Improving Adherence to Homework During Therapy: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Improving Adherence to Homework During Therapy (NCT05866185), a randomized na study. The primary outcome is Generalized Anxiety Disorder-7 (Gad-7).

2. Clinical Question

3. Trial Design

NCT05866185 is a completed randomized, parallel-group trial sponsored by the University of South Florida. The registry lists an enrollment of 79 and describes two behavioral interventions: standard therapy and standard therapy enhanced with Adhere.ly. Allocation is listed as randomized, masking as single, and the phase as NA. The identity of the masked group and further details of the masking procedure are not reported in the registry record.

The trial’s stated purpose was to compare standard therapy with therapy enhanced by a web-based platform intended to support practice of therapeutic skills between sessions. The listed conditions are anxiety, depression, and depression/anxiety. The record lists the study start as 2022-09-01, primary completion as 2024-05-29, and status as completed. These design and administrative details describe the registered study, but do not by themselves indicate how the interventions were delivered in practice or how completely participants followed them.

The primary outcome is GAD-7, assessed at baseline and 3 Months Post Baseline. Secondary outcomes include measures of mental health days, homework ratings, core CBT skills, attitudes toward homework, working alliance, and client satisfaction. The registry lists 10 outcome measures. It reports no analyses, and the primary outcome is not reduced to one comparison because it has several categories or time points. Arm-level primary-outcome results, the analysis method, and the identity of the masked group are not reported in the registry record. Consequently, the registered design can be described, but the treatment contrast cannot be quantified from the posted primary results.

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: While 40 therapists were enrolled in the trial, they were not assigned to a treatment arm until after their first referred client enrolled in the study. Not all therapists referred clients who enrolled in the study. As a result, the number of therapists allocated to a treatment arm differs from the number enrolled in the study.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: The Overall Number of Participants Analyzed refers to the number of participants enrolled and randomized to each arm. The number of participants analyzed in rows differs from this number due to participants being lost to contact and withdrawn from the study. The GAD-7 was completed by clients so data are not presented for therapists.

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: A total of 40 therapists were enrolled in the study. A total of 18 providers referred clients that enrolled in the trial and were subsequently randomized to a treatment condition. Data are reported for those providers who were randomized to a treatment condition.

6. Primary Endpoint

The registry lists the primary outcome as Generalized Anxiety Disorder-7 (Gad-7), measured over Baseline, 3 Months Post Baseline.

The primary endpoint is the Generalized Anxiety Disorder-7 (GAD-7), a client-completed measure described in the registry as assessing the severity of anxiety symptoms in adults. Scores range from 0 to 21, with higher scores indicating worse anxiety symptom severity. The record states that a score of 8 or greater is generally considered to indicate clinically significant anxiety symptom severity. This threshold gives readers a reference for interpreting an individual score; it does not replace a comparison of outcomes between randomized groups.

The endpoint is listed at baseline and 3 Months Post Baseline. Repeated measurement can describe scores at different points in a study, while a treatment comparison needs a clearly specified contrast, such as a difference between groups at a particular time or a difference in change over time. The registry record does not report a single reduced comparison across the GAD-7 time points and categories. It also does not report arm-level means, standard deviations, an estimated treatment contrast, or a confidence interval for the primary endpoint. Without those results, the direction, magnitude, and precision of any between-group difference cannot be assessed.

In general, a symptom scale can be useful for describing the outcome it measures, but a score alone does not establish why it changed. The GAD-7 endpoint concerns anxiety symptom severity; it is not itself a direct measure of homework completion or platform use.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The record describes a randomized, parallel-group design. In general, random allocation is intended to make treatment assignment independent of participants’ measured and unmeasured characteristics on average. This supports a fair comparison, but randomization alone does not guarantee that all participants provide outcome data or that the analyzed groups remain comparable after missingness. The method used to generate the allocation sequence, conceal assignments, or handle deviations from assigned treatment is not reported in the registry record.

What does a mean and standard deviation describe?

The primary outcome is classified as continuous and its summary parameter is a mean, with standard deviation as the dispersion measure. In general, a mean describes the center of a set of scores, while a standard deviation describes how spread out individual scores are around that center. A mean can make group-level comparisons readable, but it does not show the full distribution of scores or how many individuals experienced particular changes. The registry record does not report the primary outcome’s arm-level means or standard deviations, so those summaries cannot be interpreted for this trial.

A comparison of means is not the only possible analysis of a continuous outcome. An analysis may compare scores at a follow-up point, changes from baseline, or repeated measurements using a model. Those approaches answer related but not identical questions and can rely on different assumptions. The analysis approach selected for the primary outcome is not reported in the registry record. The record’s notation that the endpoint has several categories or time points and was not reduced to one comparison means that a reader should not infer a single treatment contrast from the outcome description alone.

Why does the analysis need a defined contrast?

