Evaluation of an Interactive Opioid Risk Education Program (STOMP) for Parents: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Evaluation of an Interactive Opioid Risk Education Program (STOMP) for Parents (NCT03287622), a randomized na study. The primary outcome is Opioid-related Risk Knowledge.

2. Clinical Question

The clinical question concerns a parent’s knowledge of an opioid-related risk, not a child’s clinical outcome. The registry describes the broader purpose as helping parents recognize opioid risks and make safe and effective analgesic decisions while managing medicines at home. The primary outcome therefore captures one specific element of that broader aim: awareness of over sedation after surgery. Other registered outcomes address disposal behavior, pain interference, analgesic self-efficacy, analgesic use or adherence, and decision competency. The registry record does not report the detailed wording or scoring method used to determine awareness beyond its binary description.

3. Trial Design

This completed trial, NCT03287622, evaluated the Scenario-tailored Opioid Messaging Program (STOMP) for parents. The sponsor was the University of Michigan. The registry lists randomized allocation, triple masking, and a factorial model. Enrollment was 712. The recorded start date was 2017-10-24, and primary completion was 2019-09-30.

The intervention structure included two behavioral components: Educational Intervention and Nudge. Four combinations were described: STOMP education with a Nudge, standard-of-care information with a Nudge, STOMP education without a Nudge, and standard-of-care information without a Nudge. The primary outcome comparison is reported as Education Intervention versus Standard of Care Education. The posted secondary summaries include four groups for disposal behavior, reflecting the two intervention components, while other outcomes are reported as two-group comparisons.

The registry’s brief summary describes parents and children undergoing elective surgery and says 840 parents and their children would be recruited. The recorded enrollment is 712; the registry record does not explain the difference between the proposed recruitment figure and enrollment. The record identifies the intended timing of parent knowledge and perception assessments as baseline and critical times after surgery, with the primary outcome at Day 3 follow-up. It also describes assessment of opioid handling and administration.

The trial is listed as phase NA. The original statistical analysis plan, the rationale for the target enrollment, details of masking implementation, and the trial’s original sample-size assumptions are not reported in the registry record. The presence of randomized allocation and a factorial structure does not, by itself, establish which factorial effects or interactions were prespecified for statistical testing.

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: These parents completed at least one follow-up assessment for risk awareness

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: 298 subjects (84%) completed surveys required for analysis in the INTERVENTION GROUP. 308 subjects (87%) completed surveys required for analysis in the STANDARD OF CARE GROUP

6. Primary Endpoint

The registry lists the primary outcome as Opioid-related Risk Knowledge, measured over Day 3 follow-up assessment.

The primary endpoint is the number of parent participants who became aware of a serious opioid-related adverse effect, specified as over sedation. It is measured at the Day 3 follow-up assessment and treated as a binary outcome: a participant either met the registry’s awareness criterion or did not. The stated population for this outcome consists of parents who completed at least one follow-up assessment for risk awareness.

A knowledge endpoint is relevant to the intervention’s educational purpose. Parents who manage medicines need to recognize opioid-related risks, and awareness of over sedation is one concrete, assessable element of that knowledge. The endpoint does not measure all opioid safety behaviors, whether a parent acted on the information, or whether a child experienced an adverse event. Those are distinct questions. The registry lists other outcome domains, including disposal behavior, pain interference, self-efficacy, analgesic use or adherence, and decision competency.

The endpoint is reported as participant counts by group, with a comparison expressed as a risk difference. This makes the contrast interpretable as the difference between the proportions recorded as aware in the two groups. The registry record does not report the exact assessment instrument, a fuller operational definition of awareness, or whether the endpoint was assessed by a blinded evaluator.

