Assessment and Treatment of Social Skills Deficits in Individuals With Social Phobia: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Assessment and Treatment of Social Skills Deficits in Individuals With Social Phobia (NCT00073333), a randomized na study. The primary outcome is Social Phobia Remission Rate at 6 Month Follow-up.

2. Clinical Question

The study’s stated purpose was to determine whether people with social phobia are deficient in certain social skills. Its listed primary outcome instead focuses on diagnostic status at follow-up. These are related to the broad study topic, but the outcome as described does not directly report a measure of social-skills proficiency. A secondary outcome was the score on the SPAI. The registry record does not describe the instrument’s scoring or explain how the secondary measure relates to the primary question.

3. Trial Design

The study is registered as randomized, with a parallel-group model and no masking. It lists three behavioral interventions: Social Skills Training, Exposure Treatment, and Placebo. Arm descriptions name the groups Social Effectiveness Therapy, Imaginal and In Vivo Exposure, and Attention Placebo Control. The record describes the first group as receiving social skills training and exposure, the second as receiving exposure treatment, and the third as placebo. Further details of treatment procedures and allocation are not reported in the registry record.

The registry lists enrollment of 379 and status as completed. The recorded start was 2002-12, and primary completion was 2008-03. The primary outcome timeframe is six-month follow-up. These registry dates and enrollment information describe the study record; they do not by themselves establish how many participants contributed to each outcome or whether all enrolled participants completed follow-up.

The posted primary outcome rows report 29 participants among 46 in the Social Effectiveness Therapy group and 23 among 41 in the Imaginal and In Vivo Exposure group as lacking a social phobia diagnosis. The Attention Placebo Control group has 19 participants listed, but its primary outcome value is missing. The registry record does not explain why the outcome group sizes differ from the enrollment figure, how participants were assigned to the outcome rows, or whether these rows reflect an analysis population distinct from enrollment.

No protocol-level detail about the allocation process, intended sample size, or sample-size justification is reported in the registry record. The registry does not report masking beyond identifying the study as having no masking. The absence of masking is a design feature to consider when interpreting outcomes, but the record does not describe how outcome assessment was conducted.

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: There were two studies contained in this grant. Study 1 was an assessment study and consisted of 379 participants - 200 normal controls and 179 participants with social phobia. Study 2 was a treatment study that consisted of 106 participants with social phobia. That is the study described below.

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 Social Phobia Remission Rate at 6 Month Follow-up, measured over 6 month follow up.

The primary endpoint is described as the Social Phobia Remission Rate at six-month follow-up. Its operational definition is lack of a social phobia diagnosis at that follow-up. The posted result is expressed as the number of participants meeting that definition, alongside the number listed for each group. Counts are reported for Social Effectiveness Therapy and Imaginal and In Vivo Exposure; the Attention Placebo Control group has no reported outcome value.

A diagnostic-status endpoint can communicate whether participants met the stated diagnostic criterion at a specified follow-up. It differs from a continuous symptom score: the outcome classifies participants by whether a diagnosis is present or absent, rather than reporting the degree of symptoms on a scale. The record also lists score on the SPAI as a secondary outcome, but does not include a posted result for it in the registry record.

The endpoint title uses the word “rate,” while the reported measure is a number of participants. A count is interpretable only alongside its relevant denominator and a clear account of who was assessed. The arm rows provide group counts, but the control outcome count is absent, and the registry does not explain the relationship between these rows and total enrollment. No adjusted estimate, uncertainty interval, or statistical test for the primary endpoint is reported in the registry record.

In general, follow-up endpoints are intended to capture status at a defined time after treatment. Their interpretation depends on how follow-up was completed and how missing assessments were handled. Those details are not reported in the registry record, so the posted counts alone cannot establish the completeness of outcome ascertainment.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does randomization mean?

In general, randomization assigns participants to study groups using a chance-based process. Its purpose is to reduce systematic differences between groups at assignment, so that a comparison can be more informative about the interventions. The registry identifies this study as randomized, but does not report the allocation sequence, concealment procedures, or other implementation details. The designation alone does not establish that all sources of bias were prevented.

What does a parallel-group model describe?

In general, a parallel design assigns participants to a group and assesses the groups over the study period. The registry identifies a parallel model and lists three behavioral groups. It does not report further design details such as treatment duration, visit schedules, or the timing of outcome assessment beyond the six-month follow-up stated for the primary outcome.

How should a binary endpoint be read?

In general, a binary endpoint records whether each participant falls into one of two categories. Here, the stated endpoint classifies participants according to whether they lack a social phobia diagnosis at six-month follow-up. The registry reports participant counts for the two groups with outcome values, along with the number listed in each group. It does not provide a control-group outcome value. Counts are not themselves a comparative effect estimate; a complete comparison also requires interpretable outcome information for the relevant groups and an analysis method.

What would an effect estimate and uncertainty interval add?

