Violence Prevention for Middle School Boys: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Violence Prevention for Middle School Boys (NCT03109184), a randomized na study. The primary outcome is Change in Dating Violence (DV) Perpetration From Baseline to 9 Months.

2. Clinical Question

The clinical question concerns whether a web-based program completed by middle school boys with a parent is associated with a change in dating violence perpetration over follow-up, compared with a waitlist control. The registry describes the outcome as change from baseline to 9 months, with assessments at baseline, 3 months, and 9 months. The available record does not report the observed outcome values, an effect estimate, or uncertainty around a comparison between the groups. It therefore defines the question and measurement plan but does not establish the direction or size of any difference.

3. Trial Design

The registry describes a randomized, parallel-group study with no masking. The two named conditions are Project STRONG and Waitlist Control. Enrollment is listed as 119, and the study status is completed. The sponsor is Northeastern University. The registry lists the study start as 2015-01-01 and primary completion as 2018-08-30. The phase is recorded as NA. These details describe the trial framework; they do not provide evidence about the size or direction of the intervention effect.

Project STRONG is described as a behavioral, web-based program for teens and parents. Participants move through games, activities, and didactic information together. The program description identifies emotion management, communication, and problem-solving strategies, as well as sexual health content. The available description is incomplete, so additional components or delivery details are not reported in the registry record. The waitlist condition deferred program completion until after the 3-month and 9-month surveys.

The primary outcome is titled change in dating violence perpetration from baseline to 9 months. The outcome description identifies the Conflict in Adolescent Dating Relationships Inventory (CADRI), completed by teens about conflict or disagreement with a current or recent dating partner. Assessments are listed at baseline, 3 months, and 9 months. The primary outcome population is identified as a completer analysis. The record does not define completion, report the number included in that analysis, or explain how the additional assessment time point enters the primary comparison.

The record lists seven outcome measures and 30 analyses, but does not provide enough analysis detail to reconstruct the full statistical plan. In particular, the allocation sequence, concealment procedures, outcome-assessment masking, and analysis model are not reported in the registry record. No sample-size justification for the trial is reported. The planned sample-size illustration associated with the posted analysis is not the trial’s own design justification.

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: COMPLETER ANALYSIS

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 completer analysis was deemed appropriate as the small sample size of this pilot study could be impacted substantially from inadequate intervention dose. Analyses included intervention families who received an adequate dose of intervention, defined as a minimum of 4 out of 6 intervention modules (n=114/119).

6. Primary Endpoint

The registry lists the primary outcome as Change in Dating Violence (DV) Perpetration From Baseline to 9 Months, measured over Baseline, 3 months, and 9 months.

The primary endpoint concerns change in dating violence perpetration from baseline to 9 months. The registry identifies the CADRI as a behavioral measure of abuse perpetration and victimization. Teens report in reference to conflict or disagreement with a current or recent dating partner. Questions are asked separately about perpetration and victimization, producing distinct subscales. The outcome description says that percentages include teens endorsing any perpetration or victimization; the primary outcome title specifically identifies perpetration.

This type of endpoint is relevant to the stated study aim because it captures reported behavior rather than only attitudes or skills. The broader study description concerns emotion regulation, parent-son communication, and risk for dating violence involvement, while the primary endpoint focuses on reported perpetration. A measure of any endorsement can describe how many participants report the behavior, but it does not by itself convey frequency, severity, or context. The registry record does not report the exact scoring or threshold details beyond the description of endorsement.

The assessment schedule includes baseline, 3 months, and 9 months. Although the primary outcome title specifies change from baseline to 9 months, the role of the 3-month assessment in the primary analysis is not reported in the registry record. Nor are the observed endpoint values, group-specific changes, or a between-group effect estimate reported. Consequently, the record describes what was intended to be measured, but not the observed endpoint result or its precision.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry record describes a randomized, parallel-group study without masking. Randomization is intended to make treatment assignment independent of participants’ characteristics on average, although chance imbalances can still occur. A parallel-group design compares participants assigned to different conditions over the same general follow-up period. The record does not describe how the random sequence was generated, how assignment was concealed, or which people, if any, were unaware of the assignment. Those features are not reported in the registry record.

What does the endpoint measure?

The primary endpoint is described as change in dating violence perpetration from baseline to 9 months. The CADRI is completed by teens and asks about conflict or disagreement with a current or recent dating partner. The record describes separate perpetration and victimization subscales and says percentages include teens endorsing any perpetration or victimization. The title of the primary outcome specifies perpetration. The data type is identified as counts of participants, but the record does not give the observed counts or the exact statistical formulation used to compare changes. The assessment schedule also includes 3 months, and its role in the primary analysis is not reported.

How should an effect estimate be read?

In general, an effect estimate expresses the contrast being studied, such as a difference between groups in an outcome or in change over time. Its interpretation depends on how the outcome and contrast are defined. A confidence interval, in general, describes a range of values compatible with the data and the statistical method used; a narrower interval indicates greater precision, while a wider interval indicates less precision. A p-value, in general, quantifies how unusual data at least as incompatible with a specified null model would be if that model and its assumptions held. Neither a confidence interval nor a p-value is reported for the primary endpoint in the registry record, so these concepts cannot be applied to a numerical primary result.

