The Impact of an Adapted Version of the Strengthening Families Program on IPV Among Caregivers and ACEs Among Children: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for The Impact of an Adapted Version of the Strengthening Families Program on IPV Among Caregivers and ACEs Among Children (NCT05129501), a randomized na study. The primary outcome is Adverse Childhood Experiences-Child Reported.

2. Clinical Question

3. Trial Design

The record describes a randomized, parallel-group study with no masking. Randomization was at the family level, and children were assigned to the same arm as their caregiver. The study compares Tiwahe Wicaghwicayapi with a wait-list control. The registry lists University of Nebraska Lincoln as the sponsor, describes the study as completed, and lists phase as not applicable.

The treatment description includes baseline assessment, program participation over 7 weeks with fidelity checking, a survey immediately after the program, and a later survey six months after the post-program survey. The wait-list group had access to resources while the treatment group completed the program and completed surveys on the described schedule. The primary outcome summary is child-reported, so it does not represent a caregiver-reported measure.

The registry lists enrollment as 318. That figure is the study enrollment entry; the primary outcome arm summaries report 107 in treatment and 87 in control. The record does not explain the relationship between the overall enrollment entry and the number included in these outcome summaries, so they should not be treated as interchangeable. It also does not report detailed eligibility criteria, the trial's original sample-size justification, or the full analysis plan. The design description therefore establishes the broad randomized comparison and assessment sequence, but does not resolve how all enrolled families contributed to each posted result.

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: This outcome measure is child-reported only.

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: Number of participants, including both caregivers and children (all measures in this chart include both children and caregivers).

6. Primary Endpoint

The registry lists the primary outcome as Adverse Childhood Experiences-Child Reported, measured over Past 6 months.

The primary endpoint is the child-reported mean number of adverse childhood experiences during the past 6 months. The measure is identified as the Comprehensive ACEs Measure, and the registry states that higher scores indicate higher adverse childhood experiences. The record also explicitly says the measure was collected for children only, not caregivers. This matters because randomization occurred at the family level, while the endpoint represents children's reports.

A mean is a summary of the average score in an arm. It can help describe the central level of the measured experiences across children with recorded outcome data, but it does not show the full range or distribution of individual scores. The registry also reports a standard deviation for each arm, which describes variability around the mean. A mean difference places the two arm averages on the same scale and indicates the direction and size of their unadjusted separation.

The endpoint is used because the study's stated purpose is to assess an adapted program intended to prevent adverse childhood experiences among children, including experiences related to witnessing intimate partner violence. However, the posted primary measure is a child-reported ACE score covering the past 6 months; the registry's primary outcome summary should not be read as a direct measure of every aspect of family experience or program delivery.

7. Results Posted in the Registry

• Treatment: Tiwahe Wicaghwicayapi: mean 2.48 versus 3.80 on control; difference -1.32 (95% CI -2.25 to -0.39), standardized effect d = -0.41; z-test p = 0.006.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous: it is summarized as a mean number of adverse experiences. The registry reports the mean and standard deviation for each arm, along with the number contributing to each arm summary. A standard deviation describes how spread out individual observations are around the arm mean. It is not the uncertainty in the estimated mean difference; uncertainty in a comparison also depends on the amount of information in each arm and the assumptions used for the calculation.

What does the mean difference express?

The mean difference is calculated as the treatment mean minus the wait-list control mean. With this direction convention, a negative value means the treatment-arm mean is lower. The reported arm means are 2.48 and 3.8, and the recalculated difference is -1.32. This is expressed in the scale's units: mean number of adverse experiences. It is not a percentage reduction or a standardized score. The measure's stated direction is important for interpretation because higher values indicate more adverse experiences.

What does the confidence interval add?

A confidence interval gives a range of values reasonably compatible with the estimate under the statistical model and its assumptions. For the mean difference, the reported 95% interval extends from -2.253 to -0.387. Its width reflects uncertainty in the comparison; it is not a range containing 95% of individual children's scores, and it is not a guarantee that the true effect lies in this particular interval. The interval is tied to the recalculated unadjusted comparison rather than an adjusted analysis reported by the trial.

What does the p-value test?

