Parent Feedback Intervention Targeting Student Transitions and Alcohol Related Trajectories (+) Efficacy Study: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Parent Feedback Intervention Targeting Student Transitions and Alcohol Related Trajectories (+) Efficacy Study (NCT04549454), a randomized na study. The primary outcome is Change From Baseline Typical Weekly Drinking at 1 Month.

2. Clinical Question

The registry frames the broader study as an evaluation of an online adaptation of FITSTART, a parent-based social norms intervention. Its stated rationale is that correcting parents’ misperceptions about other parents’ alcohol-related parenting practices may influence their own parenting behavior and, in turn, student drinking. The record describes the aim as testing whether student-reported drinking and related negative consequences differed between the intervention app and a control version of the app. The primary posted outcome specifically concerns typical weekly drinking; it is not itself a combined measure of drinking and consequences.

The primary outcome summaries show mean change values of 1.67 for the Intervention App arm and 1.82 for the Control App arm. The unadjusted comparison, expressed as Intervention App minus Control App, is -0.15. These values describe the outcome as defined in the registry, rather than drinking levels at a single time point. The uncertainty interval around the comparison includes values on either side of zero, and the unadjusted p-value is 0.766. This statistical evidence does not establish a clear between-arm difference in the posted primary result.

The clinical question is about an average difference between assigned app groups, not whether every participant changed in the same way. The summary statistics do not show individual trajectories, and the registry record does not report the original analysis plan, details of the analysis population, or how missing follow-up observations were handled.

3. Trial Design

The registry identifies NCT04549454 as a randomized, single-masked, parallel study. Its title is “Parent Feedback Intervention Targeting Student Transitions and Alcohol Related Trajectories (+) Efficacy Study,” and its official title describes an extension and online adaptation of the FITSTART parent-based intervention. The listed phase is NA. The registry status is completed, with an enrollment of 266.

The two study arms are the Intervention App and Control App. In the intervention arm, a parent had access to FITSTART+ PBI materials, including a personalized normative feedback quiz, information on college student drinking, and alcohol-specific advice for parents of first-year students. The arm description also mentions general advice. In the control arm, a parent had access to general advice for parents of college students, information about university resources, and a community section. The record identifies both interventions as behavioral.

The primary outcome summary reports 111 participants in the Intervention App arm and 106 in the Control App arm. These are the arm counts attached to the posted primary outcome summaries. The record does not explain how those counts relate to the enrollment figure, or provide a detailed account of exclusions or the analysis population. It also does not state which individuals were masked.

The registry gives a study start date of 2021-07-22 and a primary completion date of 2022-03-22. The stated primary outcome timeframe is baseline and 1 month. The brief description places the intended assessment in the first semester of college and describes a longitudinal design. The registry lists 8 outcome measures and 8 analyses, but it does not provide posted secondary outcome results; the count of posted secondary results is 0.

Random allocation is intended to make the groups comparable on average, while a parallel design assigns participants to one of the study arms rather than having each participant receive both. Those are general features of randomized parallel studies; the registry record does not report the allocation sequence method, concealment procedures, or a fuller protocol description. The trial’s own sample-size justification and original design assumptions are not reported in the registry record.

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.

T1 to T2

Reasons for not completing this period:

T1 to T3

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.

Population: Baseline data was only collected for students because all outcomes for this trial are student behaviors. Thus, the participant attributes are those of the students and not their parents. Additionally, there are some discrepancies between the number of participants indicated in the Participant Flow and the number of participants who reported on outcomes. This is due to some participants not providing answers on some survey questions (i.e., survey questions were not forced response).

6. Primary Endpoint

The registry lists the primary outcome as Change From Baseline Typical Weekly Drinking at 1 Month, measured over baseline, 1 month.

