App for Strengthening Services In Specialized Therapeutic Support: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for App for Strengthening Services In Specialized Therapeutic Support (NCT05207956), a randomized na study. The primary outcome is The Difference in Data Collection Consistency Between Groups Across Three Weeks.

2. Clinical Question

The clinical question concerns whether adding features intended to motivate data collection and ease its burden changes how consistently behavioral health technicians (BHTs) enter session data. The comparison is between two versions of a mobile application used by BHTs working with students with autism: an enhanced electronic platform and a basic electronic platform without the additional features.

This is a question about data-entry consistency during the stated trial period, not a direct assessment of student outcomes or of the quality of the behavioral-health services. The registry describes the data as captured through web analytics in partnership with the digital health company. The posted primary results give group means and confidence intervals, but a between-group primary effect estimate and its statistical test are not reported in the registry record. The group summaries can therefore describe the observed consistency within each arm, but do not by themselves quantify a reliable difference between the versions.

3. Trial Design

The registry identifies this as a randomized, open-label, parallel-group trial. Participants were assigned to an enhanced electronic platform or an electronic platform that was not enhanced. Masking is listed as none. The study is marked completed, with a recorded start date of 2021-09-09 and primary completion date of 2022-06-21. The phase is listed as not applicable.

The study was conducted in partnership with a digital health software company. The research team created two application versions to support BHTs who collect data while working with students with autism. The enhanced version included additional features intended to increase motivation to record data and ease the data-collection burden. The comparator was the basic electronic data-collection platform. The posted description makes the distinction between the arms the added features, rather than the presence or absence of an electronic platform.

The registry reports 27 enrolled, with 14 in the treatment group and 13 in the control group in its primary-outcome population description; it also states that primary-outcome data were complete for 23. The posted primary summaries list 13 observations for the enhanced platform and 11 for the platform that was not enhanced. The record does not reconcile these different participant counts or explain the transition from enrollment to the posted outcome summaries. These counts should therefore be read as reported for their respective descriptions, not treated as interchangeable.

The parallel design compares the two groups over the same stated three-week trial period. The primary outcome was based on electronic web analytics, while the secondary outcomes include implementor intentions, usability, attitudes, perceived and descriptive norms, and self-efficacy. The registry record does not report further detail about the randomization procedure, allocation concealment, or a prespecified statistical analysis plan.

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

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: 27 were enrolled (14 treatment, 13 control) and data complete for 23

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 The Difference in Data Collection Consistency Between Groups Across Three Weeks, measured over Three-week trial period.

The primary endpoint is data-collection consistency, expressed as the percentage of intervals in which aides entered data per session with children during each school day across a three-week period. The registry says these metrics were captured through web analytics. This operational measure reflects whether data entry occurred during the defined intervals; it is not a direct measure of the accuracy or completeness of the recorded data, the quality of care, or student outcomes.

Tracking entry activity can provide a practical measure of whether an electronic workflow is being used in routine sessions. It is relevant to the stated purpose of the application features: encouraging data collection and easing its burden. A consistency measure can describe the frequency of recorded activity, but its interpretation depends on how intervals and sessions were defined and how missing or incomplete analytics were handled. Those details are not reported in the registry record.

The posted means are 0.66 for the enhanced platform and 0.44 for the platform that was not enhanced. Their confidence intervals are 0.51 to 0.8 and 0.19 to 0.7, respectively. The registry describes the endpoint unit as percentage of intervals, but the posted values are presented in the form above. No direct between-group primary estimate or test is reported. The group means therefore describe the observed results in each arm, while a formal comparative conclusion cannot be read from those summaries alone.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry describes a randomized, parallel-group comparison with no masking. The principal outcome is continuous and is summarized as a mean with a 95% confidence interval. Secondary continuous outcomes are reported as means with standard deviations. These summaries answer different questions: a mean describes the central value in a group, a standard deviation describes variation among observations in that group, and a confidence interval expresses uncertainty about an estimated quantity.

What does a confidence interval convey?

In general, a confidence interval gives a range of values compatible with the data under the statistical procedure used. It communicates estimation uncertainty; it is not a range containing a known fraction of individual observations. The primary outcome has intervals reported separately for each arm. Those arm-specific intervals are not the same as a confidence interval for the difference between arms. A direct comparative interval would describe uncertainty in the contrast relevant to the primary question, but that contrast is not reported in the registry record.

How should the secondary comparisons be read?

The registry lists no reported secondary analyses. The displayed secondary contrasts are recalculated from the posted group means, standard deviations, and sample sizes as simple unadjusted comparisons. They are not substitutes for an analysis conducted and reported by the study team. The associated p-values are unadjusted, and the comparisons do not account for the fact that several outcomes were assessed. The record does not describe a prespecified model, adjustment for baseline values, or any other covariate adjustment for these results.