7. Results Posted in the Registry

• Education Intervention: 97.0% (287/296) versus 93.8% (289/308) on control; risk difference 3.1 percentage points (95% CI -0.2 to 6.5), risk ratio 1.03 (1.00–1.07); unadjusted two-proportion z-test p = 0.068.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Opioid Disposal Behavior

• Endpoint type: Binary: the number of participants with the event, compared as proportions.
• Test: Unadjusted two-proportion z-test, with a Wald 95% confidence interval for the risk difference.
• Result:
  • Nudge + Educational Intervention: 38.7% (48/124) versus 33.6% (44/131) on control; risk difference 5.1 percentage points (95% CI -6.7 to 16.9), risk ratio 1.15 (0.83–1.60); unadjusted two-proportion z-test p = 0.395.
  • Educational Intervention Only (No Nudge): 31.0% (40/129) versus 33.6% (44/131) on control; risk difference -2.6 percentage points (95% CI -13.9 to 8.8), risk ratio 0.92 (0.65–1.31); unadjusted two-proportion z-test p = 0.656.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Nudge + Educational Intervention and the control. The interval gives the range of effects that remain compatible with the data.
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Educational Intervention Only (No Nudge) and the control. The interval gives the range of effects that remain compatible with the data.

Pain Interference (PROMIS)

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Education Intervention: mean 8.63 versus 8.06 on control; difference 0.57 (95% CI -0.79 to 1.93), standardized effect d = 0.07; z-test p = 0.412.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Education Intervention and the control. The interval gives the range of effects that remain compatible with the data.

Analgesic Self-Efficacy

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Education Intervention: mean 32.50 versus 32.20 on control; difference 0.30 (95% CI -0.22 to 0.82), standardized effect d = 0.09; z-test p = 0.254.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Education Intervention and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes address several distinct links in the intended pathway from education to safer medication management: disposal behavior, pain interference, self-efficacy, and other listed domains of use, adherence, and decision competency. The posted numerical summaries cover disposal behavior, pain interference, and analgesic self-efficacy. Numerical results for analgesic use or adherence and analgesic decision competency are not reported in the registry record.

Across the reported secondary comparisons, the estimates do not form a consistent, precise pattern that would independently reinforce the primary knowledge result. The disposal comparisons are organized around the factorial combinations, while pain interference and self-efficacy use two-group summaries. Their confidence intervals include zero, leaving uncertainty about the direction and magnitude of the contrasts. Because these endpoints measure different constructs, a result on one cannot be assumed to explain or validate another.

These secondary findings are also less conclusive when considered alongside the number and variety of outcomes. The registry record lists multiple secondary domains, but does not report a multiplicity adjustment or a complete analysis plan. When several outcomes and contrasts are examined, chance variation can produce apparently notable estimates even if there is no underlying effect. Unadjusted results are useful for describing the posted data and generating questions for further study, but they carry less inferential weight than a prespecified primary analysis with a stated approach to multiplicity.

The secondary data should therefore be read as complementary, not as a substitute for the primary endpoint. They broaden the picture of measured parent behavior and experience, but the registry record does not establish that changes in knowledge translated into consistent changes in behavior or other outcomes. The available summaries support cautious description rather than a unified conclusion across all secondary domains.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Opioid Disposal Behavior
• Pain Interference (PROMIS)
• Analgesic Self-Efficacy
• Analgesic Use / Adherence
• Analgesic Decision Competency

9. Statistical Interpretation

10. Statistical Methods Explained

General: What does a risk difference mean? A risk difference compares the proportion with an event in one group with the proportion in another. For the primary endpoint, the event is becoming aware of over sedation. A positive estimate means the recorded event proportion was higher in the education group than in the standard-of-care group; a negative estimate would mean it was lower. The estimate is an absolute contrast on the probability scale, rather than a ratio. The registry’s primary comparison reports the risk difference as 0.031.

General: Why report a confidence interval? A point estimate is based on the observed participants and is subject to sampling variation. A confidence interval communicates a range of values compatible with the data under the analysis method. It is not a guarantee that the true effect lies in that range, nor does it give the probability that the effect is exactly one value. For the primary comparison, the reported interval runs from -0.002 to 0.065 and includes zero. That leaves uncertainty about the direction and size of the difference.

General: What does an unadjusted p-value convey? A p-value measures how compatible the observed data are with a specified null hypothesis under the statistical model. It is not the probability that the null hypothesis is true, and it does not measure the size or practical importance of a difference. The posted primary comparison gives an unadjusted p-value of 0.068. Because it is unadjusted, it should not be assumed to account for testing multiple outcomes or contrasts. The registry record does not report a multiplicity adjustment for the posted results.