The primary endpoint is change from baseline in typical weekly drinking at the 1-month follow-up, measured in typical alcohol drinks consumed per week. At each time point, participants reported the typical quantity of standard drinks consumed on each day of the week during the past 30 days using the Daily Drinking Questionnaire. The daily quantities were summed separately for baseline and the 1-month assessment to form a weekly total for each time point.

The endpoint is calculated as the baseline weekly measure minus the 1-month weekly measure. Under that definition, a positive value indicates a decrease in reported typical weekly drinking during the period; a negative value indicates an increase. The arm means are therefore mean changes, not mean drinking levels at follow-up. The registry reports a mean of 1.67 for the Intervention App arm and 1.82 for the Control App arm, with standard deviations of 3.65 and 3.77, respectively.

A change score is used to describe how an outcome moves over time, rather than describing only its level at one assessment. Comparing those changes between randomized arms addresses whether the average change differed by assigned group. As a general statistical point, a mean summarizes the average change but does not show the range of individual experiences or how the distribution is shaped. The reported standard deviations describe variation around the group means; they are not confidence intervals for the mean difference.

The primary outcome is specifically weekly drinking. Although the registry’s study description also refers to related negative consequences, those are not part of this primary endpoint definition. Details of any separate outcome scoring or the handling of missing outcome data are not reported in the registry record.

7. Results Posted in the Registry

• Intervention App: mean 1.67 versus 1.82 on control; difference -0.15 (95% CI -1.14 to 0.84), standardized effect d = -0.04; z-test p = 0.766.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous: it is a mean change in typical weekly drinks. The posted arm summaries give each group’s sample size, mean change, and standard deviation. The unadjusted re-calculation uses those summary statistics to estimate a difference between arm means and an interval for that difference. It is a summary-statistic comparison, not a reconstruction of participant-level data or of the sponsor’s full analysis.

What does the mean difference represent?

The re-calculated mean difference is -0.15 for Intervention App minus Control App. Since the outcome is baseline minus follow-up, positive change values correspond to decreased drinking. The contrast therefore describes the difference between the average changes, with a negative value indicating a lower mean change in the intervention arm than in the control arm. It should not be read as a difference in follow-up drinking levels, nor as a statement that every participant changed by that amount.

As a general statistical concept, a mean difference expresses the distance between two group averages in the outcome’s original units. Keeping the original unit makes the estimate directly interpretable as a difference in typical drinks per week on the defined change scale. The estimate alone does not convey its precision; that is why it is considered alongside a confidence interval.

Why is the standard deviation relevant?

The posted standard deviations are 3.65 in the Intervention App arm and 3.77 in the Control App arm. A standard deviation describes how spread out individual values are around the group mean. It is not the standard error of the mean and is not itself an uncertainty interval for the treatment contrast. The re-calculation uses the observed spread and arm sizes to estimate uncertainty around the difference in means.

As a general explanation, greater variation in outcome values makes a group average less precise when the sample size is held fixed. A mean difference can be small relative to the variation in individual change scores, making it difficult to distinguish a group contrast from sampling variability. This is relevant to interpretation, but it does not alter the reported estimate or establish why the result took the value it did.

How should the confidence interval and p-value be read?

The re-calculated 95% confidence interval runs from -1.138 to 0.838. In general, a confidence interval describes a range of estimates compatible with the observed data under the model and method used. It communicates both the estimated direction and the degree of uncertainty. Here its endpoints lie on opposite sides of zero, so the interval is compatible with a negative or positive mean difference as well as no difference.

The unadjusted p-value is 0.766. In general, a p-value evaluates how unusual the observed data, or data more extreme, would be under a specified null model. It is not the chance that an intervention is effective, the chance that the result will replicate, or the probability that the null is correct. A p-value should not be interpreted in isolation from the estimate, confidence interval, outcome definition, and analysis method.

The re-calculation is explicitly unadjusted. The registry record does not report the planned statistical model, any covariates, or the method used to account for repeated measurements. It also does not state whether the sponsor’s analysis was adjusted. Consequently, the re-calculation is a transparent comparison based on posted summary values, but it cannot substitute for an unavailable full analysis specification.

