidence interval, or a p-value. It also does not report the statistical analysis plan, the sample-size justification, interim analyses, or analysis populations. These missing details limit how fully the design and intended analysis can be reconstructed from the registry record.

The study description identifies feasibility, acceptability, safety, and preliminary efficacy as aims. Those aims should not be treated as interchangeable. Feasibility and acceptability concern whether the intervention can be delivered and how it is received; safety concerns adverse events; and symptom change is the listed primary outcome. The registry record does not give numerical results for feasibility or acceptability. The safety figures are described separately, while the CAPS-5 result is not reported.

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.

Before assignment: Ninety-seven individuals were assessed for eligibility in the study, but 34 were excluded as a result of not meeting study inclusion criteria, leaving 63 participants to proceed into study enrollment.

Overall Study

Reasons for not completing this period:

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 Change From Baseline in Clinician-Administered PTSD Scale at 8 Weeks, measured over 8 weeks.

The primary endpoint is change from baseline in Clinician-Administered PTSD Scale for DSM-5 (CAPS-5) score at 8 weeks. CAPS-5 is administered in a clinical interview and assesses PTSD symptom severity. The registry record describes a severity range of 0-80, with higher scores indicating more severe PTSD. The outcome is a continuous measure, and the registry identifies the planned summary as a mean with standard deviation.

Change from baseline is used to describe the direction and amount of score movement over the follow-up period within the study group. A mean change summarizes the average shift across participants with outcome data; a standard deviation describes how dispersed individual changes are around that average. These are distinct pieces of information: the mean does not show whether participants’ individual changes were similar, while the standard deviation does not indicate the direction of the average shift.

CAPS-5 is relevant to the stated clinical question because the study concerns PTSD symptoms and the outcome directly assesses symptom severity through an interview. The scale’s stated direction also matters for interpretation: higher scores indicate greater severity, so the meaning of a change depends on its direction. However, the registry record does not report the baseline mean, the 8-week mean, the mean change, its standard deviation, or any uncertainty interval. No direction or magnitude of observed symptom change can therefore be described from the registry record.

Even when a within-group change is available, it is not the same as a treatment-versus-control effect. A before-and-after comparison describes measured change among participants in the study. Without a comparison group, that change cannot isolate the contribution of the intervention from other influences over time.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

Statistical interpretation begins with the question the design can address. This study is registered as a single-group study, with no allocation to a comparison arm. Its primary endpoint is change from baseline in CAPS-5 score at 8 weeks. A within-group analysis would describe change over time among participants, while a randomized comparative analysis would estimate a difference between assigned groups. These are different estimands and should not be treated as equivalent.

What does a mean change describe?

The registry identifies the endpoint as continuous and specifies a mean with standard deviation. In general, a mean change is the average of participants’ changes from baseline to follow-up. It summarizes the group’s central shift on the measured scale. The standard deviation describes the spread of those individual changes around the mean. A mean can be close to zero even when individuals have substantial changes in opposite directions, so the spread provides useful context. Neither statistic is reported numerically for the primary endpoint in the registry record.

For CAPS-5, higher scores indicate more severe PTSD, according to the endpoint description. Thus, the direction of a mean change would be necessary to interpret whether the group’s average score moved toward higher or lower measured severity. The scale range of 0-80 describes the possible score range, not the scores observed in this study. Without the baseline and follow-up results, the direction and magnitude of change remain unknown.

Why does a control group matter?

General statistical reasoning distinguishes observed change from treatment effect. In a single-group study, the observed change combines any intervention-related change with other changes that occur over time. A concurrent control group can help estimate the change that would have occurred without the intervention, especially when participants are assigned comparably. This registry record does not list such a group or a randomized allocation process. Therefore, a within-group result, if reported elsewhere, would not alone establish that the intervention caused the change.

Possible influences on a before-and-after result include changes in symptoms unrelated to the intervention, concurrent services, expectations, repeated assessment, and regression to the mean. These are general considerations rather than reported events in this trial. Regression to the mean is the tendency for unusually high or low measurements to be less extreme on repeat measurement, even without a specific intervention effect. The registry record does not describe whether or how such influences were addressed analytically.

How should uncertainty be understood?

In general, a confidence interval communicates uncertainty around an estimate under the chosen statistical model. It is useful alongside a point estimate because an estimated mean change alone does not show how much sampling uncertainty remains. A p-value, when reported, addresses compatibility between observed data and a specified null model; it does not give the probability that a treatment works or the size of a clinically important effect. The registry record reports neither a confidence interval nor a p-value for the CAPS-5 endpoint, so these aspects of the evidence cannot be assessed.

The observed spread and the uncertainty around the mean are not the same. Standard deviation describes variability among individual observations; a confidence interval for a mean describes uncertainty about the group mean. In general, the latter depends on the data and analysis approach. Neither should be substituted for the other. No numerical dispersion or uncertainty estimate for the primary outcome is reported in the registry record.

What do the planning assumptions mean?