General: Why are participant counts important for a binary endpoint? The count and denominator show how much information supports each group’s estimated proportion. For the primary outcome, the outcome-specific denominators are 296 and 308, rather than the full enrollment. The registry defines the primary population as participants who completed at least one follow-up assessment for risk awareness. The record does not explain every difference between enrollment and outcome-specific denominators, so the denominator should be read as part of the definition of the posted result, not as evidence about why participants are absent.

General: How do the continuous outcomes differ? Pain interference and analgesic self-efficacy are reported as means and standard deviations. A mean difference compares the average scale values between groups. The standard deviation describes variation among participant scores; it is not the uncertainty of the mean difference. The confidence interval for the mean difference expresses uncertainty in the estimated contrast. Interpretation also depends on the scale and on what magnitude would matter, neither of which is fully established by the numeric summary alone.

General: What does factorial structure imply? A factorial design assigns participants across combinations of intervention components, which can support examination of each component and whether their effects depend on one another. A component’s effect averaged over the other component is not the same question as the effect of a particular combination. The registry describes the four combinations, but the posted summaries do not report a factorial interaction estimate or a complete factorial analysis. Consequently, the four-group disposal counts should not be treated as a definitive test of whether the Nudge changes the education effect.

General: Why might over-dispersion matter? For count outcomes, a model that assumes less variability than the data contain can make uncertainty appear too small. Over-dispersion refers generally to variability beyond what a chosen count model expects. It is not relevant in the same way to a binary count reported simply as participants with an event, and the registry’s primary outcome is explicitly binary. The registry record does not describe a model-based analysis or report an over-dispersion assessment for this endpoint.

The trial record identifies randomized allocation, triple masking, and a factorial model, but does not report the detailed statistical analysis plan. Specific information such as the chosen regression model, any covariate adjustment, handling of repeated measures, missing-data assumptions, or planned tests for factorial interactions is not reported in the registry record. The posted comparisons should therefore be interpreted according to the summaries actually reported, without assuming a model or adjustment that is not specified.

11. Confidence Intervals and Precision

Precision concerns how much uncertainty surrounds an estimate, not whether the estimate is favorable or unfavorable. The primary risk difference is 0.031, and its 95% confidence interval extends from -0.002 to 0.065. Since the interval crosses zero, the posted data do not pin down the direction of the difference with high precision. Values near no difference and positive differences within the interval are compatible with the reported uncertainty.

The interval’s endpoints also show that the point estimate should not be read as a precise measure of the size of any difference. The data permit a range of possible contrasts, including one close to zero. The unadjusted p-value of 0.068 is consistent with that uncertainty; it does not replace the interval or tell readers how important a difference would be.

The secondary outcomes also show uncertainty. The disposal-behavior comparisons have broad intervals, and the intervals for pain interference and self-efficacy include zero. These results do not establish equivalence: a confidence interval that includes zero can still include differences in either direction. Whether the range is narrow enough to rule out meaningful effects depends on prespecified clinical or behavioral thresholds, which are not reported in the registry record.

Endpoint denominators are smaller than total enrollment for several summaries, and they differ across outcomes. Smaller analyzed groups generally leave less information for estimating a contrast, although the registry record does not provide enough detail to attribute the observed precision to any particular factor. The estimates and intervals, rather than a binary significance label, are the clearest basis for judging what the posted data can resolve.

12. 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 estimates are illustrative, not a report of the trial’s original design calculation. For the listed non-time-to-event outcomes, the figures are participants per arm, not a combined total. The planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each row considers detecting the stated fraction of the observed effect: 100%, 75%, or 50%.

The 80% power column gives the estimated participants per arm under those assumptions for a design with an 80% chance of detecting an effect of the specified size, if that effect is real and the assumptions hold. The 90% power column uses a higher target chance of detecting the effect and therefore generally requires more participants per arm. These are design-planning quantities, not evidence about the chance that the completed trial found a real effect. This is not observed power.

The rows illustrate how the assumed effect size changes the planning estimate. Planning for 75% or 50% of the observed effect means aiming to detect a smaller contrast than the full observed estimate; smaller effects need more participants to detect under otherwise unchanged assumptions. The displayed values can therefore become much larger when the target effect is reduced. These calculations use the observed effect as a planning reference and do not establish that the observed effect is the true or clinically meaningful effect.

The sample-size estimates do not reproduce the trial’s original enrollment justification. The original design assumptions and sample-size rationale are not reported in the registry record. The registry’s recorded enrollment is 712, while its brief summary describes a proposed recruitment of 840; the record does not explain the difference. The planning calculations should be interpreted separately from those enrollment figures.