Why can the sponsor result differ in form?

The sponsor reports a Tukey-Kramer analysis for mean difference in final values, with an estimate of -0.011 and p = .985. The re-calculation instead uses the posted mean change values and their standard deviations. A comparison of final values and a comparison of change scores are different ways to define the outcome contrast. The record does not provide enough modeling detail to align them completely. The two results should therefore be described according to their own stated definitions rather than treated as identical calculations.

Tukey-Kramer is a named comparison procedure, but the registry entry does not explain the model to which it was applied, the other comparisons included in that procedure, or whether it served a multiplicity purpose in this trial. Those details are not reported in the registry record. The sponsor’s own result is the trial-reported analysis; the unadjusted calculation is a separate descriptive check from posted summaries. The registry does not flag a discrepancy between them.

What does over-dispersion mean in general?

For count outcomes, over-dispersion means that observed variation exceeds what a simple count model assumes. It can affect standard errors and confidence intervals if a model fails to account for that extra variation. This is a general concept, not a claim about the present endpoint: the primary outcome is reported as a continuous mean change with a standard deviation, and the registry does not report a count model or an over-dispersion assessment.

Likewise, general statistical methods cannot fill gaps in the trial record. The original sample-size justification, planned interim analyses, missing-data strategy, and analysis-population definitions are not reported in the registry record. The available summaries support an unadjusted comparison and a careful description of uncertainty, but not a reconstruction of those unreported procedures.

10. Confidence Intervals and Precision

The re-calculated mean difference is -0.15, and its 95% confidence interval extends from -1.138 to 0.838. The interval is the main guide to the precision of this unadjusted estimate. It includes zero and values in both directions, so the posted summary data do not pin down the direction of the between-arm mean difference with precision.

In general, a confidence interval represents uncertainty in an estimate under the assumptions of the statistical method used. A 95% confidence interval is not a guarantee that the true value lies within these particular endpoints, nor does it assign a 95% probability to the parameter after the data have been observed. Its practical value is that it displays a range of effect values compatible with the data and method. The estimate at the center is the point summary; the interval shows that the estimate is uncertain.

The interval is expressed on the original change-score scale, typical alcohol drinks consumed per week. Its width should be considered in relation to the endpoint and the question being asked. The registry does not give a threshold for what difference would be important, so the interval alone cannot establish whether all values within it would be practically unimportant or meaningful.

The unadjusted p-value of 0.766 is consistent with the interval including zero under the corresponding unadjusted comparison. Neither statistic proves equivalence. Demonstrating equivalence would require a specified equivalence margin and an analysis designed for that question; such a margin or analysis is not reported in the registry record.

The sponsor’s reported estimate of -0.011 and p = .985 come from its Tukey-Kramer analysis of final values. The registry does not report a confidence interval for that analysis. It is therefore not possible to describe the precision of the sponsor’s estimate using an interval from the registry record. The sponsor and re-calculated estimates also concern differently described contrasts, so their apparent proximity to zero should not be treated as a direct validation of one another.

11. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The planning figures are participants per arm, not a total across the two arms and not total events. They illustrate the sample sizes that would be required under the stated planning assumptions for detecting the specified share of the observed effect. The registry’s own original sample-size justification is not reported in the registry record.

The planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The planning effect is defined as a stated share of the observed effect. The rows describe planning for 100%, 75%, and 50% of the observed effect; the columns give participants per arm for 80% power and participants per arm for 90% power.

In general, power is the probability that a planned study will identify a difference at the chosen significance threshold if the assumed effect is real and the planning assumptions hold. The 80% column describes a design targeting an 80% chance of detecting the assumed effect; the 90% column targets a higher chance under that same assumed effect and method. These are design targets, not estimates of what happened in this completed trial.