The sample-size assumptions describe a planning illustration, not the design justification for this study. The illustration is described as using a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and an effect to detect stated as a fraction of the observed effect. In general, a significance level is a threshold used when evaluating data under a statistical test; a two-sided test allows departures in either direction. Equal allocation is a hypothetical way of distributing participants between two comparison arms. These assumptions do not describe the registered single-group design.

Sample-size calculations are conditional on their assumptions, including the outcome variability, the effect size selected for planning, and the analysis. A planning illustration does not show what effect was observed, does not establish that the study was adequately powered, and is not observed power. The registry record does not report the actual numerical planning results or a sample-size justification for the trial. No observed primary outcome is available in the registry record from which to evaluate those assumptions.

Why can over-dispersion matter?

General explanation: over-dispersion occurs when the variability in observed data is greater than a statistical model assumes. If that extra variability is ignored, standard errors can be too small and confidence intervals too narrow, creating unwarranted precision. The primary outcome is identified as continuous, with a mean and standard deviation, and the registry record does not report an analysis model or indicate that over-dispersion was assessed. This concept is therefore general context, not a finding about this study.

For this continuous outcome, the registry’s stated summary is the mean and standard deviation; it does not specify a model, adjustment variables, treatment of repeated observations, or a method for handling incomplete follow-up. Those details are not reported in the registry record. Without them, readers cannot reproduce an analysis or assess whether its assumptions were checked.

What can the listed analysis count tell us?

The registry record lists one outcome measure and zero analyses. This indicates that the record does not include an analysis result for the listed primary endpoint. It does not supply an inferential estimate, a confidence interval, or a hypothesis test. The number of registered outcome measures should not be taken as evidence that all relevant outcomes or analysis details are reported.

10. Multiplicity, Missing Data and Analysis Populations

Multiplicity concerns arise when several outcomes, time points, treatment contrasts, or statistical tests are examined. In general, the more tests that are considered, the greater the chance that at least one appears notable by chance if no adjustment or other prespecified strategy is used. This is a general statistical concern, not a claim that a particular multiplicity problem occurred in this study.

The registry record lists one outcome measure and zero analyses. It does not report a multiplicity strategy, an adjustment method, or a hierarchy for interpreting multiple tests. The listed primary endpoint is change from baseline in CAPS-5 at 8 weeks, but the record does not provide a numerical result or analysis for it. Other outcome definitions and results for feasibility or acceptability are not reported in the registry record. The absence of a reported multiplicity approach should not be read as proof that no such approach was used; its use is not reported in the registry record.

Missing-data methods are also not reported in the registry record. It does not state how many participants contributed baseline or 8-week CAPS-5 data, how missing follow-up measurements were handled, or whether any sensitivity analyses were conducted. Enrollment of 63 does not establish that all enrolled participants had complete endpoint data. Without the analysis population and missing-data information, readers cannot determine whether the endpoint summary, if available elsewhere, represents all enrolled participants or a subset.

The record does not report an intention-to-treat population, a per-protocol population, or another named analysis population. It also does not provide details about exclusions after enrollment, adherence criteria, or the handling of participants who discontinued. These omissions limit assessment of selection and attrition. A statistical estimate can be affected when outcome availability is related to participant characteristics or outcomes; this is a general concern, not a reported event in this study.

The registry record also does not report interim analyses, a prespecified statistical analysis plan, or methods for dealing with repeated measurements. The absence of those details means the analytic decisions cannot be evaluated from this record. It does not establish what decisions were or were not made outside the registry record.

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.

The registry safety figures list 63 participants at risk for serious adverse events and 0 serious adverse events. The same group lists 63 at risk for other adverse events and 0 other adverse events. Deaths are listed as 0. These are the counts recorded for the EAT-PTSD group.

“At risk” describes the denominator used for these registry counts; it does not establish that every participant had complete safety follow-up for the same duration. The record does not provide further information about safety surveillance, event definitions, ascertainment procedures, follow-up completeness, or whether events were judged related to the intervention. No serious adverse event terms are listed.

Zero events in the registry record means no events are recorded in these categories for this group. It does not prove that the risk of an event is absent, nor does it establish comparative safety, because no control group is listed. In general, safety interpretation depends on the size of the population observed, the length and completeness of follow-up, and how events were collected. Those details are not reported in the registry record. The counts should therefore be read as registry-reported observations, not as evidence that an event could not occur or that one intervention is safer than another.

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

The registry record documents a completed, single-group study of EAT-PTSD in veterans with PTSD, with enrollment of 63. It identifies change from baseline in CAPS-5 score at 8 weeks as the primary outcome and describes the scale as a clinical interview measure of PTSD severity, ranging from 0-80, with higher scores indicating more severe PTSD. It also records zero serious adverse events, zero other adverse events, and zero deaths in the EAT-PTSD group.

The record does not report the numerical CAPS-5 result or an analysis. As a result, it does not show the average change, variability, statistical uncertainty, or direction of the outcome. The study’s stated goals include feasibility, acceptability, safety, and preliminary efficacy, but numerical findings for feasibility and acceptability are not reported in the registry record. The primary endpoint’s presence is not itself evidence of a favorable or unfavorable result.