The unadjusted p-value is 0.006. In general, a p-value describes how unusual data at least as incompatible with a null hypothesis of no mean difference would be under that hypothesis and the calculation's assumptions. It is not the probability that the null hypothesis is true, the probability that chance alone caused the observed result, or a measure of practical importance. It also does not account for any multiplicity unless a procedure for doing so is specified. No multiplicity procedure is reported in the registry record.

Why does allocation matter to the calculation?

Randomization at the family level means children were assigned with their caregiver, rather than randomized independently within families. General statistical reasoning says observations that share a family may be correlated. When outcomes are correlated within clusters, treating every observation as independent can make uncertainty estimates too small; this is one reason cluster-aware analysis can matter. The registry describes family-level allocation but does not report whether the posted comparison accounts for family clustering. The recalculation uses arm-level summary statistics, and its interval and p-value should be understood in that context.

Why can dispersion affect inference?

The treatment standard deviation is 2.94 and the control standard deviation is 3.56. In general, more variability makes a mean less precisely estimated if other features are held constant. The pooled standard deviation used for the standardized effect calculation is 3.232. The standardized effect, reported as -0.408, expresses the mean difference relative to that pooled variability. It can support comparisons across scales, but it is not the same as the original-scale difference of -1.32 and may be less immediately interpretable in terms of adverse experiences.

The mean-difference calculation is explicitly a recalculation from posted summary statistics, not an adjusted model. The record does not report an analysis specification, covariate adjustment, handling of missing outcomes, or an analysis population definition. It also does not explain whether the family-level design was accounted for in an inferential analysis. Those absences limit what can be concluded about the exact statistical procedure behind the posted comparison. The distinction between an arm summary and a trial analysis is important: summary data allow a straightforward comparison, but do not reveal every design and analysis detail that can affect precision or interpretation.

10. Confidence Intervals and Precision

The 95% confidence interval for the unadjusted mean difference runs from -2.253 to -0.387. It is centered around the estimated difference of -1.32, with uncertainty extending toward both more negative and less negative values. Since zero is outside this interval, the reported unadjusted comparison is inconsistent with an exactly zero difference under the calculation's assumptions at the conventional 95% interval level. That statement is about the calculation, not a guarantee about the underlying effect or an adjusted trial analysis.

The interval conveys precision in a way the point estimate alone cannot. The estimate -1.32 is one value, while the interval shows that the data are compatible with a range of possible differences. The interval does not show where individual child scores fall, and it should not be mistaken for a prediction interval. The arm standard deviations, 2.94 for treatment and 3.56 for control, indicate substantial spread in scores relative to the reported means, though individual observations are not available in the registry record.

Precision depends on the amount and structure of the data as well as variability and analytic assumptions. The primary outcome summaries list 107 treatment observations and 87 control observations. Since assignment was at the family level, children in the same family could share characteristics; general statistical methods account for such dependence when appropriate. The record does not report whether this interval accounts for family clustering, missing outcome data, or any other adjustment. The displayed interval is therefore best read as the uncertainty from the unadjusted recalculation, not as a complete description of every uncertainty in the trial.

The unadjusted p-value of 0.006 complements but does not replace the interval. Neither statistic addresses the clinical or practical importance of the score difference by itself. The registry does not report a threshold for a meaningful change on this measure, so the interval cannot be classified against such a threshold using the record alone.

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 sample-size figures are planning illustrations based on the observed effect, not the trial's original design assumptions. They report participants per arm for 80% power and participants per arm for 90% power. These are not total events: the outcome is continuous, and the figures refer to participants in each of the two arms.

The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between arms, and a normal approximation. The effect to detect is set as a stated fraction of the observed effect. Planning for 100% of the observed effect gives 95 participants per arm for 80% power and 127 for 90% power. Planning for 75% of the observed effect gives 168 participants per arm for 80% power and 225 for 90% power. Planning for 50% of the observed effect gives 377 participants per arm for 80% power and 505 for 90% power.

In plain terms, 80% power describes a planning target in which a study using these assumptions would have an 80% chance of detecting an effect of the specified size at the chosen significance level, if that effect were the true one and the assumptions held. The 90% column uses a higher probability target and therefore calls for more participants under these assumptions. The listed figures are not observed power: they are illustrations for future planning based on the recalculated observed effect.