A treatment effect is interpretable only after specifying what is being compared. A follow-up mean difference asks how the groups compare at follow-up; a change comparison asks how their movement from baseline compares. In general, a baseline measurement can help describe the groups and may be used in an analysis, but its presence does not identify which comparison was performed. Here, the record lists baseline and 3 Months Post Baseline, but does not report the primary analysis or a single reduced result. The exact estimand—the outcome contrast the analysis is intended to estimate—is therefore not reported in the registry record.

Uncertainty is usually described with a standard error or confidence interval. In general, a standard error reflects the estimated uncertainty of a statistic, while a confidence interval gives a range of values compatible with the data and method. A narrow interval indicates greater precision than a wide interval, but neither width nor location can be assessed without a reported estimate and interval. No primary-outcome confidence interval or p-value is reported in the registry record. Statistical significance would not, by itself, show whether a difference is important to clients; magnitude and context matter as well.

How should planning assumptions be read?

The registry’s planning description characterizes a sample-size illustration as based on the observed effect, with a two-sided significance level of 0.05, equal allocation between arms, and a normal approximation. It describes the effect to detect as a stated fraction of the observed effect. These are planning assumptions, not a report of the trial’s own design justification or a measure of the trial’s achieved power. The sample-size illustration is not observed power. The specific illustrated participant counts and effect values are not reported in the registry record details used for this analysis.

In general, a planning calculation estimates the number of participants needed under selected assumptions. Its output depends on the effect size, variability, significance level, allocation, and analysis method used. A calculation based on an observed effect can be particularly dependent on that estimate; it should not be read as proof that the trial was adequately powered or that a result is reliable. The record does not report a sample-size justification used to design the trial, or details such as anticipated attrition or a prespecified target effect.

Why can variability affect interpretation?

For continuous outcomes, more variability makes a group mean less precise when other features are held constant. In general, a model may also need to account for features such as repeated measurements or clustering if they are part of the study design. No such model details are reported in the registry record. It would therefore be speculative to say which variance structure, repeated-measure method, or adjustment was used. Interpretation should be limited to the registered design and the results actually reported, rather than assuming a conventional method.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists 10 outcome measures, including the primary GAD-7 and secondary measures of mental health days, homework ratings, CBT skills, homework attitudes, working alliance, and client satisfaction. Multiple outcomes and multiple time points create a multiplicity issue: in general, examining many comparisons can increase the chance of finding at least one apparently notable result by chance. Statistical plans may address this through prespecification, adjustment, or a hierarchy of outcomes. The approach to multiplicity is not reported in the registry record.

The primary outcome is recorded at baseline and 3 Months Post Baseline, and the registry notes that it has several categories or time points and was not reduced to one comparison. The record does not identify which time point or contrast was intended as the single primary inferential comparison. It also does not report whether other GAD-7 analyses were planned or how they would be interpreted. The analysis plan and any correction or prioritization among outcomes are not reported in the registry record.

The registry states that participants analyzed in outcome rows differ from those enrolled and randomized because of loss to contact and withdrawal. This is a material limitation: in general, missing outcome data can reduce precision and can bias a comparison if the chance of missingness is related to outcomes or treatment assignment. The record does not report the per-arm GAD-7 analysis counts, reasons by arm, a missing-data method, or sensitivity analyses. The full analysis population and whether an intention-to-treat principle was followed are not reported in the registry record.

Because the record reports no analyses and no reduced primary result, it is not possible to determine how missing data or multiple testing affected the primary comparison. These are uncertainties about the analysis, not evidence of bias in a particular direction.

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 lists serious adverse events, other adverse events, and deaths separately for clients and therapists. For clients in the Therapy group, the record lists 14 at risk for serious adverse events and 14 at risk for other adverse events, with zero affected in either category and zero deaths. For clients in the Therapy + Adhere.ly group, it lists 25 at risk for each adverse-event category, with zero affected in either category and zero deaths.

The therapist groups each have zero listed at risk for serious adverse events and zero at risk for other adverse events, with zero affected and zero deaths. Since the record lists no therapists at risk in either group, these entries do not provide an informative account of adverse-event frequency among therapists. No serious adverse event terms are listed.

In general, zero reported events in a group does not establish that an event is impossible or that there is no risk. It describes the registry’s reported counts for the populations listed. The record does not provide further detail about event definitions, collection procedures, observation time, or whether events were assessed for relation to treatment. These counts should therefore be read as the posted safety figures, not as a complete characterization of safety.

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

The registry record establishes that a randomized, parallel-group study compared standard regular therapy with standard regular therapy enhanced by Adhere.ly, and that the primary endpoint was GAD-7. It also records the study as completed and lists secondary measures relevant to homework, CBT skills, mental health days, working alliance, and satisfaction. These registry entries describe the question the trial set out to examine and the outcomes it registered.

They do not establish the result of the primary comparison. The record reports no analyses and does not reduce the primary outcome across its categories or time points to one comparison. No arm-level primary means, between-group estimate, confidence interval, or p-value is reported in the registry record. The posted information therefore cannot show whether the groups differed in anxiety symptom severity, how large any difference was, or how precisely it was estimated.