For the stated planning scenarios, detecting 100% of the observed effect corresponds to 9,599 participants per arm for 80% power and 12,850 for 90% power. Planning for 75% of the observed effect corresponds to 17,064 participants per arm for 80% power and 22,844 for 90% power. Planning for 50% of the observed effect corresponds to 38,393 participants per arm for 80% power and 51,398 for 90% power. Smaller assumed effects need more participants because they are harder to distinguish from random variation under the same design assumptions. These figures are a planning illustration based on the observed effect, not observed power.

The registry does not report that these calculations were used to design the trial. They do not establish what sample size the investigators planned, what effect they considered important, or whether the completed study met a prespecified target. The stated assumptions define the illustration only; they should not be mistaken for the trial’s own protocol assumptions.

12. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = -0.150; pooled standard deviation σ = 3.709.
2. n = 2 × (1.96 + 0.842)² × 3.709² / -0.150² = 9,598.2, rounded up to 9,599 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
delta <- -0.15                      # observed difference in means
sigma <- 3.70908971469118                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(4549454)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 9,599 (80% power), 12,850 (90% power)
 75% of observed effect: n per arm = 17,064 (80% power), 22,844 (90% power)
 50% of observed effect: n per arm = 38,393 (80% power), 51,398 (90% power)
power.t.test: 9599.2 
Simulated power at n = 9,599 per arm: 0.800 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

13. Analyses Reported by the Sponsor

The sponsor-reported analysis is a Tukey-Kramer comparison of mean difference in final values. It reports an estimate of -0.011 and a p-value of .985. The registry does not provide a confidence interval for this analysis. This is the trial-reported result and should be described as such.

The unadjusted re-calculation uses the posted arm means and standard deviations for change from baseline in typical weekly drinking. It gives a mean difference of -0.15, a 95% confidence interval from -1.138 to 0.838, and an unadjusted p-value of 0.766. These values are not a replacement for the sponsor’s analysis: they are a separate, simple calculation from the posted summary statistics.

The analysis descriptions differ. The sponsor reports a comparison of final values, while the re-calculation compares the posted change-score summaries. The registry does not specify the complete model, covariates, or analysis population for the sponsor result, so the reasons for the difference in estimates and p-values cannot be determined from the record. The registry does not flag a discrepancy.

Both reported estimates are close to zero relative to the endpoints of the re-calculated interval, but that observation does not make the analyses identical or establish equivalence. The sponsor result should be used when describing the sponsor’s own analysis; the re-calculation is useful for understanding the posted change-score summaries and their uncertainty.

14. Multiplicity, Missing Data and Analysis Populations

The registry lists 8 outcome measures and 8 analyses, while the number of posted secondary results is 0. That means the primary comparison can be discussed from the available posted result, but the broader set of outcomes and analyses cannot be evaluated from posted secondary estimates. The record does not identify which of the listed outcomes were designated primary or secondary beyond the stated primary endpoint.

Multiplicity arises when several hypotheses or outcomes are tested. As a general statistical issue, conducting many tests can increase the chance that at least one result appears statistically notable by chance if no adjustment or other strategy is used. The registry record does not report whether the investigators planned a multiplicity adjustment, how the 8 analyses relate to the 8 outcome measures, or whether the sponsor’s Tukey-Kramer procedure addressed a particular family of comparisons. It would therefore be inappropriate to assume either that multiplicity was handled or that it was ignored.

The record also does not report how missing baseline or follow-up measurements were handled, how many participants contributed to each analysis beyond the posted primary arm counts, or whether an intention-to-treat, per-protocol, or other analysis population was used. These details matter because exclusions and missing observations can affect the population represented by the estimate and the uncertainty around it. The registry entry does not provide enough information to assess those choices.

The study description refers to a longitudinal design and describes baseline and 1-month assessments for the primary endpoint. It does not state whether the primary analysis used a change score, a model of repeated measurements, an adjustment for baseline, or another approach. The re-calculation uses the posted change summaries; the sponsor’s analysis is described as a comparison of final values. Neither description supplies a full statistical analysis plan.