Smaller effects are harder to distinguish from random variation, so the planning illustration requires more participants as the assumed effect becomes smaller. These figures do not establish what sample size this trial planned or justified. The trial's own sample-size rationale and original design assumptions are not reported in the registry record.

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 = -1.320; pooled standard deviation σ = 3.232.
2. n = 2 × (1.96 + 0.842)² × 3.232² / -1.320² = 94.1, rounded up to 95 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 <- -1.32                      # observed difference in means
sigma <- 3.23244553962888                     # 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(5129501)
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 = 95 (80% power), 127 (90% power)
 75% of observed effect: n per arm = 168 (80% power), 225 (90% power)
 50% of observed effect: n per arm = 377 (80% power), 505 (90% power)
power.t.test: 95.1 
Simulated power at n = 95 per arm: 0.802 (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. Multiplicity, Missing Data and Analysis Populations

The record lists two outcome measures but posts no secondary outcome results. The primary outcome is the child-reported ACE measure described in the registry. It does not report a multiplicity adjustment or a plan for interpreting several outcomes together. In general, examining multiple outcomes or repeated analyses can increase the chance of at least one apparently unusual result under a collection of null hypotheses. Whether that concern applies, and how it should be handled, depends on the prespecified analysis plan; that plan is not reported in the registry record.

The outcome description identifies assessments at baseline, immediately after the program, and six months after the post-program survey. However, the posted primary summary does not specify which assessment time is represented by the values, beyond the measure's timeframe of the past 6 months. It also does not explain whether comparisons across all assessment occasions were planned, whether the reported comparison was selected from a larger set, or whether repeated observations were modeled. These details should not be inferred from the schedule alone.

Missing-data handling is not reported in the registry record. The outcome summary lists 107 treatment and 87 control observations, while overall enrollment is listed as 318. The record does not explain whether the difference reflects eligibility for the child-only outcome, missing surveys, exclusions, or another reason. No assumptions about the missingness mechanism, imputation, or sensitivity analyses are stated.

The analysis population is also not reported. The registry does not specify whether the comparison follows an intention-to-treat principle, includes only participants with observed outcomes, or uses another population definition. This matters because randomization was at the family level and children were assigned with caregivers. No cluster-adjusted model, covariate-adjustment plan, or other detailed statistical model is described. The unadjusted recalculation should therefore be kept distinct from any unreported sponsor analysis or trial analysis plan.

14. 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 adverse-event entries report zero serious adverse events and zero deaths in each arm. The registry lists 174 at risk in the treatment arm and 144 at risk in the wait-list control arm for the serious-event summaries; it lists the same at-risk counts for other adverse events, with zero affected in both arms. No serious adverse-event terms are listed.

These entries describe what is recorded in the registry, not proof that no adverse events occurred outside the recorded information. The figures do not provide event narratives, severity details beyond the serious-event category, timing, causal attribution, or a fuller account of safety monitoring. The record also does not explain why the at-risk counts for safety differ from the outcome-summary counts. They should not be substituted for the numbers contributing to the primary outcome.

Zero recorded events in both arms does not support a comparative estimate of relative safety from these entries. With no recorded affected participants, the registry gives no event contrast to interpret. The entries should be read narrowly as the posted serious and other adverse-event counts, rather than as a complete assessment of possible harms or as evidence about effectiveness.

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

The primary outcome summary shows a lower mean child-reported ACE score in the treatment arm than in the wait-list control arm: 2.48 compared with 3.8. The unadjusted recalculated mean difference is -1.32, with a 95% confidence interval from -2.253 to -0.387 and an unadjusted p-value of 0.006. Since higher scores mean more adverse experiences, the direction of the reported difference favors a lower average score in the treatment arm on this measure and timeframe.

This result does not, by itself, establish that the program caused the observed difference. Randomized allocation is a design feature relevant to causal inference, but the registry record does not report key analysis details such as how missing data were handled, whether family-level dependence was accounted for, or which analysis population was used. Nor does the posted result establish whether the difference is important in practical terms: no threshold for meaningful change is reported.

