Efficacy of a Web-Based Alcohol Intervention for High School Students: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Efficacy of a Web-Based Alcohol Intervention for High School Students (NCT03613818), a randomized na study. The primary outcome is Weekly Drinking.

2. Clinical Question

The study is registered as a randomized, parallel-group trial. Its stated aim is to evaluate the intervention in relation to underage drinking and associated negative consequences among high school seniors. The primary outcome is a continuous measure, expressed as drinks per week, with higher scores designated as worse outcomes.

The registry record identifies Alcohol-Related Consequences as a secondary outcome. It also lists six outcome measures, but does not report numerical results or analysis details for the primary outcome. The question can therefore be described from the trial record, but the posted information does not establish the direction, size, or precision of any difference between groups.

3. Trial Design

The registry record identifies a randomized, parallel-group design with no masking. The two arms are eCHECKUP TO GO and Control. The intervention is behavioral and is described as a brief, web-based alcohol intervention; the control is described as assessment only. The registered enrollment is 311.

The record gives a study start date of 2018-09-15 and a primary completion date of 2019-04-01. The study status is completed. The phase is listed as NA, and the condition is Underage Drinking. Boise State University is listed as the sponsor.

The primary outcome is Weekly Drinking, measured in drinks per week and summarized as a mean with a standard deviation. It is assessed at baseline, 1 month follow-up, and 6-month follow up. Because the outcome is described at several time points, a group comparison requires a clear definition of which time point or contrast is being estimated. The registry record does not identify a single primary comparison among those time points, and its posted results do not give numerical outcome estimates.

Random allocation is intended to make treatment groups comparable on average, though it does not guarantee identical group characteristics. With no masking, participants and study personnel were not masked according to the record. The record does not describe who generated or implemented the allocation sequence, whether allocation was concealed, or other procedures beyond the design labels stated above. Those details are not reported in the registry record.

The study summary presents eCHECKUP TO GO as a brief intervention intended to address underage drinking and related consequences, with a goal of being easily disseminated as a school-based intervention. This is a statement of purpose, not evidence of effectiveness. The available record provides a design description, but does not report numerical primary-outcome findings that would permit an estimate of the intervention’s observed association with weekly drinking.

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

Analysis population for the primary outcome, as defined in the registry: One participant was removed from the analyses due to unreliable reporting

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 Weekly Drinking, measured over Baseline, 1 month follow-up, and 6-month follow up.

Weekly Drinking is the primary endpoint. It is a continuous measure reported in drinks per week, summarized by a mean and standard deviation. The assessment uses the Daily Drinking Questionnaire: respondents report the number of drinks they probably would have on each day of a typical week, and the seven daily reports are combined to form the weekly measure. The record describes a minimum of 0 and no stated maximum; it also gives a sample score range with a maximum of 26. Higher scores are designated as worse outcomes.

A continuous endpoint can retain information about the magnitude of reported drinking rather than reducing responses to a simple yes-or-no category. Means describe the average level in a group, while standard deviations describe how dispersed individual scores are around that average. These summaries can help characterize both the group’s typical score and variability among participants.

Measuring weekly drinking at baseline and follow-up provides a way to describe drinking over time and compare patterns between the randomized groups. The registry record specifies baseline, 1 month follow-up, and 6-month follow up, but does not report numerical means, standard deviations, or group contrasts at those time points. Consequently, the endpoint’s definition is available, while its observed results and precision are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry describes the study as randomized and parallel-group. In a randomized design, assignment to the intervention or control is determined by an allocation process rather than by participants choosing their group. As a general statistical principle, randomization helps limit systematic differences between groups at the start of a trial, on average. It does not ensure that every measured or unmeasured characteristic is balanced in a particular trial. Details of sequence generation and allocation concealment are not reported in the registry record.

A parallel-group design assigns participants to a group and compares the groups over the study period. Here, the named arms are eCHECKUP TO GO and Control, with assessment only described as the control condition. The record states that masking was none. In general, masking can reduce the influence of expectations on reporting, care, or outcome assessment, depending on who is masked. The record does not provide further detail about outcome assessment procedures.

The primary outcome is continuous: a mean is used to summarize weekly drinks, and a standard deviation describes the spread of scores around the mean. As a general explanation, the standard deviation is a descriptive measure of variability among observations; it is not the same as the standard error, which describes uncertainty in an estimated quantity. The registry record does not post the group means or standard deviations needed to characterize the observed outcome.

The assessment asks respondents to report expected drinks for each day of a typical week and combines the seven reports. This produces a weekly measure in drinks per week. Self-reported measures can be affected by recall, interpretation of a drink, and willingness to report; these are general considerations for questionnaire outcomes, not reported findings about this trial. The record specifically states that one participant was removed from analyses because of unreliable reporting, but it does not explain the reliability criterion or describe further data-quality procedures.

