The Opening Doors to Early Intervention Study: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for The Opening Doors to Early Intervention Study (NCT03625115), a randomized na study. The primary outcome is Evaluation of the Child's Cognitive Functioning (i.e., Sensorimotor Development, Problem Solving Skills).

2. Clinical Question

3. Trial Design

The Opening Doors to Early Intervention Study was a randomized, parallel-group behavioral intervention study sponsored by Children's Hospital of Philadelphia. Its stated aim was to test a patient navigation program intended to improve families’ engagement with early intervention services and help them address barriers to accessing those services. The study concerned early developmental delays and child development in Philadelphia.

Participants were assigned to Family Navigator or usual care. In the intervention group, a designated Family Navigator was to engage and inform parents and assist them in following through with referrals and services. Usual care consisted of information about early intervention and routine Child Find procedures. The registry records single masking, but the identity of the masked people is not reported in the registry record. The study’s phase is recorded as not applicable.

The registry lists enrollment of 357 and records the study as completed. The study started on 2018-09-11, with primary completion on 2023-09-25. These are registry dates and do not by themselves describe the duration of follow-up for each family. The primary outcome was cognitive functioning measured at 12 months.

The primary outcome record says that 223 participants completed the cognitive section of the Bayley-III assessment. The registry explains that some families could not attend in person or that child behavior prevented completion. Thus, the assessment group is not the same as the enrolled group. The registry record does not report the analysis population definition, how missing assessments were handled in the primary comparison, or whether the analysis followed the randomized assignment regardless of intervention participation.

The record lists seven outcome measures and eight analyses, but does not report a complete statistical analysis plan. It also does not report the planned sample-size justification, any interim analyses, or the identity of those masked. The secondary outcome list includes Public Policy Changes. Those details limit what can be concluded about the design and analysis beyond what is explicitly recorded.

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.

Before assignment: We are reporting on participant data from 357 participants, 174 in the control arm and 183 in the intervention arm.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: A total of 223 participants completed the cognitive section of the Bayley III assessment. The reason why this number is not equal to 357 is because some families were unable to make it in person for the assessment or the assessment could not have been completed due to child behavior.

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: We are reporting on participant data from 357 parent/child dyads, 174 in the control arm and 183 in the intervention arm.

6. Primary Endpoint

The registry lists the primary outcome as Evaluation of the Child's Cognitive Functioning (i.e., Sensorimotor Development, Problem Solving Skills), measured over 12 months.

The primary endpoint was the child’s cognitive functioning at 12 months, assessed with the Cognitive domain of the Bayley Scales of Infant and Toddler Development, Third Edition (BSID-III). The registry describes the measure as a validated assessment for children aged 1-42 months. Its Cognitive domain uses developmental play tasks to obtain a developmental quotient and assess the child’s level of cognitive functioning.

The recorded outcome is a composite score derived from a single scaled test score from the Cognitive Scale. The stated scale range is 40 to 160. Higher scores denote stronger skills and abilities in this domain, and the score is scaled to a mean of 100 and a standard deviation of 15. Those scale properties describe how scores are constructed and interpreted; they do not establish the expected score in this particular study population.

Cognitive development is relevant to the study’s stated aim of evaluating whether a navigation program that supports engagement with early intervention is associated with child development outcomes. The endpoint is a measured developmental assessment rather than a direct count of referrals or service use. The registry reports the mean and full range for each randomized group. It does not report a between-group confidence interval or an estimate of the magnitude of the group contrast in the primary outcome entry.

The cognitive assessment was completed by 223 participants. The registry notes that in-person attendance was not possible for some families and that child behavior prevented some assessments from being completed. This matters when interpreting the endpoint because the posted results describe assessed children, while the enrolled group was larger.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does a group mean describe?

A mean is a measure of the central level of scores in a group. For the primary outcome, the registry reports means for usual care and Family Navigator at 12 months. A mean is useful for describing a group, but it does not show how widely individual scores vary or how precisely the group mean has been estimated. The reported full ranges add information about the lowest and highest recorded values, but they do not show the distribution of scores between those endpoints.

