1/2 A Multi-site Systems Intervention for Unemployed Persons With Social Anxiety: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for 1/2 A Multi-site Systems Intervention for Unemployed Persons With Social Anxiety (NCT02633267), a randomized na study. The primary outcome is Liebowitz Social Anxiety Scale.

2. Clinical Question

The trial concerns a community-based systems intervention intended to address social anxiety and employment outcomes among unemployed people with social anxiety disorder. Its randomized comparison distinguishes the addition of cognitive behavioral therapy to usual vocational services from usual vocational services alone. The registry record identifies the Liebowitz Social Anxiety Scale as the primary outcome and describes the outcome across baseline, post treatment, 3 month, 6 month and 12 month follow up. It does not identify a single timepoint as the sole primary comparison; the stated timeframe is mean scores across all those timepoints.

The record also lists the Patient Health Questionnaire and Hours Worked Per Week among the secondary outcomes. The registry record does not report their numerical results or an analysis linking changes in anxiety to employment outcomes. Enrollment is listed as 250, but no outcome results are available to indicate whether the recorded participants contributed measurements at each timepoint or how many were included in any analysis. Thus, the question can be described from the design and outcome definitions, but the direction, size, and precision of any group difference cannot be established from the posted results.

3. Trial Design

The study is listed as a randomized, parallel-group behavioral intervention trial with single masking. The registry record names two groups: Usual Vocational Services + CBT and Usual Vocational Services. It describes the trial as a two-site project and identifies the University of Michigan as sponsor. The study is marked completed, with enrollment of 250. The listed phase is NA.

Participants assigned to the intervention group received usual vocational services together with additional cognitive behavioral therapy at a vocational services center. The comparison group received vocational services as usually delivered to service-seeking clients. This is an add-on comparison: the groups differ in whether cognitive behavioral therapy accompanies the usual vocational services, as described in the registry. Details about the content, schedule, or delivery of the therapy beyond that description are not reported in the registry record.

The record gives the study start as 2016-01 and primary completion as 2021-05. It does not report the randomization procedure, allocation concealment, the identity of the party or parties masked, or whether masking was maintained throughout follow-up. The word “single” identifies the masking category but does not resolve who was masked. The record also does not report the planned allocation ratio, site-specific enrollment, or whether any participants changed or discontinued their assigned services.

The primary outcome timeframe includes baseline, post treatment, 3 month, 6 month and 12 month follow up. A registry outcome timeframe is not itself a description of the statistical model used to compare groups across repeated measurements. The record does not report a statistical analysis plan, the planned handling of within-person correlation, or a method for combining timepoints. It also reports no analysis entries. Consequently, the design can be characterized as randomized and parallel, while important operational and analytic details remain unspecified.

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 Liebowitz Social Anxiety Scale, measured over Mean scores across all timepoints: baseline, post treatment, 3 month, 6 month and 12 month follow up..

The primary endpoint is the Liebowitz Social Anxiety Scale, recorded as a score on a scale and summarized as a mean with standard deviation. The registry describes it as measuring social anxiety and avoidance. Its anxiety or fear items rate how anxious or fearful a person feels in a situation, and its avoidance items rate how often the person would avoid that situation. The two subscale sums are added to form the total score.

The registry gives the rating ranges for each item as 0-3, from none to severe for fear or anxiety, and from never to usually for avoidance. It also gives severity bands for the total score: 0-54=subclinical, 55-64=moderate, 65-79=marked, 80-94=severe, and 95-144 (maximum score)=very severe. These descriptions clarify what the instrument is intended to capture; they do not show the trial participants’ scores or changes in scores.

Repeated measurement can describe the course of a symptom measure over treatment and follow-up. Here, the stated primary timeframe combines baseline, post treatment, 3 month, 6 month and 12 month follow up. The registry does not report a numerical group comparison, an estimated change, or the uncertainty around such an estimate. The reason this measure was selected as primary, and whether a particular score difference was considered clinically important, are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The endpoint is continuous: a score is recorded for each participant, and the registry identifies the mean and standard deviation as the summary measures. The statistical concepts below explain how such data are commonly interpreted. They do not describe a confirmed analysis from this trial, because the analysis method is not reported in the registry record.

What does a mean summarize?

A mean is an average across the observations included in an analysis. In a randomized trial, a mean score can describe each assigned group at a particular assessment, or a mean change can describe how scores differ from an earlier assessment. Those summaries answer different questions. A mean at follow-up reflects the observed score distribution at follow-up; a change score also depends on the baseline value and on how change is defined. The registry specifies mean scores across baseline, post treatment, 3 month, 6 month and 12 month follow up, but does not state whether the intended comparison was based on separate means, change from baseline, or a model combining repeated measurements.

A standard deviation describes the spread of individual scores around a group mean. It is not the same as the uncertainty in the mean or in a group contrast. To quantify uncertainty in a comparison, an analysis also needs to account for the number and pattern of observations and the statistical model. The registry reports neither outcome summary statistics nor an estimated contrast, so precision cannot be assessed from the posted record.

Why do repeated measurements need careful handling?