Several measurements over time call for an analysis that recognizes how observations from the same participant are related. As a general statistical point, repeated measurements on an individual are usually not independent; methods that account for within-person association can avoid treating those observations as unrelated information. Different analyses might estimate follow-up group differences, change from baseline, or an overall time pattern. Their interpretation depends on the model, the time points included, and the contrast chosen. The analysis method and the intended primary contrast are not reported in the registry record.

A confidence interval, in general, gives a range of values compatible with an estimate under the assumptions of the statistical model and conveys precision. A narrower interval indicates greater precision than a wider interval, all else equal. A confidence interval does not resolve bias from measurement or missing data, and it does not by itself indicate whether a difference is practically important. No primary-outcome confidence interval is reported in the registry record.

A p-value, as a general concept, describes how unusual data at least as extreme as those observed would be under a stated null hypothesis and model. It is not the probability that the null hypothesis is true, nor a direct measure of the size or importance of an effect. The registry record lists no analyses and does not report a primary-outcome p-value. The statistical plan, including any prespecified model or hypothesis test, is not reported in the registry record.

The sample-size assumptions described in the record are for a planning illustration based on an observed effect, not the trial’s own design. The stated assumptions are a two-sided significance level of 0.05, equal allocation between arms, and a normal approximation; the effect to detect is a stated fraction of the observed effect. Those assumptions explain the basis for a planning exercise, but no calculated planning values are included in the registry record for this account. Such illustrations are not observed power and do not replace an estimate and uncertainty interval from trial data. The trial’s sample-size justification is not reported in the registry record.

In general, over-dispersion occurs when observed variability is greater than a statistical model assumes. If a model understates variability, standard errors can be too small and intervals or tests can give an overly optimistic impression of precision. This concept may matter for outcomes whose distributions do not fit a simple model, but the registry record does not provide enough outcome data or analysis detail to assess the distribution of weekly drinking or whether over-dispersion was considered.

Interpretation also depends on the analysis population. An intention-to-treat analysis generally retains participants in their randomized groups, while analyses based on available observations or exclusions can answer different questions and may be vulnerable to selection effects. The record notes the removal of one participant due to unreliable reporting, but does not report whether the primary analysis followed an intention-to-treat approach or how other exclusions were handled. These methods cannot be inferred from the randomization label alone.

10. Multiplicity, Missing Data and Analysis Populations

The registry record lists six outcome measures, with Weekly Drinking identified as the primary outcome and Alcohol-Related Consequences listed as a secondary outcome. It does not report a multiplicity strategy, such as adjustment of significance thresholds or a hierarchy of hypotheses. When several outcomes or time-point comparisons are tested, the chance of finding at least one apparently unusual result can increase. As a general statistical point, prespecifying a primary comparison or accounting for multiple testing can help clarify how results should be interpreted. The record does not state how multiplicity was addressed.

The primary outcome is measured at baseline, 1 month follow-up, and 6-month follow up. The record does not identify a single primary contrast across these measurements. It is therefore not possible to determine from the registry record whether follow-up values, changes from baseline, or a repeated-measures summary were intended as the central test. The analysis details are not reported in the registry record.

The record says one participant was removed from the analyses because of unreliable reporting. It does not explain how reliability was assessed, whether the exclusion was determined before examining outcomes, or how missing measurements at follow-up were handled. The number of missing outcome observations, reasons for missingness, imputation methods, and sensitivity analyses are not reported in the registry record.

As a general statistical point, missing data can affect both the representativeness of the analyzed participants and the precision of estimates. An analysis using only observed measurements relies on assumptions about why data are missing; different assumptions can lead to different conclusions. The registry information does not permit assessment of those assumptions. The analysis population, including whether participants were analyzed according to randomized assignment, is not reported in the registry record.

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 safety record lists the eCHECKUP TO GO arm with 174 participants at risk for serious adverse events and 0 affected, and 174 at risk for other adverse events and 0 affected. It lists 0 deaths. For Control, it lists 137 participants at risk for serious adverse events and 0 affected, and 137 at risk for other adverse events and 0 affected. It also lists 0 deaths. No top serious adverse event terms are listed.

These figures are counts recorded in the registry. They indicate that no affected participants or deaths are listed in these categories for either arm. They do not provide a detailed description of how events were solicited, classified, or reviewed, and no event narratives are reported in the registry record.

As a general statistical point, a count of zero recorded events does not establish that the underlying risk is exactly zero. The precision of a risk estimate depends on the number observed, the amount of observation, and the way events were collected and reported. The registry figures should therefore be read as reported counts, not as proof that no event could occur or as a comparison establishing a difference between arms.

The safety counts address adverse events and deaths; they do not report the primary outcome of weekly drinking. Neither the safety figures nor the absence of listed serious-event terms supplies an estimate of the intervention’s effect on drinking.

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

The registry record establishes that a randomized, parallel-group study compared a brief, web-based alcohol intervention with an assessment-only control among high school seniors. It identifies weekly drinking as the primary outcome and describes how the measure was constructed from reports for each day of a typical week. It also gives the assessment time points and identifies Alcohol-Related Consequences as a secondary outcome.

