Effectiveness of an Online Parenting Training: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Effectiveness of an Online Parenting Training (NCT05111886), a randomized na study. The primary outcome is Aim 3: Change in Behavioral Assessment System Child Score.

2. Clinical Question

3. Trial Design

The study, titled “Effectiveness of an Online Parenting Training,” is registered as NCT05111886. The registry describes a randomized, parallel-group design with no masking. It lists an overall enrollment of 94 and identifies two Federally Qualified Health Center primary care clinics as the setting for the personnel component. The study status is completed, with a start date of 2022-02-21 and a primary completion date of 2024-06-01.

The record includes groups for primary care personnel training, parents receiving eHealth GenPMTO, parents in a control group, and community therapists. For primary care personnel, the listed comparison is communication-skills training against a control condition in which personnel receive a written description of the referral process but no training. The parent outcome comparison is eHealth GenPMTO against Parents Control. The registry lists therapists trained to deliver GenPMTO as another group, but the full design connecting all groups and interventions is not reported in the registry record.

For the primary outcome, the posted results include 23 parents in the eHealth GenPMTO group and 16 in Parents Control. These are the numbers contributing to the reported outcome, not a replacement for the overall enrollment figure. The adverse-event reporting lists different numbers at risk for some groups, so the registry record does not establish that every enrolled participant contributed to every outcome.

The primary outcome is assessed at 8 weeks. The registry lists 10 outcome measures and four secondary outcomes, including readiness to change at 8 weeks and 1 year. The registry record does not report the original sample-size assumptions, allocation ratio, randomization procedure, or detailed follow-up and analysis plans.

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:

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

6. Primary Endpoint

The registry lists the primary outcome as Aim 3: Change in Behavioral Assessment System Child Score, measured over 8 weeks.

The primary outcome is the change in the Externalizing Risk Score, a subscale from the Behavior Assessment System for Children, Third Edition, Parent Report Form—Preschool. It is based on nine items with four response choices. The raw score ranges from 0 to 27; higher scores indicate worse externalizing-behavior functioning. Scores of 0-10 are classified as normal risk, 11-19 as elevated, and 20 or above as extremely elevated.

Parents completed the measure before the intervention window and again after an 8-week interval. Change is defined as the score at 8 weeks minus the baseline score. Thus, a negative change means the measured score was lower at follow-up, while a positive change means it was higher. The outcome is reported as a group mean and standard deviation, with a mean difference comparing the parent groups.

Using a continuous score preserves information across the measure’s range rather than reducing each observation to a category. In general, a difference in mean change describes the average separation between groups on this outcome; it does not describe how every individual child’s score changed. The record does not report whether other score summaries or thresholds were used in the analysis.

7. Results Posted in the Registry

• Parents eHealth GenPMTO: mean -3.17 versus 0.13 on control; difference -3.30 (95% CI -8.58 to 1.98), standardized effect d = -0.41; z-test p = 0.220.

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.

Readiness to Change - Patient Preferences Subscale Score

• 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:
  • Primary Care Personnel Training: mean 17.09 versus 17.25 on control; difference -0.16 (95% CI -1.57 to 1.25), standardized effect d = -0.09; z-test p = 0.824.
  • Therapists: mean 16.23 versus 17.25 on control; difference -1.02 (95% CI -2.48 to 0.44), standardized effect d = -0.55; z-test p = 0.172.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Primary Care Personnel Training 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 Therapists and the control. The interval gives the range of effects that remain compatible with the data.

The registry lists four secondary outcomes, while numerical results are posted for the Readiness to Change—Patient Preferences Subscale Score. The available comparisons involve primary care personnel training versus primary care personnel control, and therapists versus primary care personnel control. These results concern readiness to change in those groups rather than the parent-focused child Externalizing Risk Score.

Across the two posted comparisons, the estimated mean differences are negative, and both confidence intervals include zero. The unadjusted p-values are 0.824 for primary care personnel training and 0.172 for therapists. Thus, the numerical pattern does not supply a precise separation from the personnel control group for either comparison. These findings should be interpreted on their own measure and in their own study groups, not as confirmation or contradiction of the parent outcome.

In general, secondary outcomes can provide information about other dimensions of a study, but they are often examined alongside multiple comparisons. When many outcomes or contrasts are tested, the chance of at least one apparently notable result arising by chance can increase. A prespecified hierarchy or multiplicity adjustment can address that issue, but such plans are not reported in the registry record. The posted secondary p-values are unadjusted, so they carry less evidential weight than a result interpreted under a clearly specified, prespecified analysis plan.