In general, a p-value measures how unusual the observed data, or data more extreme, would be under a specified null hypothesis and statistical model. It does not give the probability that the null hypothesis is true, the probability that a result occurred by chance, or the size or practical importance of an effect. A p-value should be interpreted alongside the estimate, its uncertainty, the outcome definition, and the analysis plan. For the secondary results, the registry does not report trial-team analyses, and the posted p-values are unadjusted; they therefore warrant cautious interpretation.

Why do sample-size illustrations depend on assumptions?

The planning illustrations are not observed power and do not describe the trial’s original design justification. They use the observed effect as a planning input, assume two-sided significance level 0.05, equal allocation between arms, and a normal approximation, and consider detecting stated fractions of that observed effect. In general, such calculations are sensitive to the assumed effect size and variability. If the effect used for planning is uncertain, the resulting sample-size estimate is uncertain too. The registry record does not report the original sample-size justification, so the illustrations should not be taken as evidence about the adequacy of the study’s planned enrollment.

For continuous outcomes, a standard deviation is a measure of spread around a mean. Greater spread relative to the contrast of interest generally makes a precise comparison harder to obtain. For the secondary outcomes, the posted group standard deviations contribute to the recalculated comparisons; the registry does not provide a reported model that accounts for other sources of variation or repeated measurement.

What remains unclear about the analysis?

The registry record does not report the method used to generate the primary arm-level confidence intervals, the primary comparative analysis, or an analysis population definition beyond the enrollment and completion statements. It also does not explain how missing observations were treated, whether the baseline assessments were incorporated into the secondary analyses, or whether any interim analyses were conducted. These details should not be inferred from the fact that the study was randomized or from the posted summaries.

In general, over-dispersion matters when observed variation exceeds what a statistical model assumes: standard errors can then be understated and uncertainty intervals too narrow if the model does not accommodate that variation. The registry does not report a count-based model or an over-dispersion assessment for this continuous endpoint, so such methods cannot be attributed to this trial. The primary outcome is described as a percentage of intervals, but its reported analysis is summarized as a mean with a confidence interval. The record does not give enough detail to establish how interval-level observations were aggregated or whether within-person or within-session dependence was modeled.

The posted sample counts and the record’s enrollment and data-completion descriptions do not align in an explained way. This creates uncertainty about which observations contributed to each summary. Without a reported primary analysis and clearer accounting of the analyzed participants, the arm-level results are best read as descriptive statistics rather than a complete inferential comparison.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists multiple secondary outcomes in addition to the primary endpoint. It reports no analyses for the trial overall and no reported analyses for the secondary outcomes. The posted secondary comparisons are unadjusted recalculations, and the registry record does not report a multiplicity procedure, a hierarchy among outcomes, or a rule for interpreting secondary tests. When many outcomes are examined, some estimates may look unusual by chance; unadjusted results should therefore be treated as exploratory rather than as a collection of independent confirmatory findings.

The primary outcome description says 27 participants were enrolled and data were complete for 23. The enrollment description also gives treatment and control counts, while the posted primary arm summaries list different numbers of observations. The record does not reconcile these counts or describe an analysis population in enough detail to explain the difference. It does not report reasons for missing primary data, whether missingness differed by group, or how any incomplete records were handled. The missing-data method is not reported in the registry record.

The record also does not describe whether analyses followed intention-to-treat principles, whether participants were analyzed according to assignment, or whether any per-protocol or other analysis populations were used. Randomization is reported, but that alone does not establish how the analysis handled departures from assignment or missing observations. The statistical analysis plan, interim analyses, and sample-size justification are not reported in the registry record.

These omissions limit interpretation of both the primary summaries and secondary comparisons. Readers cannot determine from the registry alone whether the analyzed observations represent all randomized participants, whether baseline values were used in adjusted analyses, or whether any prespecified decision rules governed the outcomes. The posted results should consequently be interpreted as the record describes them, without filling these gaps through assumptions.

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 reports zero serious adverse events and zero deaths in each group. It also reports zero other adverse events in each group. The adverse-event group entries list 14 at risk in the enhanced-platform group and 13 at risk in the group using the platform that was not enhanced. No serious-event terms are listed.

These figures describe the events recorded in the registry; they do not establish that no adverse events could occur or that the intervention is safe in other settings. The registry record does not provide further information about adverse-event definitions, collection procedures, duration of safety monitoring, or the relationship of any event to the application. With limited information about ascertainment, zero reported events should be read as an absence of recorded events in these entries, not as proof of absence of risk.

The safety figures also do not address the primary question about data-collection consistency. They are a separate part of the registry record and should not be used to infer the effectiveness of either platform version.