A single-group change-from-baseline result, even if available, would describe change among participants over time rather than the causal effect of EAT-PTSD compared with another intervention or no intervention. General influences on scores over time could include the course of symptoms, other care, expectations, or repeated assessment. Without a comparison group, the registered design cannot separate those influences from any intervention-related change.

The recorded safety counts are also limited in what they establish. They describe events recorded for the study group, but do not provide a comparative risk estimate or enough information to determine the completeness and duration of safety follow-up. Zero recorded events should not be interpreted as proof of zero risk.

The most defensible reading is therefore descriptive: the registry record establishes the study’s design, enrollment, intervention, endpoint definition, and listed safety counts. It does not report results sufficient to determine the amount or precision of change in PTSD symptoms or to estimate a comparative treatment effect. Conclusions beyond those points are not supported by the results reported in the registry record.

13. Why This Trial Matters Statistically

This study raises an important statistical distinction between studying whether an intervention can be delivered and estimating whether it changes an outcome relative to an alternative. The registry description identifies feasibility, acceptability, safety, and preliminary efficacy as aims. A single-group design can contribute descriptive information about participants who receive an intervention, but it does not provide a randomized comparison with another condition. Keeping the design and the claim aligned is essential when interpreting early or preliminary research.

The primary outcome is clearly tied to PTSD symptom severity: change from baseline in CAPS-5 score at 8 weeks. Its clinical-interview format and stated score direction make the endpoint interpretable in principle. Yet a well-defined endpoint is only one part of evidence. The registry record does not report the outcome estimate, variability, or uncertainty, so readers cannot evaluate the observed symptom change or its precision from this record.

The study also illustrates why registry transparency matters. The record gives a design, enrollment figure, intervention description, and endpoint definition, while the numerical outcome and analysis are absent. Registration can help clarify what was intended to be measured, but interpretation of results depends on accessible estimates, methods, missing-data information, and analysis populations. Without them, it is not possible to compare the stated aims with reported findings or assess the robustness of an analysis.

Finally, the safety figures demonstrate the difference between recorded events and a comparative safety conclusion. The registry lists zero serious adverse events, zero other adverse events, and zero deaths, but a single-group record cannot establish comparative safety, and details of follow-up and ascertainment are not reported. Statistical interpretation benefits from stating precisely what the record documents and separating it from what it cannot establish.

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 principal limitation for interpreting the primary endpoint is that its numerical result is not reported in the registry record. Although the endpoint and time frame are defined, the record supplies no baseline value, follow-up value, mean change, standard deviation, confidence interval, or p-value. Readers therefore cannot assess the direction, size, or precision of CAPS-5 change.

The study is registered as single group, with allocation listed as NA and masking as NONE. No comparator is listed. Consequently, the design does not provide a randomized between-group estimate, and any within-group change would not by itself distinguish intervention-associated change from other changes over time. This limits causal interpretation.

The registry record does not provide detailed eligibility criteria or participant characteristics. It also does not report treatment attendance, adherence, the amount of intervention received, delivery fidelity, or departures from the manualized approach. These details would help describe the population and how the intervention was implemented, but are not reported in the registry record.

Analysis details are limited. The record lists zero analyses and does not report a statistical analysis plan, model, adjustment variables, interim analyses, analysis populations, missing-data methods, or sensitivity analyses. The status of follow-up data for the primary endpoint is not reported. Enrollment alone does not establish how many participants contributed endpoint measurements.

The registry describes feasibility and acceptability as aims but does not report their numerical results or measures. Safety information is limited to the listed counts; event definitions, ascertainment, follow-up duration, and relatedness assessments are not reported. These gaps restrict interpretation of both the implementation aims and the safety observations.

The planning illustration is not the trial’s own design justification and assumes equal allocation between two arms, whereas the registered trial is single group. The registry record does not report a sample-size justification for the actual study. Taken together, these limitations mean that the record describes the study structure and intended primary outcome more fully than it documents the results needed for statistical evaluation.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Trauma-Focused Equine-Assisted Therapy (TF-EAT) for Veterans With PTSD — NCT03068325.
• Registry record last updated 2025-04-08; status last verified 2025-04.
• Results first posted 2025-04-08.
• 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

NCT03068325 is listed as a completed, single-group study of Trauma-Focused Equine-Assisted Therapy for veterans with PTSD. Enrollment was 63. The recorded study period began in 2016-04, with primary completion in 2019-07. Masking is listed as NONE, and the intervention is manualized EAT-PTSD.

The primary outcome is change from baseline in CAPS-5 score at 8 weeks. The registry describes CAPS-5 as a clinical-interview measure of PTSD severity, with scores ranging from 0-80 and higher scores indicating more severe PTSD. The record lists one outcome measure and zero analyses; it does not report the numerical primary result or statistical analysis.

The EAT-PTSD group lists 0 serious adverse events, 0 other adverse events, and 0 deaths among 63 participants at risk for each adverse-event category. Feasibility, acceptability, missing-data methods, analysis populations, and a sample-size justification are not reported in the registry record. The record supports a description of the design and registered endpoint, but not an estimate of symptom change or a comparative treatment effect.