Uncertainty is also relevant: a nonsignificant p-value does not establish that groups are equivalent, and a point estimate alone does not demonstrate a reliable difference. The confidence intervals communicate the range of estimates compatible with each comparison under the analysis method. The record does not report numerical findings for the other listed secondary outcomes, so an overall account of all secondary endpoint results is not possible from the registry record.

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

• Intervention Acceptability Measure
• Appropriateness Measure
• Feasibility Measure
• Readiness to Change - Patient Preferences Subscale Score

9. Statistical Interpretation

10. Statistical Methods Explained

The primary endpoint is continuous, and the registry reports means and standard deviations for change scores in each parent group. A mean summarizes the average change within a group. A standard deviation describes how dispersed individual change scores are around that group mean. In general, the standard deviation is not the uncertainty of the mean itself: it reflects variation among participants, whereas a confidence interval for a group difference reflects uncertainty in estimating the contrast.

What does the mean difference represent?

The comparison is defined as the eHealth GenPMTO group mean minus the Parents Control group mean. The posted group means are -3.17 and 0.13, respectively, and the posted mean difference is -3.3. The negative sign indicates that the estimated average change was lower in the eHealth GenPMTO group under the stated change-score definition. Since lower follow-up scores indicate less externalizing risk on this scale, the sign can be understood in the scale’s direction. It remains a comparison of group averages, not a description of each participant.

In general, a mean difference is easy to interpret in the original measurement units, but it can be influenced by the scale, the timing of measurement, and variation among participants. A standardized effect expresses a difference relative to a measure of variability and can aid comparisons across measures, but it does not replace the original-unit estimate. Standardized effects are not needed to interpret the central posted finding; the original-scale estimate and its interval retain the direct score meaning.

How should the p-value be understood?

The registry reports an unadjusted p-value of 0.22 for the primary comparison. In general, a p-value measures how compatible the observed data are with a null hypothesis under a specified statistical model. It does not measure the size or importance of an effect, and it is not the probability that the null hypothesis is true. A p-value also does not tell readers whether an estimate is precise; that is better assessed by considering the confidence interval and the spread of the observations.

“Unadjusted” indicates that the reported result is not described as adjusted for multiple comparisons. Whether any covariates were included in the primary analysis, and the full model specification, are not reported in the registry record. The posted result therefore should not be read as a substitute for a detailed analysis plan or a complete account of the fitted model.

What does the confidence interval add?

The 95% confidence interval for the mean difference is -8.577 to 1.977. In general, a confidence interval conveys the uncertainty of an estimate under the method used to construct it. A wider interval indicates less precision than a narrower interval on the same scale. Because this interval includes zero and spans values on both sides of zero, it does not identify a single direction of the group difference with high precision. It is not a range that contains 95% of individual participant outcomes.

Confidence intervals depend on the analysis method and its assumptions. The registry record does not report the method used to calculate the primary interval, whether the analysis accounted for clustering or repeated measurements beyond the change-score construction, or whether any missing outcomes were handled by imputation. Those details matter for evaluating the interval’s exact interpretation.

Why does variability matter?

The reported standard deviations, 7.51 and 8.76, indicate appreciable variation in change scores relative to the group averages. In general, when participant outcomes vary widely and the number of observations is limited, a group mean can be estimated less precisely. A few participants with particularly large changes can also influence a mean, depending on the distribution. The registry record does not report distributions, plots of individual observations, or robustness analyses, so it is not possible to assess these features from the posted summaries alone.

For a continuous outcome, standard deviations are appropriate summaries when the aim is to describe spread around a mean. If the data are strongly skewed or contain influential outliers, other summaries or models may also be informative. Such distributional details and any alternative analyses are not reported in the registry record. The posted group means, standard deviations, mean difference, interval, and p-value should therefore be interpreted as the available summary evidence rather than as a complete account of all analytic choices.

11. Confidence Intervals and Precision

The primary comparison’s 95% confidence interval extends from -8.577 to 1.977 points around a mean difference of -3.3 points. It is broad enough to include zero and differences in either direction. The point estimate therefore gives a useful center for the comparison, but the interval shows that the data do not estimate the difference with high precision. The posted unadjusted p-value, 0.22, is consistent with the uncertainty conveyed by the interval; neither number should be interpreted alone.

In general, a confidence interval is a range produced by a statistical procedure that, under its assumptions and repeated use, would cover the target quantity at the stated rate. It is not a statement that there is a 95% probability that this particular interval contains the true effect, and it does not describe the range of individual scores. Here, the interval concerns the mean difference between groups in change scores.

The outcome groups include 23 and 16 parents, and the within-group standard deviations are 7.51 and 8.76. With appreciable variation in participant-level change, relatively small outcome groups can leave substantial uncertainty about the difference in means. The registry record does not report the full analysis method or a confidence interval for each group’s mean change. It also does not report details of missing-data handling, which could affect the interpretation if outcomes were unavailable for some participants.