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

The posted primary summaries describe data-entry consistency in each group during the three-week trial period. The enhanced-platform arm has a reported mean of 0.66, and the arm using the platform that was not enhanced has a reported mean of 0.44. The confidence intervals indicate uncertainty around those arm-specific means. The registry does not report a direct primary comparison, so the summaries alone do not establish the size or precision of a between-group effect.

The results do not show whether any difference was caused by the added features. Nor do they establish whether the collected data were accurate, whether students experienced different outcomes, or whether the platform changed the quality of behavioral-health services. The primary endpoint records whether data entry occurred in defined intervals, not what the entered data mean or how they were used.

The secondary measures describe implementor-related constructs, but their posted contrasts are unadjusted recalculations and are not reported trial-team analyses. They do not independently confirm the primary result. The registry record also leaves uncertainty about the analysis population, missing-data handling, and how the reported participant counts relate to one another.

The study is a randomized comparison of two application versions, but important information needed for a fuller statistical interpretation is not reported in the registry record. In particular, the primary between-group estimate and its uncertainty are absent. The responsible reading is therefore limited: the registry records arm-level outcome summaries and no recorded adverse events in the listed groups, but it does not provide the primary comparative analysis needed to quantify the evidence for a difference between platform versions.

13. Why This Trial Matters Statistically

This trial raises a useful statistical distinction between measuring use of a tool and testing whether the tool changes use. Web analytics can provide an operational measure of data-entry activity during routine work. But when the research question is comparative, arm-specific means are only part of the evidence: a direct between-group estimate, with its uncertainty and a clear analysis population, is needed to assess the contrast.

The registry shows why study status and randomized design do not by themselves guarantee that a comparative result can be interpreted fully. The trial is marked completed and randomized, but the primary comparison is not reported as an estimate or test. The record also gives different participant counts in its enrollment, data-completion, and arm-summary descriptions without reconciling them. These gaps matter because readers need to know which observations support the results and how uncertainty in the contrast was assessed.

The secondary outcomes illustrate another common issue: several measures can be collected, while the record may not specify which analyses were planned or how multiplicity was addressed. Unadjusted calculations from summary statistics can describe the posted data, but they carry less weight than prespecified, clearly reported analyses. Planning illustrations based on observed effects can help convey assumptions for future study planning, but they do not supply evidence of observed power or explain the original design.

For biostatisticians and clinical researchers, the key lesson is to distinguish descriptive summaries, recalculated comparisons, and trial-team analyses. Clear reporting of the primary contrast, participant flow, missing-data handling, and outcome hierarchy would make the evidence easier to interpret and reproduce.

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.

Several limitations specific to this registry record constrain interpretation. First, the primary outcome is reported by arm, but a direct between-group estimate, confidence interval, and test are not reported. The record indicates that values were missing or not estimable for a two-arm comparison of the continuous endpoint. The available summaries therefore do not fully answer the comparative primary question.

Second, participant counts are not reconciled. The registry reports 27 enrolled, gives treatment and control counts in the outcome-population description, states that data were complete for 23, and lists arm-level primary summaries with different counts. The record does not explain the differences or identify precisely which participants contributed to each analysis. Reasons for incomplete data and the missing-data method are not reported in the registry record.

Third, the registry provides little detail about the statistical plan. It does not report the primary analysis method, how any within-person or within-session dependence was handled, whether baseline measurements were incorporated into secondary analyses, or how multiplicity was addressed. No analyses are listed as reported by the trial team. The secondary comparisons are recalculations from posted summary statistics and should not be confused with investigator-reported analyses.

Finally, the outcome measures have a defined scope. Web analytics are described as recording data-entry consistency, not data accuracy, service quality, or student outcomes. The record does not give further detail about the construction of intervals, the handling of missing analytics, or the measurement properties of the secondary scales. These limitations do not show that the measures are invalid; they identify information that is not reported in the registry record and therefore cannot be assessed from these results.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: App for Strengthening Services In Specialized Therapeutic Support — NCT05207956.
• Registry record last updated 2025-03-07; status last verified 2025-03.
• Results first posted 2025-03-07.
• 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

NCT05207956 is a completed, randomized, open-label, parallel-group trial of an enhanced electronic data-collection platform compared with a basic platform for BHTs working with students with autism spectrum disorder. The study period is recorded from 2021-09-09 to primary completion on 2022-06-21. The primary endpoint was the percentage of intervals with data entered per session during each school day across a three-week period, captured through web analytics.

The registry reports arm-specific primary means and 95% confidence intervals but does not report a primary between-group estimate or test. It lists secondary implementor measures, with numerical summaries for some outcomes and no trial-team analyses reported. Enrollment, data-completion, and arm-summary counts are not reconciled in the record. Zero serious adverse events, other adverse events, and deaths are recorded in both groups. Interpretation is limited by missing comparative analysis details, unclear participant accounting, and unreported missing-data and multiplicity methods.