The Bayley-III Cognitive domain score is scaled, with higher values indicating stronger skills and abilities. The scale’s stated mean and standard deviation describe its scoring framework. They are not the observed mean and spread in either randomized group. Keeping the scale properties distinct from trial results avoids treating a reference feature of the instrument as a result from this study.

What does the reported t-test address?

A two-sided t-test evaluates evidence about a difference between group means, allowing for a difference in either direction. In general, the test compares the observed separation of means with the variability and amount of information in the data under a specified model. Its p-value is calculated under a null hypothesis and the assumptions of the test. It is not an effect-size estimate, a confidence interval, or a direct measure of clinical importance.

The registry reports a two-sided t-test and p = 0.30. It does not report the test statistic, degrees of freedom, the estimated mean difference, or a confidence interval for that contrast. The p-value alone cannot communicate the range of effect sizes reasonably compatible with the data. Nor can it establish that the effect is negligible.

What is needed to support an equivalence conclusion?

Equivalence testing asks whether the treatment effect is sufficiently close to no difference according to a prespecified margin. The margin defines the largest difference that would still count as practically equivalent. A confidence interval for the effect is then assessed against that margin using the chosen procedure. This differs from simply failing to reject a conventional no-difference hypothesis.

The registry classifies the reported analysis as equivalence, but an equivalence margin and confidence interval are not reported in the registry record. Consequently, the test label and p-value do not reveal whether the required equivalence criterion was met. The registry also does not report enough detail to evaluate the test’s assumptions or reproduce the sponsor’s analysis.

Why does missing assessment matter?

Randomization aims to make comparison groups similar at assignment, on average. Missing outcome assessments can weaken that protection if the availability of an outcome is related to group assignment or to the outcome itself. The registry says 223 participants completed the cognitive assessment and notes inability to attend in person or child behavior as reasons for noncompletion. It does not report how many assessments were missing in each group, whether missingness differed by assignment, or how the primary analysis handled missing values.

In general, an analysis limited to participants with observed outcomes describes those assessed. It may not estimate the same contrast as an analysis that includes all randomized participants under an explicit missing-data approach. Methods such as imputation or sensitivity analyses can examine dependence on assumptions about missing outcomes, but their use in this study is not reported in the registry record. The analysis population and the handling of missing data therefore remain important uncertainties.

How should planning illustrations be read?

Sample-size planning calculations are hypothetical illustrations, not observed results and not evidence of the trial’s achieved power. The registry’s planning assumptions describe a two-sided significance level of 0.05, equal allocation, and a normal approximation, with the effect to detect expressed as a stated fraction of the observed effect. Such calculations depend on their assumptions and on the effect used for planning. They do not substitute for the observed estimate and its uncertainty, and they do not reveal the trial’s original design justification. The original sample-size justification is not reported in the registry record.

Over-dispersion is a general concern when outcome variability exceeds what a statistical model assumes. In general, underestimating variability can make uncertainty appear smaller than it is, while allowing for greater variability can widen uncertainty. The primary outcome is analyzed as a continuous score in the reported t-test; the registry does not report a separate over-dispersion model or diagnostics. This general issue should not be mistaken for evidence that over-dispersion occurred in this trial.

Multiplicity is another general statistical concern when several outcomes or analyses are examined. Repeated testing can increase the chance of at least one apparently noteworthy finding, depending on the analysis strategy. The registry lists seven outcome measures and eight analyses, but a multiplicity adjustment or prespecified hierarchy is not reported in the registry record. The primary endpoint should therefore be distinguished from other outcome measures, and the overall approach to multiple testing cannot be assessed from the reported details.

10. Analyses Reported by the Sponsor

The registry reports the sponsor’s primary comparison as a two-sided t-test with p = 0.30 and classifies it as an equivalence analysis. This is the sponsor’s reported inferential result. The registry does not report a recalculated between-group estimate or confidence interval, so there is no recalculated contrast to quantify alongside the sponsor’s p-value in this account. The arm-level means and ranges are descriptive summaries and do not, by themselves, reproduce the inferential test.