The interval should be read in the scale’s units and alongside the definition of change: follow-up score minus baseline score. Values below zero favor a more negative mean change in eHealth GenPMTO relative to Parents Control, while values above zero favor a more positive mean difference. The interval does not by itself determine whether any value is clinically important; a threshold for meaningful change is not reported in the registry record.

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 figures are participants per arm for 80% power and participants per arm for 90% power; they are not total event counts. The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, a normal approximation, and an effect to detect set to a stated fraction of the observed effect. For the primary comparison, the row using 100% of the observed effect gives 94 participants per arm for 80% power and 125 participants per arm for 90% power. Planning for 75% of the observed effect gives 166 and 222 participants per arm, respectively; planning for 50% gives 373 and 499.

In general, the 80% column describes a planning target in which the assumed study design would have an 80% chance of detecting the specified effect at the stated significance level, if the assumptions hold. The 90% column uses a higher chance of detection and therefore requires more participants for the same assumed effect. Smaller effects are harder to distinguish from random variation, so planning for a smaller fraction of the observed effect requires more participants per arm. The figures are planning illustrations based on the observed result, not observed power.

These calculations are not the trial’s original design assumptions. The original sample-size justification and the assumptions used when the study was designed are not reported in the registry record. Nor do these planning figures establish that the observed effect is stable or likely to recur: they translate an assumed effect into an illustrative sample-size requirement under the stated statistical assumptions.

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, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = -3.300; pooled standard deviation σ = 8.040.
2. n = 2 × (1.96 + 0.842)² × 8.040² / -3.300² = 93.2, rounded up to 94 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 <- -3.3                      # observed difference in means
sigma <- 8.04021345689481                     # 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(5111886)
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 = 94 (80% power), 125 (90% power)
 75% of observed effect: n per arm = 166 (80% power), 222 (90% power)
 50% of observed effect: n per arm = 373 (80% power), 499 (90% power)
power.t.test: 94.2 
Simulated power at n = 94 per arm: 0.801 (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.

14. Multiplicity, Missing Data and Analysis Populations

The record lists 10 outcome measures and four secondary outcomes, but it does not report a detailed statistical analysis plan, a hierarchy for interpreting outcomes, or a correction for multiple comparisons. It also does not report whether the primary outcome was designated as the sole confirmatory test or how the different study groups and endpoints were intended to be analyzed together. These omissions make it difficult to assess the extent to which the posted comparisons were selected in advance.

In general, testing multiple outcomes or contrasts increases the opportunity for chance findings if each is interpreted using an unadjusted threshold. Multiplicity procedures can control error rates across a defined family of tests, but the appropriate approach depends on the study’s objectives and prespecified testing structure. Since those details are not reported in the registry record, the secondary comparisons should be viewed as exploratory rather than as a set of independently definitive tests. The primary comparison is also best interpreted with the stated unadjusted result and its interval, without assuming an unreported adjustment.

The record does not report whether the primary analysis used an intention-to-treat population, a per-protocol population, or another analysis population. It does not give participant flow by outcome, reasons for missing measurements, or the method used to handle missing data. Outcome counts differ from the adverse-event counts for some groups; these figures refer to different reporting contexts and do not, by themselves, explain missing outcome observations.

In general, missingness can affect a comparison when the availability of measurements is related to participant characteristics or outcomes. Complete-case analyses, imputation, and model-based approaches make different assumptions. Without the analysis population, missingness information, and handling method, the degree to which missing data may influence the estimates cannot be assessed. These methods and the original sample-size justification are not reported in the registry record.

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 reports zero serious adverse events, zero other adverse events, and zero deaths in each listed group. The numbers at risk are 21 for primary care personnel training, 14 for its control, 23 for parents eHealth GenPMTO, 20 for Parents Control, and 16 for therapists. These are the group-specific figures in the safety record; they are not the same as the primary endpoint counts for every group.

In general, a zero count means no events of the specified type were recorded among the listed participants during the recorded safety reporting period. It does not establish that an event is impossible or that no events occurred outside the recorded scope. The registry record does not provide further detail on how adverse events were collected, the duration of safety follow-up, or definitions used for non-serious events. The figures should therefore be read as registry-reported counts, not as a comprehensive evaluation of safety.

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

The primary result estimates a difference in mean change in children’s Externalizing Risk Scores between the parent groups. The observed mean change was -3.17 in the eHealth GenPMTO group and 0.13 in Parents Control, producing a mean difference of -3.3. The 95% confidence interval ranges from -8.577 to 1.977, and the unadjusted p-value is 0.22. Together, these figures describe an estimate with substantial uncertainty that includes values on both sides of zero.