Measurements from the same participant over time are generally related: a person’s score at one assessment may be associated with that person’s scores at other assessments. A statistical method for repeated measurements should account for that dependence rather than treating every score as if it came from a different person. Possible approaches in general include models for repeated measures and analyses of defined changes, but the registry record does not identify which approach, if any, was used.

When a study describes several assessment times, the analysis also needs a clear target. It might estimate a group contrast at a particular follow-up, an average contrast across assessments, or a pattern of change over time. Those targets are not interchangeable. The trial’s stated primary timeframe includes baseline and post-treatment and follow-up assessments, but no single contrast, timepoint-specific estimate, or time-by-group analysis is reported in the registry record. The description alone does not establish how baseline scores were used.

What would an effect estimate and confidence interval convey?

An effect estimate expresses the contrast defined by an analysis, such as a difference between group means. Its interpretation depends on the endpoint scale, the groups being contrasted, the assessment time, and whether the estimate is adjusted or unadjusted. A confidence interval conveys statistical uncertainty around the estimate under the assumptions of the method. A narrow interval indicates greater precision than a wide interval; an interval that includes values on both sides of no difference may leave the direction and size of the contrast uncertain. These are general interpretive principles, not claims about the trial’s unreported results.

A p-value, if reported, addresses how compatible the observed data are with a specified null model under the analysis assumptions. It does not quantify the size or clinical importance of an effect. A p-value alone would not provide the full interpretation of a repeated-measures outcome; the estimate, interval, outcome definition, and analysis population would also matter. No primary-outcome p-value is reported in the registry record.

How should missing observations be considered?

Repeated follow-up creates the possibility that some participants do not have measurements at every assessment. The amount and pattern of missingness matter because analyses can rely on assumptions about why data are missing. For instance, an analysis may assume that observed information is adequate to model missing scores, while other approaches may make different assumptions. Such assumptions cannot be evaluated without information about the observed follow-up data and the method used. The registry record does not report missing-data methods, counts with outcome data, or sensitivity analyses.

Random assignment supports a comparison between assigned groups when the analysis preserves that assignment and handles follow-up appropriately. However, the record does not state whether the primary analysis followed an intention-to-treat principle, used another analysis population, or included participants according to treatment received. It also does not report adherence or crossover information. No particular analysis population or missing-data strategy should therefore be attributed to this trial.

What do the planning assumptions mean?

The registry describes a planning illustration based on a fraction of the observed effect, with a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Such an illustration asks what sample size would be associated with specified assumptions; it is not an observed trial result and is not observed power. The record does not include the observed effect estimate or numerical planning values in the reported trial details, so the assumptions cannot be used to assess the actual comparison or establish how the trial’s enrollment was justified. The sample-size justification for the trial is not reported in the registry record.

More generally, a planning estimate depends on the target effect, variability, significance level, allocation, and analysis assumptions. If those inputs differ from the eventual data or analysis, the planning exercise may not describe the achieved precision. It also cannot remedy the absence of a reported outcome estimate. In this trial, the key interpretive need is a transparent primary analysis with group summaries, a defined contrast, uncertainty estimates, analysis population, and an account of missing observations. Those details are not reported in the registry record.

10. Multiplicity, Missing Data and Analysis Populations

The primary outcome is framed across baseline, post treatment, 3 month, 6 month and 12 month follow up. Considering multiple assessment times can raise multiplicity questions, particularly if several time-specific comparisons are tested and then interpreted as separate opportunities to find a difference. A prespecified overall contrast or a multiplicity adjustment can address some of these concerns, but the appropriate approach depends on the analysis question. The registry record does not report whether a multiplicity strategy was planned or used, or whether one assessment was designated as the key comparison.

The record lists three outcome measures, including the Liebowitz Social Anxiety Scale, the Patient Health Questionnaire, and Hours Worked Per Week. It does not report a hierarchy among outcomes, a testing sequence, or adjustments for multiple outcomes. Nor does it report interim analyses or stopping rules. Those elements are not reported in the registry record, so the chance of selective emphasis across outcomes or timepoints cannot be assessed.

Missing-data methods and analysis populations are also not described. The registry does not give assessment-specific participant counts, reasons for missing measurements, or sensitivity analyses. It does not state whether analyses included all randomized participants, only participants with available outcomes, or another defined group. These omissions matter because missingness and analysis-population choices can affect both the estimate and its uncertainty. Enrollment of 250 does not establish the number contributing to any particular endpoint analysis.

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 zero serious adverse events affected among 120 participants at risk in the Usual Vocational Services + CBT group, and zero among 130 at risk in the Usual Vocational Services group. Deaths are listed as zero in each group. Other adverse events affected are also listed as zero in both groups. These counts describe the safety entries recorded in the registry; they are not results for the social anxiety endpoint.

A count of zero recorded events does not by itself establish that no events occurred outside the reporting system or that ascertainment was complete. The registry record does not describe how adverse events were solicited, defined, monitored, or attributed, nor does it provide event narratives or follow-up details. The “at risk” figures are the denominators used in the safety record and should not be treated as outcome-analysis counts. They differ between groups, but the record does not explain the reason.