13. 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, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.938; treatment proportion p₁ = 0.970; average p̄ = 0.954.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.2964 = 0.5809.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.2956 = 0.2488.
4. n = (0.5809 + 0.2488)² / (0.0313)² = 703.4, rounded up to 704 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
p0 <- 0.938311688311688                          # control proportion
p1 <- 0.969594594594595                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^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 (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(3287622)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 704 (80% power), 942 (90% power)
 75% of observed effect: n per arm = 1,353 (80% power), 1,810 (90% power)
 50% of observed effect: n per arm = 3,269 (80% power), 4,376 (90% power)
power.prop.test: 703.4 
Simulated power at n = 704 per arm: 0.807 (20000 replicates)

The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-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.

14. Multiplicity, Missing Data and Analysis Populations

The registry record lists multiple outcomes, including the primary awareness endpoint and secondary domains covering disposal, pain interference, self-efficacy, analgesic use or adherence, and decision competency. It also describes several intervention combinations within a factorial design. Testing multiple outcomes, groups, and contrasts creates a multiplicity issue: the more comparisons made, the greater the opportunity for chance findings if each is interpreted on its own without adjustment.

The record does not report a multiplicity-control strategy, such as a hierarchy of tests or an adjustment for multiple comparisons. It does not report the full prespecified statistical analysis plan, so it is not possible to determine which secondary comparisons were planned in advance, whether any were exploratory, or how the factorial components and their interaction were intended to be analyzed. The primary comparison is accompanied by an unadjusted p-value; the posted secondary comparisons are also described as unadjusted.

Missing-data handling is another unresolved issue. The primary outcome population is defined as parents who completed at least one follow-up assessment for risk awareness. The outcome-specific denominators vary: the primary groups include 296 and 308 participants, while other outcomes have their own denominators. The registry record does not report reasons for missing assessments, the amount or pattern of missing data by group, or an imputation or sensitivity-analysis approach. It is therefore not possible to assess from the registry record whether the analyzed participants differ systematically from those without an outcome assessment.

The record also does not report a full intention-to-treat analysis definition or explain how participants were handled if they did not complete assigned intervention components. Randomized allocation is recorded, but that alone does not specify the analysis population. These omissions limit assessment of how robust the posted comparisons are to missing outcomes, departures from assigned treatment, or multiple testing.

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.

Most frequent serious adverse event terms

Serious events with the highest arm-level rate: dehydration (0.3%), postoperative hemorrhage (0.3%), deep vein thrombosis (0.3%), adverse drug reaction (0.3%), suspected postoperative infection (0.3%).

The registry reports serious adverse events for 4 participants among 298 at risk in the Education Intervention group and 3 participants among 308 at risk in the Standard of Care group. Other adverse events are reported as 0 in each group, and deaths are reported as 0 in both groups. These are event counts for the recorded groups; they should not be interpreted as proof that no unreported events occurred.

The registry lists Dehydration, Postoperative hemorrhage, Deep vein thrombosis, Adverse Drug Reaction, and Suspected postoperative infection among the leading serious event terms, each at 0.3%. These terms describe the reported events, but the record does not establish that an event was caused by an intervention. Serious adverse-event summaries are not the primary measure of this educational trial, and the counts alone do not provide a detailed comparison of event types, timing, severity, or relatedness.

The at-risk denominators and the primary-outcome denominators are not identical for the education group. The registry record does not explain that difference. Safety counts should therefore be interpreted with their own stated denominators rather than substituted for outcome-specific populations.

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

The primary data describe high recorded awareness of over sedation in both comparison groups, with a point estimate favoring the Education Intervention group. The confidence interval includes zero and extends across a range of possible differences, so the result does not establish a clear direction or precise size of the contrast. The unadjusted p-value is 0.068. These findings should be presented as an uncertain estimate, not as a definitive finding that the groups were different or identical.

The measured endpoint is awareness at Day 3, among parents with at least one follow-up assessment. It does not directly show whether parents changed medication handling, administration, or disposal; whether children experienced fewer adverse events; or whether pain management changed. The secondary summaries add information about selected outcomes, but their uncertainty and the lack of reported multiplicity methods limit the conclusions that can be drawn across them.