The result does not establish that the intervention caused a change, that the groups were equivalent, or that the true difference is exactly the point estimate. Nor does it show that every child’s score moved in the same direction. The endpoint is a parent-reported subscale score measured over an 8-week interval, and the registry record does not report a threshold for a clinically important difference.

The study’s randomized designation is relevant to its design, but the registry record does not report the randomization procedure, the analysis population, the handling of missing outcome data, or the complete statistical model. Those details are needed to judge how closely the reported comparison reflects the intended randomized contrast and which assumptions support the inferential results.

The posted readiness-to-change results concern other groups and another outcome; they do not directly answer the primary parent-focused question. Likewise, the zero adverse-event counts are limited to the registry’s stated categories and reporting groups. Neither should be used to broaden the conclusion about the primary endpoint.

In general, an estimate can be compatible with a range of effects while remaining informative about the direction and uncertainty of the observed sample contrast. The most faithful interpretation is therefore neither a claim of benefit nor a claim of no effect: the posted data give a negative point estimate, but the interval is wide and includes zero. The broader relevance of this result depends on features such as participant selection, intervention delivery, outcome availability, and the completeness of reporting, some of which are not described in the registry record.

17. Why This Trial Matters Statistically

This study raises statistical questions that are common in behavioral and implementation research: how to distinguish the effects of a parent-focused program from variation in measured behavior, how to interpret outcomes from several participant groups, and how to assess precision when outcome counts are limited. The primary endpoint is a continuous parent-reported score, so the group comparison concerns average change rather than a simple count of participants who improved or worsened.

The design also spans parents, primary care personnel, and therapists. These groups have different roles and outcomes, so their estimates should not be collapsed into one overall treatment effect. The parent comparison addresses change in child externalizing-risk scores, while the posted readiness-to-change comparisons address a separate construct among personnel and therapists. Keeping those questions distinct is important for avoiding an overbroad reading of the results.

The confidence interval makes uncertainty visible in the original score units. Its inclusion of zero and its span across negative and positive values show why the point estimate alone is not an adequate summary. The planning illustrations also show how assumed effect size influences the participants-per-arm requirements, while emphasizing that planning calculations based on an observed effect are not equivalent to a prospective sample-size justification.

Finally, the registry record illustrates why transparent reporting matters. Information about the analysis population, missing-data handling, multiplicity, and original design assumptions helps readers judge the reliability and scope of estimates. Those details are not reported in the registry record, so interpretation should remain anchored to the posted outcome summaries and their stated uncertainty.

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 parent outcome groups contributing to the primary comparison include 23 and 16 participants. The registry does not report why these are the available outcome counts, how many participants were initially assigned to each parent group, or whether missing measurements were handled in any particular way. Consequently, it is not possible to assess potential attrition effects from the posted summaries alone.

The registry identifies a randomized, parallel design but does not report the randomization procedure, allocation concealment, analysis population, or detailed statistical model. It also does not report whether the primary analysis accounted for the clinic setting or other grouping features. These gaps limit assessment of the assumptions behind the estimated difference and its confidence interval.

The full description of the Parents Control condition is not reported in the registry record. Details of the parent intervention’s delivery, adherence, and exposure are also limited. Without these details, readers cannot determine from the registry alone how the contrast was implemented or how closely participants followed the intended procedures.

The primary outcome is a parent-reported measure assessed at the 8-week point. The registry does not report additional outcome timing for this endpoint, assessor masking, or a clinically meaningful threshold for interpreting score changes. The relatively broad confidence interval further limits precision about the size and direction of the group difference.

The record lists multiple outcomes, but does not provide a complete multiplicity plan or numerical results for every listed secondary measure. The original sample-size justification is also not reported. These limitations do not invalidate the posted estimates, but they restrict the strength and breadth of conclusions that can be drawn from this record.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Effectiveness of an Online Parenting Training — NCT05111886.
• Registry record last updated 2026-02-04; status last verified 2026-01.
• Results first posted 2026-02-04.
• 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

NCT05111886 is a completed randomized, parallel-group study titled “Effectiveness of an Online Parenting Training.” The primary parent-focused outcome is the change in children’s Externalizing Risk Score from baseline to 8 weeks. The posted comparison of eHealth GenPMTO with Parents Control estimates a mean difference of -3.3, with a 95% confidence interval from -8.577 to 1.977 and an unadjusted p-value of 0.22.

The registry also posts readiness-to-change results for primary care personnel training and therapists compared with primary care personnel control. It reports zero serious adverse events, other adverse events, and deaths in each listed group. Details of the original sample-size justification, missing-data methods, analysis populations, and multiplicity plan are not reported in the registry record.