Nor does the record establish that the two approaches were equivalent. In general, a failure to report a difference is not the same as evidence that meaningful differences have been ruled out. Equivalence or non-inferiority conclusions require a specified margin and an analysis designed to assess it; such a margin and analysis are not reported in the registry record. Likewise, the intervention description and study purpose do not show whether Adhere.ly increased homework completion or changed clinical outcomes.

The GAD-7 measures anxiety symptom severity, not platform use or homework completion directly. The listed secondary outcomes include homework-related measures, but their results are not reported in the registry record. The record also notes that some participants were lost to contact or withdrew, and that outcome-row analysis counts differ from the enrollment and randomization counts. Without group-specific analyzed counts and missing-data methods, the impact of incomplete follow-up cannot be judged.

The appropriate interpretation is therefore limited: the registry describes a completed randomized comparison and records safety counts, but it does not provide the analyses needed to evaluate treatment effects on the primary or secondary outcomes. That limitation is about the available registry results; it is not a conclusion about what happened to participants or whether either treatment approach was beneficial.

13. Why This Trial Matters Statistically

This trial is statistically relevant because it connects an implementation-focused intervention—support for therapeutic practice between sessions—with a clinical symptom measure. The registered comparison is clear at a broad level: standard therapy versus standard therapy enhanced with Adhere.ly. The primary endpoint, GAD-7, measures anxiety symptom severity, while several secondary outcomes address homework, CBT skills, attitudes, alliance, and satisfaction. Together, those measures represent different aspects of the question; they should not be treated as interchangeable outcomes.

The record also illustrates why registration details and result reporting serve different purposes. Randomization describes how treatment assignment was structured, while an analysis result requires a defined contrast, a measure of uncertainty, and an account of who contributed data. Here, the registry notes multiple categories or time points for the primary outcome, reports no analyses, and does not provide a single reduced comparison. A trial can be completed and still leave its primary treatment contrast uninterpretable from the registry information available.

Missing outcome data matter in this setting because the record explicitly says the number analyzed differs from the number enrolled and randomized due to loss to contact and withdrawal. In general, a reader needs group-specific analysis counts and information about the handling of missing data to assess the strength of an outcome comparison. Without that detail, even a reported average would be harder to interpret; in this record, the primary averages and contrast are not reported.

The registry’s planning assumptions also illustrate a distinction between study planning and study findings. A planning illustration based on an observed effect is not the same as the trial’s original design justification, and it is not observed power. Keeping those concepts separate helps prevent planning calculations from being mistaken for evidence about the precision or success of a clinical comparison. In this case, the absent primary analysis remains the central statistical limitation.

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 for interpreting efficacy is that the registry record reports no analyses and no reduced primary comparison. Although GAD-7 is identified as the primary outcome and the measurement occasions are listed, arm-level results and an effect estimate are not reported. There is consequently no basis in the posted record for describing the direction, magnitude, or precision of a primary-outcome difference.

The analyzed population is also incompletely described. The record explains that outcome-row counts differ from the number enrolled and randomized because of loss to contact and withdrawal, but the GAD-7 analysis counts by arm and the reasons for missingness by arm are not reported. The record does not state how missing data were handled, whether all randomized participants were included in the primary analysis, or whether sensitivity analyses were conducted. These omissions prevent assessment of how attrition may affect the comparison.

Further limits concern analysis specification. The registry notes multiple categories or time points and does not reduce the primary outcome to one comparison. It does not report the selected primary contrast, statistical model, adjustment variables, handling of repeated measurements, or approach to multiplicity. These details are important for understanding exactly what effect an analysis would estimate and how uncertainty would be calculated.

The record does not provide further information about the masking procedure, implementation or uptake of Adhere.ly, adherence to the assigned intervention, or protocol deviations. The extent to which these factors affected treatment delivery cannot be judged. Finally, the listed safety counts have limited context: event definitions, ascertainment procedures, and observation time are not reported in the registry record. These limitations constrain interpretation of the registered information without establishing that any particular result is biased or incomplete.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Improving Adherence to Homework During Therapy — NCT05866185.
• Registry record last updated 2026-01-15; status last verified 2025-12.
• Results first posted 2026-01-15.
• 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

NCT05866185, titled “Improving Adherence to Homework During Therapy,” is listed as a completed randomized, single-masked, parallel-group study sponsored by the University of South Florida. The registry records enrollment of 79, a start date of 2022-09-01, and primary completion on 2024-05-29. The interventions were standard therapy and standard therapy enhanced with Adhere.ly.

The primary outcome was GAD-7 at baseline and 3 Months Post Baseline. The registry lists 10 outcome measures and reports no analyses; it does not reduce the primary outcome to one comparison across its categories or time points. Primary arm-level results and analysis details are not reported in the registry record. The record notes that outcome-row analyzed counts differ from the number enrolled and randomized due to loss to contact and withdrawal.

For clients, the registry lists zero serious adverse events, zero other adverse events, and zero deaths in both treatment groups. Therapist groups have zero listed at risk. These entries describe the recorded safety counts, with limited additional event-collection detail reported.