Milk Thistle in Trichotillomania in Children and Adults: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Milk Thistle in Trichotillomania in Children and Adults (NCT02473913), a randomized phase 2 study. The primary outcome is Change in NIMH Trichotillomania Severity Scale (NIMH-TSS) Scores.

2. Clinical Question

The registry describes a study intended to evaluate the efficacy and safety of silymarin in children and adults with trichotillomania. Its stated hypothesis was that silymarin would be more effective and well tolerated than placebo. That is the question the study set out to investigate, not a finding established by the registry record.

The primary outcome was change in NIMH-TSS score, a continuous measure of symptom severity. Because the study used a cross-over design, participants were scheduled to receive both milk thistle and placebo in different phases, with the order determined by randomization. The primary-outcome description refers to change from baseline to the end of the 13-week study, rather than giving a posted numerical comparison between the two treatment phases.

The registry record does not report a primary-outcome estimate, confidence interval, or analysis result. It therefore does not establish the direction or size of any difference between milk thistle and placebo, nor how precisely such a difference was estimated. The clinical question is clear from the planned design and outcome, but the posted record does not provide the result needed to answer it.

3. Trial Design

This was a randomized, phase 2, quadruple-masked, placebo-controlled cross-over study sponsored by the University of Chicago. Its registered title describes a double-blind study, while the registry’s masking classification is quadruple. The record does not explain which people or roles were included in that masking classification.

The registry lists enrollment of 22. Each subject was scheduled for a 6 week milk thistle phase and a 6 week placebo phase, with the order depending on randomization. The primary-outcome description says the entire study for a subject would last 13 weeks and mentions a one week washout period. The record does not provide further detail about the washout procedure or how the outcome assessment aligned with each treatment phase.

In a cross-over design, participants receive more than one study condition in sequence. This can allow comparisons within the same participant, but interpretation depends on factors such as treatment order, changes over time, and whether effects carry into a later phase. These are general design considerations; the registry record does not state how they were handled in the analysis.

The record lists a start of 2015-03, primary completion of 2018-06, and status of completed. It also lists secondary measures covering hair pulling, clinical severity and improvement, disability, anxiety, depression, and child and parent assessments. The registry lists 7 outcome measures, but no analysis entries. The record does not give a completed participant flow, a description of adherence, or a numerical result for the primary outcome. Completion status alone does not indicate what the trial found.

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: This is a crossover study. Therefore, only 22 participants were technically enrolled, but they each were supposed to complete both the placebo and the Milk Thistle Arm.

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 in NIMH Trichotillomania Severity Scale (NIMH-TSS) Scores, measured over Baseline and 13 weeks.

The primary endpoint was change in scores on the NIMH Trichotillomania Severity Scale (NIMH-TSS), assessed from baseline to 13 weeks. The scale has 5 questions addressing average time spent pulling, time spent pulling on the previous day, resistance to urges, resulting distress, and daily interference. Scores range from 0 to 25, with higher scores indicating greater severity.

A continuous severity score can represent variation across participants and can be summarized using a mean and standard deviation, the summary form registered for this outcome. Change over time is relevant to the study question because the registry aimed to assess whether symptom severity differed with silymarin compared with placebo. In general, a change score expresses how an outcome differs from its starting value; interpretation depends on the comparison used and the analysis method.

The registry describes the endpoint as change from baseline to after the 13-week study. It does not report the mean change in either condition, the estimated difference between conditions, or uncertainty around that difference. Nor does it report an analysis showing how the two treatment phases were compared. The scale’s direction is documented, but the clinical meaning of any particular change magnitude is not established in the record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does a continuous outcome mean?

The NIMH-TSS is recorded as a score, so the primary outcome is continuous rather than a count of participants who did or did not experience an event. The registry specifies a mean and standard deviation as the outcome summary. In general, a mean describes the average score or change in a group, while a standard deviation describes how spread out individual values are around that mean. Neither summary alone gives the estimated difference between milk thistle and placebo.

For a treatment comparison, an estimate should identify the contrast being made. In a cross-over study, that might involve comparing participants’ outcomes under the two conditions while accounting for their sequence or study period. The registry record does not state the exact estimand or model used, and it does not report an estimate. An intended outcome and its summary format do not reveal which statistical procedure was ultimately applied.

Why does the cross-over structure matter?

In general, a cross-over study assigns treatment order and has participants receive each condition in sequence. This design can reduce the effect of stable differences between participants when the comparison uses measurements from the same people. It also introduces considerations that are less central to a simple parallel-group comparison. Scores may change over time irrespective of treatment, and the effect of an earlier treatment may persist into a later period. The washout period is intended as part of the study sequence, but its presence alone does not demonstrate that carryover was absent.