Those details define what the study set out to investigate; they do not answer whether the intervention changed weekly drinking. Numerical group results, a between-group contrast, and an estimate of precision are not reported in the registry record. No direction or magnitude of effect can therefore be stated from these records. The study’s completed status is not a substitute for outcome findings.

As a general principle, an estimated difference should be interpreted alongside its uncertainty and the way it was analyzed. A small p-value alone would not establish practical importance, while a non-small p-value would not prove that groups are identical. Such interpretation requires the actual estimates and their context. Those numerical findings are absent from the registry record.

The study summary describes an aim of providing a brief, low-cost intervention that could be disseminated as a school-based intervention. This describes the intended public-health use, not a demonstrated result. The record does not report evidence on implementation, uptake, cost, or dissemination, so those aspects cannot be evaluated from the information recorded.

The safety counts report zero affected participants for serious and other adverse events in both arms, and zero deaths. These counts should be understood as the registry’s reported safety information. They do not determine the primary outcome, and they do not establish that an intervention has no possible risks.

The defensible conclusion is limited: the trial question and endpoint are documented, but the registry record does not report the numerical primary-outcome results needed to assess the observed difference or its precision. It would be inappropriate to infer a benefit, no effect, or equivalence from the absence of those results.

13. Why This Trial Matters Statistically

This trial is statistically informative as an example of why a clearly described design and a reported result are different kinds of evidence. The record identifies randomization, the intervention and control conditions, the primary endpoint, and the measurement schedule. Those elements help readers understand the question being studied. Without group outcome summaries or an estimated contrast, however, they do not show what the data indicate.

Weekly drinking is measured as a continuous outcome based on self-reports across a typical week. Such an endpoint preserves variation in reported amounts and can support analyses of average levels or changes over time. At the same time, interpretation depends on the quality and completeness of reports and on how repeated measurements are modeled. The record notes an exclusion for unreliable reporting, while leaving the reliability criteria and broader missing-data approach unreported.

The multiple time points also make the statistical target important. A difference at a particular follow-up, a difference in change from baseline, and a pattern over time are distinct questions. A reader needs the planned contrast and analysis approach to know which question an estimate answers. Those analysis details are not reported in the registry record.

For clinical researchers, the case illustrates the value of reporting estimates, uncertainty, analysis populations, and missing-data methods alongside design descriptions. For biostatisticians, it underscores that a registered endpoint alone cannot recover an effect estimate, and that planning assumptions should not be mistaken for observed findings. The registry’s planning assumptions describe an illustration, not observed power or evidence about the trial outcome.

The record is useful for identifying the intended comparison and measurement strategy, while the absence of numerical primary-outcome results limits statistical interpretation. That distinction matters whenever a registry entry is used to understand what a trial can and cannot establish.

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 limitation of the available record for statistical interpretation is that it does not report numerical results for the primary outcome. There are no group means, standard deviations, effect estimates, confidence intervals, or p-values for weekly drinking. The observed direction, magnitude, and precision of any group difference cannot be assessed.

The outcome is measured at baseline, 1 month follow-up, and 6-month follow up, but the registry record does not specify a single primary comparison among those time points. It does not report the analysis model or explain how repeated observations were handled. This makes it impossible to identify the estimand or assess whether the analysis matched a prespecified plan.

The record notes that one participant was removed from analyses because of unreliable reporting. It does not state the reliability rule, the timing of that decision, the number of missing observations at follow-up, or the treatment of missing data. The analysis population and any sensitivity analyses are not reported in the registry record.

The trial is described as unmasked. The record does not provide further detail about who knew assignments or how outcome reporting was collected and assessed. Since weekly drinking is based on self-report, measurement and reporting processes are relevant considerations, but their influence cannot be determined from the registry information.

The registry lists six outcome measures and one secondary outcome category, but does not report a multiplicity plan or specify how the several time points relate to the primary hypothesis. The sample-size justification and the full statistical plan are not reported in the registry record. These limitations concern what can be evaluated from the available entry; they are not evidence that a particular design or analysis choice was made.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Efficacy of a Web-Based Alcohol Intervention for High School Students — NCT03613818.
• Registry record last updated 2021-04-01; status last verified 2021-03.
• Results first posted 2021-04-01.
• 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

NCT03613818 is a completed randomized, parallel-group study sponsored by Boise State University. The registry lists an enrollment of 311, a start date of 2018-09-15, and a primary completion date of 2019-04-01. Masking is listed as none.

The study compares eCHECKUP TO GO, described as a brief, web-based alcohol intervention, with Control, described as assessment only. Weekly Drinking, measured in drinks per week, is the primary outcome. It is assessed at baseline, 1 month follow-up, and 6-month follow up. Alcohol-Related Consequences is listed as a secondary outcome, and the record lists six outcome measures.

The record states that one participant was removed from analyses because of unreliable reporting. It lists no analyses and does not report numerical primary-outcome results. The safety record lists zero affected participants for serious and other adverse events and zero deaths in both arms. These details describe the registered record; they do not provide an estimate of the intervention’s effect on weekly drinking.