In general, an effect estimate quantifies a comparison between groups using a chosen scale. A confidence interval conveys uncertainty around that estimate under the specified statistical method. For a binary outcome, analysts may use different scales and models, and the choice should be appropriate to the question and data. No such primary-endpoint estimate or confidence interval is reported in the registry record. The record also does not report a p-value or specify an analysis model for the primary endpoint.

What does the registry say about statistical analyses?

The registry lists no posted statistical analyses. That means the record does not provide inferential results to interpret; it does not establish what analyses may or may not have been conducted outside the registry. The statistical analysis plan, including any covariate adjustment, handling of repeated or incomplete assessments, and definition of the analysis population, is not reported in the registry record.

What is over-dispersion, and is it relevant?

In general, over-dispersion describes variation greater than a statistical model expects. It can matter when modeling outcomes such as counts or clustered observations because a model that assumes too little variation may give uncertainty estimates that are too narrow. The primary endpoint is described as a binary participant outcome and reported as counts, but the registry does not report a model or analysis that would allow over-dispersion to be assessed. No claim about over-dispersion or its handling can be made from the registry record.

How should planning illustrations be distinguished from trial results?

In general, sample-size planning estimates describe how many participants might be needed under stated assumptions; they are not observed trial outcomes or evidence of observed power. The registry’s planning assumptions describe a two-sided significance level of 0.05, equal allocation between two arms, a normal approximation, and an effect to detect defined as a stated fraction of the observed effect. The record does not report the trial’s own sample-size justification. Any planning illustration based on an observed effect should be interpreted as conditional on those assumptions, not as a substitute for a reported analysis or as evidence that the study had a particular probability of detecting an effect.

What information is missing for reproducing the analysis?

In general, reproducing a clinical-trial analysis requires a clear outcome definition, the analysis population, treatment-group data, the model or test, and rules for missing observations. The registry supplies the endpoint description and some group counts, but not the control outcome value, the statistical analysis plan, or the treatment of missing data. It also does not report an adjusted estimate or explain the relationship between the enrollment figure and the outcome-group sizes. These omissions limit independent assessment of the statistical results.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Social Effectiveness Therapy", "Imaginal and In Vivo Exposure")
n      <- c(46, 41)
events <- c(29, 23)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Social Effectiveness Therapy  46  29  63.0  47.5  76.8  48.6  75.5  48.5  75.5
ARM  Imaginal and In Vivo Exposure  41  23  56.1  39.7  71.5  41.0  70.1  41.0  70.2

11. Multiplicity, Missing Data and Analysis Populations

The registry lists one secondary outcome, score on the SPAI, and reports three outcome measures in total. It does not provide a multiplicity strategy, identify which outcomes were treated as confirmatory, or describe adjustment for multiple comparisons. In general, testing multiple outcomes or comparisons can increase the chance of at least one apparently notable result by chance. Whether and how that issue was addressed is not reported in the registry record.

No secondary outcome result is included in the record. No statistical analyses are posted, and the record does not identify a primary analysis population or specify whether analyses were based on assigned groups, participants who completed treatment, or another set. Such analysis-population definitions matter because they determine which participants contribute to each estimate.

The registry does not describe missing-data handling, reasons for missing outcomes, follow-up completion, or any imputation or sensitivity analysis. The control group has 19 participants listed but no primary outcome value. The record also does not explain why the outcome rows list fewer participants than the enrollment figure of 379. These gaps prevent assessment of whether the missing outcome information could affect the interpretation of the reported counts.

In general, missing outcome data can introduce bias when the likelihood of missingness is related to participants’ outcomes or group assignment. The registry does not provide the information needed to determine whether that concern applies or how it was addressed. The counts should therefore be interpreted as the posted values, without assuming that they represent all enrolled participants or a prespecified analysis population.

12. Safety Results

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

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

The adverse-event listings report zero serious adverse events among the participants at risk in each of the three groups: Social Effectiveness Therapy, Imaginal and In Vivo Exposure, and Attention Placebo Control. They also report zero other adverse events among those at risk in each group. No serious adverse-event terms are listed.

These figures describe what is recorded in the registry, not proof that no adverse events occurred outside the information captured in the record. The number of participants at risk is reported as 46, 41, and 19 across the groups. The record does not provide further detail about how adverse events were collected, defined, monitored, or attributed to an intervention. Death counts are not reported in the registry record.

In general, a zero count in a posted safety listing means that no events are entered for that category in the displayed record. It does not establish that an intervention has no safety risks, particularly when the record does not explain the ascertainment process or completeness of reporting. The adverse-event figures should be read as registry reporting, rather than as a comprehensive account of all possible harms.

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

The registry record documents a randomized, parallel-group study of behavioral approaches for social phobia and identifies a primary endpoint based on diagnostic status at six-month follow-up. It posts outcome counts for two groups: 29 of 46 participants in Social Effectiveness Therapy and 23 of 41 in Imaginal and In Vivo Exposure were recorded as lacking a social phobia diagnosis. The Attention Placebo Control group has 19 participants listed, but no outcome value is reported.