For that reason, analysis of cross-over data often needs to account for the participant’s treatment sequence and period, as appropriate to the design and data. This is a general statistical explanation, not a description of the method used in this trial. The registry record does not report a statistical model, a test, or whether period and carryover considerations were examined. It is not possible to infer those choices from the cross-over label.

What would a confidence interval contribute?

In general, a confidence interval gives a range of values compatible with the observed data under the assumptions of a statistical method. It communicates precision as well as the estimated direction and magnitude of a contrast. A narrow interval indicates greater precision than a wide interval, though interpretation also depends on which values are clinically meaningful. The registry record does not report a confidence interval for the primary outcome, so the precision of a treatment comparison cannot be assessed.

A p-value, when reported, addresses how compatible data are with a specified statistical model and null hypothesis. It does not by itself describe effect size, clinical importance, or the probability that a treatment is effective. No primary-outcome p-value is reported in the registry record. Without an estimate and its uncertainty, a significance-based interpretation would be unsupported.

How should planning calculations be understood?

Any sample-size figures associated with the posted material are planning illustrations based on an observed effect, rather than the trial’s own design justification. The registry says the illustrations use a two-sided significance level of 0.05, equal allocation, and a normal approximation, with the target effect expressed as a stated fraction of the observed effect. These are assumptions for the illustration, not evidence that the trial was designed with those assumptions.

In general, a sample-size calculation estimates how many participants per arm might be needed to detect a specified effect under stated assumptions. It depends on the assumed effect and variability, the chosen significance level, and the desired power. A calculation based on an observed effect is especially dependent on that effect estimate and is not a measure of the probability that the completed trial detected an effect. The planning values should therefore not be described as observed power. The registry record does not report its own sample-size justification or statistical design calculations.

More broadly, statistical interpretation requires the analysis population, handling of missing outcomes, and analysis methods as well as a numerical estimate. Those details are not reported in the registry record. The registered mean-and-standard-deviation format indicates how the outcome was intended to be summarized; it does not supply the underlying data or define the analysis.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists several secondary outcomes in addition to the primary NIMH-TSS endpoint. When a study examines multiple outcomes, time points, or comparisons, the chance of finding at least one apparently unusual result can increase. In general, a statistical plan may specify a primary comparison, a hierarchy, or an adjustment for multiple testing. The registry record does not report whether multiplicity was addressed, how secondary outcomes were prioritized, or whether any adjustment was used. Since no analysis results are posted, the impact of these choices cannot be assessed.

The primary-outcome description refers to baseline and 13 weeks, while also describing repeated NIMH-TSS assessment during the study. The record does not explain how intermediate measurements were used in the primary analysis, or whether the outcome was analyzed at more than one time point. The record’s note that the primary outcome has several categories or time points and was not reduced to one comparison means a single primary comparison is not available in the posted analysis material.

Missing-data procedures are not reported in the registry record. It does not state how missing scores, withdrawal, incomplete treatment phases, or incomplete follow-up were handled. The analysis population is also not reported: the record does not specify whether the intended analysis included all randomized participants or a subset with particular data available.

These omissions matter because missingness and analysis-population choices can affect both the estimate and its uncertainty. General methods include analyzing participants according to randomized assignment or using models that can incorporate available repeated measurements, but the record does not identify a method used. No specific handling strategy should be attributed to this trial based on the information posted.

11. Safety Results

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

Deaths

Other (non-serious) adverse events

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

Most frequent non-serious adverse event terms

The registry reports serious adverse events for the milk thistle and placebo groups, with zero serious events listed in each. It also reports zero deaths in each group. For other adverse events, the record lists 6 affected participants among 18 at risk in the milk thistle group and 7 among 21 at risk in the placebo group. These are the posted counts and denominators; they should be read as registry entries, not as a complete safety analysis.

The record does not provide event descriptions for those other adverse events, their severity, timing, duration, or whether participants experienced more than one event. It also does not explain why the at-risk figures differ between groups or how the adverse-event groups relate to the enrolled population. No additional rates or comparative measures can be inferred from the counts alone.

A zero count of reported serious events does not establish that the risk of serious events is absent. It describes what was recorded for the listed groups. The record does not report a statistical comparison of adverse events or detail the methods used to collect and classify them. These figures should therefore be interpreted descriptively and separately from the unreported primary-outcome result.