These figures should be read as registry-reported counts rather than as a comprehensive comparison of safety. No rate or comparative estimate is reported, and no additional safety interpretation is warranted from the counts alone.

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

The posted record establishes that a randomized, parallel-group trial compared usual vocational services plus cognitive behavioral therapy with usual vocational services alone among unemployed persons with social anxiety disorder. It identifies the Liebowitz Social Anxiety Scale as the primary outcome and gives its assessment timeframe. It also lists the Patient Health Questionnaire and Hours Worked Per Week as secondary outcomes. These details clarify the trial question and the measures selected to address it.

The record does not establish the size or direction of a difference between groups. No primary outcome means, standard deviations, effect estimate, confidence interval, or p-value are reported, and the analysis count is 0. It is therefore not possible to say from the posted results whether scores differed, by how much, or with what precision. The same limitation applies to the secondary outcomes: their numerical results and analyses are not reported in the registry record.

Completion status and enrollment describe trial administration, not evidence of an outcome effect. Likewise, the safety counts of zero serious adverse events and zero deaths in the registry do not answer the primary efficacy question or establish the completeness of safety reporting. A randomized design can strengthen a treatment comparison when its conduct and analysis are reported, but the design label alone does not supply the missing results.

The registry record also does not explain the sample-size justification, missing-data approach, analysis population, or handling of multiple timepoints and outcomes. Those omissions limit assessment of how the intended comparison was carried out. The appropriate interpretation is therefore descriptive: the record specifies the intervention, comparator, population, outcomes, and selected safety counts, while leaving the comparative outcome findings and their uncertainty unreported.

13. Why This Trial Matters Statistically

This trial is statistically notable for combining a service-system intervention with a behavioral treatment and evaluating a continuous symptom measure over repeated assessments. Its design raises questions that are common in clinical and behavioral research: how to define a primary contrast across time, how to account for repeated scores from the same participant, and how to interpret missing follow-up information. These questions are relevant to the meaning and precision of any group comparison.

The registry identifies both symptom and employment-related outcomes, including Hours Worked Per Week. This makes clear that the study was intended to consider more than a symptom score, although the record does not report numerical findings for either outcome category. Without results, it is not possible to judge whether the primary measure or employment outcomes changed, whether patterns were consistent across assessment times, or how uncertain any estimated differences would be.

The statistical value of a randomized comparison depends not only on assignment but also on transparent reporting of the analysis. Group summaries, an explicit estimand or contrast, uncertainty intervals, the analysis population, and a description of missing data would allow readers to distinguish the estimated effect from its precision and from the assumptions used to obtain it. The registry record does not report those elements for the primary outcome.

As a result, the record is useful for understanding the study question and design, but its statistical contribution cannot be judged from outcome evidence that is not posted. The distinction between a defined trial and a reported treatment-effect estimate is important: design features describe how evidence could be generated, while the analysis and results are needed to quantify what the 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 main trial-specific limitation is the absence of reported outcome analyses. Although the registry identifies a primary measure and a repeated-assessment timeframe, it provides no group-level scores or comparison estimate. The direction, magnitude, and precision of the primary result are therefore unavailable. The record also lists secondary outcomes without their numerical results.

Important details about the endpoint analysis are not reported in the registry record. These include the selected contrast across timepoints, whether baseline was incorporated into the model, the method for accounting for repeated observations, and the analysis population. The record does not report how missing measurements were handled or provide assessment-specific follow-up counts. Those gaps prevent evaluation of the assumptions supporting any potential estimate.

The intervention description does not specify the content or delivery details of cognitive behavioral therapy beyond its addition to usual vocational services at a vocational services center. The record does not identify who was masked, explain allocation concealment, or describe adherence, crossover, or site-level implementation. It does not report a sample-size justification, interim analyses, or a multiplicity plan. Each omission limits appraisal of design conduct or analysis, but none establishes that a particular problem occurred.

Finally, the safety figures are limited to registry counts, with no description of event collection or completeness. The study is marked completed, but completion does not fill the gap in outcome reporting. These limitations are specific to what the registry record documents and should not be interpreted as proof that unreported procedures or analyses were absent from other study materials.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: 1/2 A Multi-site Systems Intervention for Unemployed Persons With Social Anxiety — NCT02633267.
• Registry record last updated 2022-09-21; status last verified 2022-09.
• Results first posted 2022-06-23.
• 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

NCT02633267 is a completed, randomized, single-masked, parallel behavioral trial sponsored by the University of Michigan. Enrollment is listed as 250, and the study is described as a two-site intervention for unemployed persons with social anxiety disorder.

The intervention group received usual vocational services plus cognitive behavioral therapy; the comparator received usual vocational services. The primary outcome was the Liebowitz Social Anxiety Scale, with mean scores specified across baseline, post treatment, 3 month, 6 month and 12 month follow up. The Patient Health Questionnaire and Hours Worked Per Week are listed as secondary outcomes.

The registry record reports no outcome analyses or numerical outcome results. It lists zero serious adverse events affected and zero deaths in each group. Details on the primary analysis, missing data, analysis populations, multiplicity, and sample-size justification are not reported in the registry record.