What analysis details are missing?

The record does not report the statistical model, covariates, treatment of repeated measurements, or handling of clustering or dependence between observations. It does not state whether the primary comparison was adjusted, whether the analysis followed randomized assignment, or how participants with incomplete follow-up were handled. These choices matter because repeated observations from one participant are generally related, and the selected model determines how that relationship is represented. This is a general statistical consideration; the registry record does not identify the model used in this trial.

The primary outcome is marked as a completer analysis. In general, analyzing only participants with complete outcome information can be vulnerable to selection if completion is related to assignment or outcomes. An analysis retaining participants according to randomized assignment can preserve the original comparison, but its implementation still requires decisions about missing observations. The registry does not report the number missing, reasons for missingness, or any imputation or sensitivity analysis. It is therefore not possible to assess the impact of incomplete data.

How should multiplicity be considered?

The record lists seven outcome measures and 30 analyses. In general, assessing multiple outcomes or comparisons raises the chance that some findings may appear notable by chance alone. Statistical approaches can address this concern through prespecified primary outcomes, testing hierarchies, or adjustments, but the appropriate approach depends on the questions and analysis plan. The record does not report whether any such approach was used, nor does it identify the prespecified family of tests. The listed counts alone do not show which analyses were confirmatory or how their results should be weighted.

What does the planning illustration represent?

The sample-size assumptions describe a planning illustration based on an observed effect, with a two-sided significance level of 0.05, equal allocation, and a normal approximation. The target effect is described as a stated fraction of the observed effect. In general, sample-size calculations estimate the number of participants needed under specified assumptions; they are not observed power and do not establish that a study has detected an effect. The illustration is not the trial’s own design rationale. No trial-specific sample-size justification is reported in the registry record, and no sample-size illustration values are reported in the information available for this analysis.

The distinction between planned and observed quantities is important. Planning calculations depend on assumed effects and statistical methods; observed estimates depend on the data and the analysis actually conducted. A planning calculation cannot replace a reported effect estimate, confidence interval, or outcome count. Here, the registry record gives the endpoint definition and study structure, but it does not provide the primary numerical result or sufficient analysis details to evaluate the result statistically.

10. Multiplicity, Missing Data and Analysis Populations

The registry record lists seven outcome measures and 30 analyses. The primary outcome is change in dating violence perpetration from baseline to 9 months; listed secondary outcomes concern emotion regulation skills, parent-adolescent communication, and distress tolerance from baseline to 9 months. The record does not identify the full relationship between all outcome measures and analyses, designate a complete hierarchy of outcomes, or explain which analyses were confirmatory versus exploratory. It does not report a multiplicity adjustment or another strategy for interpreting results across the analyses.

In general, when many outcomes or comparisons are examined, the chance of at least one apparently notable result can increase. A prespecified primary endpoint and transparent reporting of the full set of analyses help readers distinguish the main study question from other analyses. The number of outcomes and analyses by itself does not reveal whether a particular result is robust; the analysis plan and results are needed. Neither a comprehensive result set nor adjustment details are reported in the registry record.

For missing data, the primary population is identified as a completer analysis. The record does not report how completion was defined, how many participants completed each assessment, whether missingness differed between groups, or why observations were missing. It also does not state how incomplete records were handled or whether sensitivity analyses were conducted. Consequently, the possible effect of missing data on the primary comparison cannot be assessed.

The distinction between randomized enrollment and the outcome analysis population matters. Enrollment is listed as 119, but the primary endpoint’s analyzed participant count is not reported in the registry record. The safety denominators do not establish how many participants contributed endpoint data. The record also does not report whether participants were analyzed in their assigned condition or whether any exclusions occurred after randomization.

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 serious-adverse-event entries list 60 participants at risk in Waitlist Control and 59 in Project STRONG. In each group, the number with a serious adverse event is recorded as 0, the number with other adverse events is recorded as 0, and deaths are recorded as 0. No top serious-event terms are listed. These are the safety figures recorded for the two groups.

These entries should be read as registry counts, not as a comprehensive demonstration that no adverse experiences occurred. The record does not provide further information about how adverse events were defined, how they were collected, the period of surveillance, or whether all event categories were reported. It does not give individual-level descriptions or explain whether the safety counts include participants who did not complete outcome assessments. The denominators shown for safety should not automatically be assumed to be the numbers analyzed for the primary endpoint.

Zero recorded events in these entries does not establish that the intervention has no risks, and it does not answer the primary effectiveness question. Conversely, these entries do not describe an observed safety signal. The registry record reports no serious adverse events, other adverse events, or deaths in either listed group, but its scope and level of detail limit what can be inferred beyond those counts.

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

The record describes a randomized comparison of a parent-and-teen web-based program with a waitlist condition. Its primary question concerns change in teen-reported dating violence perpetration from baseline to 9 months, measured using the CADRI. It also describes assessments at 3 months and identifies secondary areas including emotion regulation, communication, and distress tolerance. These registry entries explain the study’s focus and measurement approach.