A confidence interval including zero does not demonstrate equivalence or rule out every meaningful difference. Demonstrating equivalence would require an appropriate design and prespecified margins, neither of which is reported in the registry record. Likewise, the observed point estimate should not be assumed to represent the effect that would occur in other settings or populations.

The broader purpose of STOMP was to support parents’ risk recognition and medication-management decisions. The posted primary outcome addresses one part of that goal. The registry record does not provide enough detail about missing outcomes, analysis methods, or the operational definition of awareness to resolve all uncertainties around the result. The findings are best understood as estimates from this completed randomized trial, with limits in precision and reporting, rather than as a standalone judgment about the intervention’s overall value.

17. Why This Trial Matters Statistically

This trial illustrates why a statistically informative result requires more than a point estimate. The primary comparison is an absolute difference in a binary knowledge outcome, accompanied by a confidence interval and an unadjusted p-value. Considering these together makes the uncertainty visible: the estimate favors education, but the interval includes no difference and allows a range of possible effects.

The factorial structure also matters to interpretation. Education and Nudge are separate behavioral components, and the trial includes combinations of both. A two-group comparison of education with standard information does not automatically answer whether the Nudge adds benefit, whether either component acts differently in the presence of the other, or which combination is most informative. Those questions require clearly specified contrasts and analyses, which are not reported in the registry record.

The record also demonstrates the importance of distinguishing enrollment from outcome-specific denominators. Enrollment was 712, while the primary outcome uses smaller group denominators defined by follow-up assessment. Different outcomes have their own participant counts. Without details about missingness and analysis populations, readers cannot fully evaluate how those denominators affect interpretation.

Finally, the secondary outcomes and planning illustrations show why multiple endpoints should be handled transparently. Distinct outcomes can broaden a trial’s relevance, but unadjusted comparisons across many domains deserve caution. Planning estimates based on observed effects can illustrate how detectable effect size relates to required enrollment, but they are not a substitute for the original design assumptions or observed evidence. The statistical value of the record lies in reading estimates, uncertainty, design, and reporting limitations together.

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 several trial-specific questions unresolved. Although randomization, triple masking, and a factorial model are recorded, the methods used to generate allocation, maintain masking, and analyze the factorial components are not reported in the registry record. The trial’s original sample-size justification and planned analysis methods are also not reported.

The primary outcome is described as binary awareness of over sedation, but the exact assessment instrument, threshold, and assessment procedure are not reported. The endpoint captures knowledge at Day 3, not subsequent behavior or clinical events. The broader outcomes of opioid handling and administration are part of the trial’s stated purpose, but the registry record does not provide posted numerical results for every listed outcome.

Outcome denominators vary, and the record does not describe the amount, reasons, or pattern of missing data. The primary analysis population requires at least one follow-up assessment, but the handling of participants without such an assessment is not reported. The registry also does not state whether the reported comparisons were adjusted for baseline characteristics or whether repeated assessments were modeled.

The design includes two intervention components, but the posted summaries do not include an interaction analysis. Without that analysis and its prespecified interpretation, the four-arm disposal summaries cannot resolve whether the components operate independently or jointly. Multiple outcomes and contrasts are listed, while multiplicity handling is not reported. These reporting gaps limit the strength of claims that can be made from the posted estimates and should be considered alongside their confidence intervals.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Evaluation of an Interactive Opioid Risk Education Program (STOMP) for Parents — NCT03287622.
• Registry record last updated 2020-11-19; status last verified 2020-10.
• Results first posted 2020-11-19.
• 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

NCT03287622 is a completed randomized, triple-masked, factorial trial sponsored by the University of Michigan, with recorded enrollment of 712. It evaluated scenario-tailored opioid education, with and without a behavioral Nudge, against standard-of-care information. The primary endpoint was parent awareness of over sedation at Day 3 follow-up.

The primary comparison reports 287 of 296 participants aware in the education group and 289 of 308 in the standard-of-care group. The risk difference is 0.031, with a 95% confidence interval from -0.002 to 0.065 and an unadjusted p-value of 0.068. Selected secondary outcomes and serious adverse-event counts are also posted. The registry record does not report the original sample-size rationale, full analysis plan, multiplicity strategy, or detailed missing-data methods.