Interim analyses and stopping rules are not reported in the registry record. The original sample-size justification and the rationale for the trial’s analysis choices are also not reported. These omissions do not invalidate the posted estimates, but they limit independent appraisal of how the primary result fits into the trial’s complete prespecified analysis strategy.

15. 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’s adverse-event record lists 134 participants at risk in the Intervention App group and 132 at risk in the Control App group. Serious adverse events are reported as 0 in each group. Other adverse events are also reported as 0 in each group, and deaths are reported as 0 in each group.

These figures describe what is recorded for the groups and denominators in the adverse-event entry. The at-risk counts are distinct from the primary outcome arm counts, which are 111 and 106. The record does not explain the relationship between those different sets of counts, so they should not be combined or treated as interchangeable.

In general, a report of zero recorded events means that none were reported in the specified record and group; it does not establish that no event of any kind occurred or that an intervention has no safety concerns. The registry does not provide serious-event terms, and the list of top serious-event terms is empty. It also does not describe event definitions, ascertainment procedures, follow-up completeness, or whether events were judged related to an app.

The safety figures are descriptive registry counts. They should not be read as a comparative safety analysis, and the record does not provide enough detail to determine how comprehensively adverse events were collected.

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

The primary result describes average change in typical weekly drinking between baseline and the 1-month follow-up. The Intervention App arm’s mean change is 1.67, and the Control App arm’s mean change is 1.82. The unadjusted estimated difference is -0.15 for intervention minus control, with a 95% confidence interval from -1.138 to 0.838 and an unadjusted p-value of 0.766. These data do not establish a statistically clear difference between the two arm means.

The outcome’s sign convention is important: a positive value indicates a decrease from baseline, while a negative value indicates an increase. The posted means are positive in both groups, but the between-arm estimate concerns the difference between average changes. It does not reveal how many participants decreased, increased, or stayed the same, nor does it characterize individual outcomes.

The confidence interval spans zero and both directions. This means the summary statistics do not give a precise estimate of the direction of the between-arm difference. A result that is not statistically clear is not proof that the treatments are equivalent, and it is not proof that any difference is exactly zero. The registry does not report an equivalence margin or a clinically important difference against which to judge the range.

The sponsor’s reported final-value comparison gives -0.011 with p = .985. That result is also not statistically clear, but it is not the same calculation as the unadjusted change-score comparison. The complete sponsor model is not reported in the registry record, so the two analyses should not be merged into one estimate or interpreted as if they used identical methods.

The study description concerns an online parent-based program and student drinking during the first semester in college. The posted primary result alone cannot establish whether the app changes drinking in other populations, over other follow-up periods, or on outcomes not reported. Although the registry refers to related negative consequences and lists 8 outcome measures, it posts no secondary results. The primary drinking result therefore cannot stand in for all outcomes the study may have examined.

The record also does not report the missing-data approach, analysis population, full statistical plan, or the trial’s original sample-size justification. Those gaps limit assessment of robustness and generalizability. The statistical interpretation is limited to the registered outcome definition and posted comparison; it is not medical advice and does not determine whether any participant should use a particular program.

17. Why This Trial Matters Statistically

This trial raises a statistical question about whether an online parent-based intervention can be evaluated through a randomized comparison of student-reported drinking changes. The registry describes an adaptation intended to extend FITSTART beyond on-campus orientation sessions by using an app. The primary endpoint is a defined change score, making the meaning of the direction explicit: positive values indicate a decrease in typical weekly drinking over the assessment period.

For biostatisticians and clinical researchers, the result illustrates why an estimate and its uncertainty should be read together. The point estimate is -0.15, but its 95% confidence interval ranges from -1.138 to 0.838. The interval makes clear that the available summary data do not tightly determine the direction of the difference. A p-value alone would not communicate that range of plausible values.