A recalculation from posted summary statistics, when available, is generally an unadjusted analysis and may not reproduce the sponsor’s model, analysis population, or handling of missing outcomes. It should not automatically replace the trial’s own analysis. In this record, there is no indicated discrepancy between the posted figures and a sponsor result. The more important interpretive limitation is that the registry does not report the effect estimate, confidence interval, equivalence margin, or sufficient analysis details to evaluate the equivalence claim. The reported p-value should therefore be interpreted as the sponsor’s test result, not as proof of equivalence.

11. Multiplicity, Missing Data and Analysis Populations

The registry lists seven outcome measures and eight analyses, with Public Policy Changes among the listed secondary outcomes. A list of outcomes and analyses does not show which comparisons were designated primary in the analysis plan, whether other outcomes were exploratory, or how conclusions were prioritized. The primary outcome is identified as cognitive functioning at 12 months. The registry record does not report a multiplicity adjustment, testing hierarchy, or other procedure for controlling the interpretation of multiple analyses.

Missing primary outcome information is directly relevant. The registry reports that 223 participants completed the cognitive section of the Bayley-III, compared with enrollment of 357. It attributes incomplete assessment to some families being unable to attend in person or to child behavior preventing completion. The registry does not report the number assessed in each randomized group as a proportion of that group, whether these reasons differed between groups, or whether other reasons contributed.

The record also does not report the primary analysis population, whether all randomized participants were analyzed according to assigned group, or the method used for missing cognitive scores. It does not describe imputation, weighting, a complete-case analysis, or sensitivity analyses; these approaches should not be assumed. Without those details, it is not possible to determine how the posted comparison relates to outcomes among participants whose assessments were unavailable or whether the analysis depends on assumptions about those missing outcomes.

The registry reports eight analyses but does not report an interim-analysis plan or whether any interim testing affected the primary comparison. It also does not report a full statistical analysis plan. These absences do not demonstrate that such procedures were or were not used; they mean that the registry record does not provide the information needed to assess them. Accordingly, the primary result should be interpreted alongside the incomplete outcome ascertainment and the unreported approach to multiplicity.

12. 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 record reports zero serious adverse events in the usual-care group and zero in the Family Navigator group. It also reports zero other adverse events and zero deaths in each group. The registry lists 174 participants at risk for serious and other adverse events in usual care and 183 in Family Navigator. No serious adverse-event terms are listed.

These figures describe the events recorded in the registry for the reported groups. Zero recorded events is not proof that no event could occur, and does not establish that the groups had identical safety profiles. The figures also do not indicate the length or completeness of adverse-event monitoring, the criteria used to collect events, or whether events were assessed as related to the intervention. Those details are not reported in the registry record.

The at-risk counts for adverse events are not the same measure as completion of the cognitive assessment. Safety counts and developmental outcome assessments have different roles and denominators, so the adverse-event figures should not be used to infer how many participants contributed to the primary outcome. They are best read narrowly as the registry’s reported event counts, without broader conclusions about risk or causation.

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

The result describes a randomized comparison of a Family Navigator program with usual care, using a child cognitive score at 12 months as the primary outcome. The posted means are 83.5 for usual care and 81.94 for Family Navigator. The sponsor reports a two-sided t-test with p = 0.30, classified as an equivalence analysis. These registry entries convey the observed group summaries and the reported test result, but they do not provide a complete account of the size or precision of the group contrast.

A non-small p-value is not evidence that two groups are identical. It can arise when an effect is small, when estimates are imprecise, or under other combinations of data and model assumptions. To assess the range of plausible effects, readers need an effect estimate and confidence interval. To establish equivalence, readers also need a prespecified margin and evidence that the uncertainty interval meets the equivalence criterion. Those elements are not reported in the registry record.

The endpoint was not completed by everyone enrolled. The registry reports 223 completed cognitive assessments and explains that some families could not attend in person or that child behavior prevented completion. If the assessed participants differ from those without scores in outcome-relevant ways, the group summaries may not represent the full randomized groups. The registry does not report an analysis that resolves this concern.