Those observations do not establish how the interventions compare. The missing control outcome prevents a complete descriptive reading across the listed groups, while the absence of comparative estimates and uncertainty measures prevents assessment of the magnitude and precision of any between-group effect. No p-value or confidence interval for the primary endpoint is reported. The registry also does not provide a posted result for the SPAI secondary outcome.

In general, a count of participants meeting an outcome definition is not sufficient on its own to establish a causal effect. Interpretation depends on the completeness of outcome measurement, the analysis population, the prespecified methods, and the uncertainty around comparisons. Those details are not reported in the registry record. Although the study is identified as randomized, the registry entry alone does not provide all information needed to assess how the design was implemented or how outcomes were analyzed.

The record does not support a claim that one approach is superior, equivalent, or ineffective. It also does not provide evidence that the interventions changed social-skills deficits, which the study’s brief summary identifies as a research objective. The posted primary outcome concerns diagnostic status, and the registry does not give a result for the SPAI outcome. Conclusions should remain limited to the recorded counts and the reporting gaps.

14. Why This Trial Matters Statistically

This study illustrates a common distinction in clinical-trial reporting: an outcome may have a clear label and a defined follow-up time, while the posted information remains insufficient for a comparative statistical interpretation. The primary outcome is described as remission at six-month follow-up and operationalized as lack of a social phobia diagnosis. Yet the registry reports outcome values for only two of the three listed groups, and it provides no comparative estimate or uncertainty interval.

For biostatisticians and clinical researchers, the entry highlights why outcome counts need to be accompanied by complete denominators, participant-flow information, a defined analysis population, and a stated analysis method. The registry lists enrollment of 379, while the primary outcome rows list 46, 41, and 19 participants. Without an explanation of how those figures relate, readers cannot determine from the record which participants contributed to the outcome information or whether follow-up was complete.

The entry also illustrates the difference between a registry’s description of a study and its reporting of results. Randomized allocation and a parallel design describe important features, but they do not replace the analysis plan or comparative findings. The SPAI is named as a secondary outcome, yet no result is posted for it. Multiplicity handling, missing-data methods, and the primary analysis population are also not reported.

These limitations matter statistically because incomplete outcome reporting restricts what can be estimated and how precisely it can be interpreted. The registry record remains useful for identifying the study question, intervention groups, and some observed counts, while making clear that those items do not amount to a complete efficacy analysis.

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 primary reporting limitation is that the Attention Placebo Control group has a listed group size of 19 but no posted value for the primary endpoint. The record therefore lacks outcome information for one of the three groups. It also does not report a treatment contrast, confidence interval, or p-value, so the precision and statistical evidence for a comparative effect cannot be assessed from the registry record.

Participant accounting is unclear. Enrollment is listed as 379, while the primary outcome rows list 46, 41, and 19 participants. The record does not explain these figures, describe participant flow, or state how many people were assessed at follow-up. It does not report reasons for missing outcomes or how missing data were handled. These omissions make it difficult to judge the completeness and representativeness of the posted outcome counts.

The statistical analysis plan and analysis population are not reported in the registry record. No model, adjustment strategy, or multiplicity approach is specified, and no statistical analyses are posted. The SPAI is listed as a secondary outcome, but its result is not included. The record also does not provide details of the allocation procedure, treatment content, outcome-assessment process, or the attention placebo condition. These absences limit assessment of bias, reproducibility, and the relevance of the outcome definition to the study’s stated purpose.

The adverse-event listings show zero recorded serious and other adverse events in the three groups, but the record does not describe event collection or completeness. Death counts are not reported. These safety entries should not be treated as a full account of potential harms.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Assessment and Treatment of Social Skills Deficits in Individuals With Social Phobia — NCT00073333.
• Registry record last updated 2013-07-18; status last verified 2013-07.
• Results first posted 2013-07-02.
• 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 registry describes a completed randomized, parallel-group study with no masking, examining social skills training, exposure treatment, and placebo for social phobia. Enrollment is listed as 379. The primary endpoint is lack of a social phobia diagnosis at six-month follow-up.

Primary outcome counts are posted for Social Effectiveness Therapy and Imaginal and In Vivo Exposure: 29 of 46 participants and 23 of 41 participants, respectively, were recorded as lacking a diagnosis. The Attention Placebo Control group lists 19 participants, but its outcome value is not reported in the registry record. No comparative statistical analysis, confidence interval, or p-value is posted. The SPAI is listed as a secondary outcome without a posted result.

The record does not explain the outcome-group sizes relative to enrollment or report the analysis population, missing-data methods, or multiplicity plan. Adverse-event listings record zero serious and zero other adverse events in each group; death counts are not reported. The available information supports a description of selected registry entries, but not a complete comparative interpretation.