The trial also illustrates the importance of aligning estimands before comparing results. The sponsor reports a Tukey-Kramer comparison of final values, whereas the unadjusted re-calculation uses change-score summaries. The values can be described side by side, but the registry does not provide enough model detail to treat them as two estimates of exactly the same quantity. Clear reporting of the outcome contrast, analysis population, adjustment strategy, and uncertainty is important when readers assess trial findings.

Planning illustrations based on an observed effect can be informative about how assumptions influence design requirements, but they are not a substitute for an original sample-size rationale. The registry’s planning illustration assumes a two-sided significance level of 0.05, equal allocation, and a normal approximation; its original design assumptions are not reported. This distinction matters because post hoc planning scenarios should not be presented as proof that the completed study was adequately or inadequately powered.

Finally, the record lists multiple outcomes and analyses but posts no secondary results. Without a stated multiplicity strategy, missing-data details, and a fuller analysis plan, readers cannot fully assess how the primary comparison fits into the whole evidence base from the trial. Those reporting issues are broadly relevant to transparent interpretation of randomized clinical research.

18. 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 registry record leaves important details of the trial methods unspecified. The allocation is described as randomized, but the method of sequence generation and allocation concealment is not reported. Masking is listed as single, without identifying who was masked. These details are relevant to evaluating the conduct of a randomized study, but they cannot be inferred from the designation alone.

The primary outcome summaries include 111 participants in the Intervention App arm and 106 in the Control App arm, while the registry’s enrollment is 266. The record does not explain the relationship between those figures or state how many participants posted each assessment. The missing-data approach, exclusions, and analysis population are not reported. The adverse-event entry uses different at-risk counts, 134 and 132, and the record does not explain how they relate to the outcome counts.

The sponsor’s analysis is identified as Tukey-Kramer for mean difference in final values, but the full model and its assumptions are not described. The re-calculation uses the change-score means and standard deviations, so it does not reproduce the sponsor’s reported result. The registry does not state whether baseline adjustment, covariates, or a repeated-measures model were used in the sponsor analysis.

The record lists 8 outcome measures and 8 analyses but posts no secondary results. It does not report whether multiplicity was addressed, whether interim analyses were planned or conducted, or how outcomes beyond the primary measure were prioritized. The original sample-size justification is also not reported; the planning figures are an illustration based on the observed effect, rather than the documented basis for the trial’s design.

The intervention and control descriptions in the record are not fully detailed. The study concerns a particular online adaptation and a first-semester assessment, so the primary result does not establish how the program would perform in other settings, with different parent access, or over other periods. The registry does not provide enough information to assess implementation, adherence, or the extent of app use. These limitations constrain interpretation without changing the values that are posted.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Parent Feedback Intervention Targeting Student Transitions and Alcohol Related Trajectories (+) Efficacy Study — NCT04549454.
• Registry record last updated 2023-06-01; status last verified 2023-05.
• Results first posted 2023-06-01.
• 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.

22. Record Summary

NCT04549454 is a completed randomized, single-masked, parallel study of the FITSTART+ PBI intervention app compared with a control app. The registry lists an enrollment of 266 and dates the study start to 2021-07-22, with primary completion on 2022-03-22. The listed phase is NA.

The primary endpoint is change from baseline in typical weekly drinking at 1 month. Positive change indicates a decrease. The posted arm means are 1.67 for the Intervention App and 1.82 for the Control App. The unadjusted re-calculation estimates a mean difference of -0.15, with a 95% confidence interval from -1.138 to 0.838 and p = 0.766. The sponsor-reported Tukey-Kramer final-value comparison is -0.011 with p = .985.

The registry lists 8 outcome measures and 8 analyses but posts 0 secondary results. Details of the missing-data strategy, analysis population, multiplicity handling, full statistical plan, and original sample-size justification are not reported in the registry record.