The measure is child-reported and covers the past 6 months. It should not be interpreted as a direct finding about caregiver IPV, every type of ACE, or outcomes beyond the reported measure and timeframe. The record lists two outcomes but does not post secondary results, so this result does not represent the full set of outcomes the study may have considered. The outcome summary also includes fewer observations than the overall enrollment entry, and the registry does not explain why.

The appropriate conclusion is limited: the posted arm averages differ in the stated direction, and the unadjusted recalculation indicates uncertainty that does not include zero under its assumptions. Further claims about durability, mechanisms, subgroup effects, or generalizability are not established by these figures. The record reports the program assessment schedule, including a later survey, but the primary result itself does not identify a follow-up time point beyond its stated measure timeframe.

16. Why This Trial Matters Statistically

This study raises statistical issues that are especially relevant when family programs are evaluated through child outcomes. Randomization was conducted at the family level, and children were assigned with caregivers. That design can create dependence among observations from the same family. In general, analyses that account for the allocation unit are important because the effective information in clustered data may differ from what a calculation treating every child as independent implies. The registry does not state whether its unadjusted comparison accounts for this structure.

The distinction between enrollment and endpoint participation also matters. The registry lists enrollment as 318, while the primary outcome summaries list 107 treatment observations and 87 control observations. Without a participant flow or missing-data account, readers cannot determine why those counts differ or how representative the outcome summaries are of all enrolled families. This limits assessment of possible attrition or selection effects.

The outcome itself is child-reported and focuses on adverse experiences over the past 6 months. That is a distinct construct from caregiver IPV and from other possible family outcomes. Statistical interpretation depends on keeping the endpoint's respondent, definition, and timeframe in view rather than treating one score as a proxy for every intended effect.

Finally, planning illustrations based on an observed effect are useful for understanding how assumptions about effect size and power relate to sample size, but they do not reveal the original trial's design rationale. The record does not report that rationale. These distinctions—family-level allocation, outcome-specific participation, the scope of the measure, and the boundary between observed results and planning calculations—help prevent overinterpretation of a concise registry result.

17. 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. It does not report detailed eligibility criteria, the number of families contributing to the child-only endpoint, or a participant flow explaining the difference between the overall enrollment entry and the arm counts for the primary outcome. It is therefore not possible to determine from the record alone why the outcome summaries include 107 treatment observations and 87 control observations.

The primary outcome description specifies child reports and a past-6-month timeframe, but the posted comparison does not identify the survey occasion represented by the arm means. The study description includes baseline, immediate post-program, and later surveys; the registry does not clarify how the primary comparison relates to those occasions. No results for the later assessments or secondary outcomes are posted.

The record does not report the statistical analysis plan, the analysis population, missing-data procedures, covariate adjustments, or whether clustering by family was incorporated into inference. The recalculated difference and interval are unadjusted and based on summary statistics. The registry also does not report a threshold for a meaningful change in the ACE measure or the trial's original sample-size justification.

The safety entries list no recorded adverse events, but provide limited detail about ascertainment, timing, or attribution. The intervention descriptions are also incomplete at the end of their text, and do not fully characterize program content or control resources. These gaps constrain assessment of implementation and safety context. They do not negate the posted summary, but they limit how far it can be generalized or used to support broader conclusions.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: The Impact of an Adapted Version of the Strengthening Families Program on IPV Among Caregivers and ACEs Among Children — NCT05129501.
• Registry record last updated 2025-02-05; status last verified 2025-02.
• Results first posted 2025-02-05.
• 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.

21. Record Summary

The registry record describes a completed, randomized, parallel-group study with no masking, sponsored by University of Nebraska Lincoln. The intervention was Tiwahe Wicaghwicayapi, compared with a wait-list control. Randomization was at the family level, and children were assigned to the same arm as their caregiver.

The primary endpoint was child-reported adverse childhood experiences over the past 6 months. The treatment mean was 2.48 and the wait-list control mean was 3.8. The unadjusted recalculated mean difference was -1.32, with a 95% confidence interval from -2.253 to -0.387 and an unadjusted p-value of 0.006. The registry does not report secondary outcome results or detailed analysis and missing-data methods.