What the record does not establish is the outcome. It does not report group-specific endpoint values, a comparison of change, an effect estimate, a confidence interval, or a p-value. Without those results, it is not possible to say whether the groups differed, by how much, or with what precision. The absence of a numerical result in the registry record is not evidence of no difference, and it should not be interpreted as evidence that the program did or did not change the measured outcome.

The outcome is based on teen reports of behavior concerning a current or recent dating partner. A measure of reported perpetration addresses a defined part of the study’s broader aims, not every possible dimension of relationships, communication, or safety. The program’s focus on emotion management and communication does not itself show that those skills changed, just as a change in a secondary skill measure would not by itself establish a change in perpetration. The registry record does not report results for those outcomes either.

The completer-analysis designation, missing-data details, and unreported analysis model also constrain interpretation. The enrollment figure does not reveal the number included in each outcome analysis. The record’s counts of outcome measures and analyses indicate a broad set of analyses, but the multiplicity approach is not stated. These gaps make it inappropriate to infer an analysis strategy or the reliability of any unreported finding.

The safety entries record zero serious adverse events, zero other adverse events, and zero deaths in both groups, using the listed group denominators. Those entries describe what is registered, but they do not answer the effectiveness question or establish a complete picture of safety. The appropriate conclusion is limited: the record identifies the design, study question, endpoint, and safety counts, while the primary outcome result and important analysis details are not reported.

13. Why This Trial Matters Statistically

This trial is statistically informative as an example of why a clear outcome definition and a reported numerical result are both needed. The registry identifies a behavioral endpoint, specifies the respondent and instrument, distinguishes perpetration from victimization, and gives an assessment schedule. Those details help readers understand what the study intended to measure. However, a defined endpoint alone cannot answer the comparative question; the observed counts or estimates and their uncertainty are necessary to assess what the data show.

The randomized, parallel-group structure frames a comparison between Project STRONG and a waitlist condition. Interpreting that comparison also depends on knowing the analysis population and how the repeated assessments were handled. The completer-analysis label signals that the analysis population deserves particular attention, while the absence of completion counts and missing-data methods leaves that issue unresolved. These are not technical details separate from interpretation: they influence which participants and observations support the estimate.

The registry also lists seven outcome measures and 30 analyses. That breadth makes transparent reporting of outcome prioritization and multiplicity methods especially useful. Without a stated hierarchy or adjustment approach, readers cannot tell how the full analysis set informed any reported conclusion. The record does not report these methods or the primary result.

Finally, the safety figures illustrate the importance of separating descriptive counts from broader claims. The registry lists no recorded adverse events or deaths in either group, but does not provide detailed collection or follow-up information. The figures should be read in their stated scope. Taken together, the study record provides a useful outline of the research question and design, while the missing result and analysis details prevent a statistical assessment of the intervention’s comparative effect.

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 principal limitation for interpretation is that the registry record does not report numerical results for the primary endpoint. No group-specific counts, changes, effect estimate, confidence interval, or p-value are available in the record. The study’s question can be characterized, but the comparative outcome cannot be assessed.

The primary population is labeled a completer analysis, yet the record does not define completion or give the number of participants contributing data at each assessment. It does not report missingness by group, reasons for missing data, or the method used to handle incomplete records. This leaves uncertainty about how the analyzed participants relate to those randomized and whether incomplete follow-up could affect interpretation.

The primary outcome title specifies baseline to 9 months, while the stated assessment schedule also includes 3 months. The role of the 3-month information in the primary analysis is not reported. The endpoint description refers to percentages of teens endorsing any perpetration or victimization, while the primary endpoint focuses on perpetration. Further detail about the scoring and statistical formulation is not reported in the registry record.

Important design and analysis details are also absent. The record does not describe sequence generation, allocation concealment, the statistical model, covariate adjustment, repeated-measures handling, or analysis according to assigned group. It lists seven outcome measures and 30 analyses but does not report a testing hierarchy or multiplicity approach. A trial-specific sample-size justification is not reported. The available safety entries are counts, without details about event definitions or collection. These limitations are specific to the information recorded and do not imply that unreported procedures were or were not used.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Violence Prevention for Middle School Boys — NCT03109184.
• Registry record last updated 2019-11-20; status last verified 2019-03.
• Results first posted 2019-11-20.
• 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

NCT03109184 is a completed randomized, parallel-group study sponsored by Northeastern University, comparing the web-based behavioral program Project STRONG with a waitlist control. The registry lists enrollment of 119, no masking, a start date of 2015-01-01, and primary completion on 2018-08-30.

The primary outcome is change in dating violence perpetration from baseline to 9 months, assessed with teen reports on the CADRI; assessments are listed at baseline, 3 months, and 9 months. The primary population is described as a completer analysis. The registry lists seven outcome measures and 30 analyses. It does not report the primary numerical result, the statistical model, missing-data handling, or a multiplicity strategy.

The serious-adverse-event entries list 60 participants at risk in Waitlist Control and 59 in Project STRONG, with zero serious adverse events, zero other adverse events, and zero deaths in each group. These counts describe the registry entries and do not supply the missing primary outcome result.