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

The registry record establishes that a randomized, masked, placebo-controlled cross-over study was registered to evaluate milk thistle in children and adults with trichotillomania. It specifies the NIMH-TSS as the primary outcome and describes the planned study phases. It also records group-level adverse-event counts. Those details characterize the question, design, and selected safety entries.

The record does not establish whether NIMH-TSS scores improved more during milk thistle than placebo, whether either condition was associated with a change, or how large any difference may have been. There is no posted primary-outcome estimate, confidence interval, or analysis result. The record therefore cannot support a conclusion about statistical significance, clinical importance, or precision of the treatment comparison.

Likewise, a completed status is an administrative status, not a result. A stated hypothesis is not evidence that it was supported, and the lack of a posted result is not evidence that the treatments performed alike. The secondary-outcome list also does not show what those measures found.

General interpretation of a cross-over trial would consider the paired structure, treatment sequence, study period, and possible carryover, as well as missing data and the analysis population. The registry record does not report how those issues were handled. Without a numerical comparison and sufficient analysis details, readers cannot judge the robustness of an effect estimate.

The appropriate boundary is therefore descriptive: the registry records a study designed to compare silymarin with placebo, but its posted results do not answer the primary statistical question. The safety counts are limited entries and do not resolve the efficacy question or provide a complete account of safety.

13. Why This Trial Matters Statistically

This trial is statistically notable for its cross-over structure. Rather than assigning participants to remain in one condition throughout, the registered design scheduled milk thistle and placebo phases in an order determined by randomization. In general, such designs can make within-participant comparisons informative because each participant may contribute observations under both conditions. The same feature makes sequence, period, and possible carryover important to interpretation.

The primary outcome is a continuous severity score, and the registry identifies a specific symptom measure with a defined range and direction. That gives a clear description of what the study intended to assess. But an outcome definition is only one part of an interpretable result: the effect estimate, uncertainty, analysis method, and analysis population are also needed to evaluate the comparison.

The contrast between a detailed registered question and the absence of a posted primary analysis is important for readers. Trial status and planned outcomes do not substitute for results. Nor can descriptive adverse-event counts establish the magnitude or precision of a symptom-score difference.

The study also illustrates why a planning calculation should be kept separate from trial findings. Planning illustrations describe sample sizes under assumptions; they do not measure the power achieved by a completed study. The registry explicitly characterizes its calculations as illustrations rather than the trial’s own design justification. This distinction helps prevent planning quantities from being mistaken for evidence about the observed outcome.

For statistical readers, the central lesson is that the design can be described while the treatment effect remains unassessable from the registry record. A transparent account of the outcome analysis and its uncertainty would be needed to move from the registered question to a quantitative interpretation.

14. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The most important limitation of the posted record for interpreting this trial is the absence of a numerical primary-outcome result. The record does not report the mean change, a treatment contrast, a confidence interval, or a p-value. As a result, the direction, size, and precision of the primary comparison cannot be assessed.

The record also does not provide a detailed participant flow or explain the relationship between the enrollment figure and the group-specific adverse-event at-risk figures. It does not report how many participants completed both phases or contributed data at the primary assessment. The reasons for missing outcome data, if any, and the methods used to handle them are not reported in the registry record.

Although the design is identified as cross-over and the description includes a washout period, the record does not specify the analysis used to address sequence, period, or carryover. It does not report the statistical model, the analysis population, or whether the primary endpoint was analyzed as a within-participant comparison. These omissions limit any assessment of how the design was translated into an estimate.

The registry lists secondary measures but does not post their results or describe how multiple outcomes were handled. The adverse-event information is also limited: event terms and further details for non-serious events are not reported, and no comparative safety analysis is given. These limitations concern what can be learned from the registry record; they do not establish that additional analyses or information do not exist elsewhere.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Milk Thistle in Trichotillomania in Children and Adults — NCT02473913.
• Registry record last updated 2020-11-20; status last verified 2020-11.
• Results first posted 2020-11-04.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

18. Record Summary

The registry record describes NCT02473913, a phase 2 randomized, quadruple-masked, placebo-controlled cross-over study sponsored by the University of Chicago. It lists children and adults with trichotillomania as the target population and milk thistle, identified as silymarin, as the intervention. Participants were scheduled for 6 week phases of milk thistle and placebo, with order determined by randomization.

The primary outcome was change in NIMH-TSS score from baseline to 13 weeks. The record lists enrollment of 22 and a completed status, but does not report a numerical primary-outcome analysis. It lists several secondary measures and reports zero serious adverse events and zero deaths in the two groups, alongside group-specific counts for other adverse events.

The posted record supports a description of the design and intended question, but does not provide the result required to estimate or interpret the primary treatment comparison.