The findings therefore do not establish that the intervention improved cognitive scores, that it had no effect, or that the groups were equivalent. Nor do they establish whether the program changed referral completion, service access, or other outcomes beyond the reported measures. Those are distinct questions, and the record’s stated primary outcome is cognitive functioning. The result should be interpreted as a limited report of observed scores and a sponsor test, with important precision, equivalence, and missing-data details absent.

14. Why This Trial Matters Statistically

This trial addresses a statistical challenge common in intervention studies that work through families and service systems: the intended pathway may involve engagement and access, while the primary outcome is a child developmental score. The registry describes a Family Navigator role designed to support parents through early intervention referrals and services, and identifies cognitive functioning at 12 months as the primary endpoint. The distinction between the intervention’s intended pathway and the measured endpoint matters when interpreting what the result can answer.

The study also illustrates why a p-value should not be treated as a complete result. The registry reports a p-value but does not report a confidence interval for the group contrast or the margin required to interpret an equivalence analysis. Without these, readers cannot readily judge the magnitude or precision of the contrast or verify an equivalence conclusion. Reporting estimates and uncertainty alongside a test result is important for understanding what the data allow.

Assessment completion is another central statistical issue. The registry notes that the cognitive assessment was completed by 223 participants and gives practical reasons for noncompletion. In family-centered research, incomplete assessments can affect interpretation if completion is related to participant characteristics, intervention exposure, or developmental outcomes. The record does not report enough detail to determine whether this occurred or how the analysis addressed it.

Finally, the listed outcomes and analyses make clear why a prespecified analysis strategy is valuable. The registry does not report how multiplicity was handled or provide a complete analysis plan. These limitations do not invalidate the posted results, but they narrow the claims that can be supported from the registry record and identify the information that would make the findings easier to evaluate.

15. 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 primary result is incompletely reported for assessing an equivalence claim. Although the registry labels the sponsor’s test as an equivalence analysis, it does not report the equivalence margin or a confidence interval for the between-group effect. The p-value alone cannot establish that the groups fall within an acceptable equivalence range.

There is also a notable difference between the number enrolled and the number reported as completing the cognitive assessment: enrollment was 357, while 223 participants completed that assessment. The registry attributes noncompletion to inability to attend in person or child behavior, but does not break down missing assessments by randomized group or explain how missing outcome data entered the analysis. Selection into the assessed group could affect interpretation if assessment availability was related to cognitive outcome or treatment assignment.

The registry reports group means and full ranges but not a between-group effect estimate with uncertainty. It does not provide the test statistic, degrees of freedom, or detailed assumptions for the t-test. The identity of those masked is not reported, and the record does not include the full statistical analysis plan, sample-size justification, interim-analysis details, or multiplicity approach. These omissions prevent a fuller assessment of the analysis decisions and precision.

The record lists one secondary outcome, Public Policy Changes, as well as multiple outcome measures and analyses, but does not explain their hierarchy or how they were analyzed. The adverse-event record gives event counts but not monitoring duration, collection procedures, or attribution. These limitations are specific to the information recorded for this study; they should not be taken as evidence that unreported procedures were absent.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: The Opening Doors to Early Intervention Study — NCT03625115.
• Registry record last updated 2025-02-10; status last verified 2025-02.
• Results first posted 2025-02-10.
• 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.

19. Record Summary

The Opening Doors to Early Intervention Study was a completed, randomized, parallel-group behavioral study sponsored by Children's Hospital of Philadelphia. It compared a Family Navigator program with usual care consisting of early intervention information and routine Child Find procedures. The study enrolled 357 participants and recorded primary completion on 2023-09-25.

The primary outcome was cognitive functioning on the Bayley-III Cognitive domain at 12 months. The registry reports means of 83.5 for usual care and 81.94 for Family Navigator, and a sponsor-reported two-sided t-test with p = 0.30, classified as an equivalence analysis. The cognitive assessment was completed by 223 participants. The registry does not report the equivalence margin, a confidence interval for the group contrast, or the primary missing-data analysis.

The adverse-event record reports zero serious events, other events, and deaths in both groups. The results are best interpreted as group summaries and a reported test, with limits on judging precision, equivalence, and the effect of incomplete assessment.