NOURISH: Nourishing Our Understanding of Role Modeling to Improve Support and Health: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for NOURISH: Nourishing Our Understanding of Role Modeling to Improve Support and Health (NCT00628030), a randomized na study. The primary outcome is Child BMI.

2. Clinical Question

This framing separates the intervention’s intended behavior-change approach from the measured endpoint. The outcome is a child growth measure; it is not a direct measure of parents’ modeling behavior. The record also names child feeding, child quality of life, parental BMI, and parental dietary intake of fat as secondary outcome domains. It does not report numerical results for those domains in the registry record for the registry record.

3. Trial Design

NOURISH was a randomized, parallel-group trial listed as completed. The registry record gives an enrollment of 184 and lists the phase as NA. It identifies Virginia Commonwealth University as the sponsor. The listed study dates are 2008-04 for study start and 2010-04 for primary completion.

The trial had a NOURISH behavioral intervention arm and a Wellness Group comparator. The registry description says the first 2 waves and second 2 waves of NOURISH participants received face-to-face interventions lasting 12 and 6 weeks, respectively. The interventions differed in duration but covered the same concepts. The record does not explain how the different durations were handled in the primary outcome analysis or whether duration-specific results were evaluated.

The Wellness Group session addressed diet and exercise in pediatric overweight. An independent interventionist moderated it and was blinded to the study’s specific aims and hypotheses. The trial’s masking field is NONE. That does not mean that all staff or participants necessarily knew every study detail; it means the registry does not list masking for the trial. The record does not report further information about allocation concealment, the randomization procedure, or who knew participants’ assignments.

The registry does not report a detailed statistical analysis plan, the planned sample-size justification, or the analysis populations. It also does not provide enough information to establish how missing measurements, withdrawals, or the different NOURISH durations were treated analytically. These gaps limit assessment of how the randomized design translated into the reported outcome analysis.

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.

Baseline to Post-Assessment

Reasons for not completing this period:

Post to 6 Month Follow-up

Reasons for not completing this period:

5. Baseline Characteristics

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

Population: Families completed baseline, post, and six-month follow-up assessments. Although baseline and outcome data for parents and children were collected, only parents participated in the intervention: NOURISH (n = 92; 44 parents/caregivers, 48 children). Wellness Group (n = 92; 47 parents/caregivers, 45 children).

6. Primary Endpoint

The registry lists the primary outcome as Child BMI, measured over Basline, Posttest.

The primary endpoint is child BMI percentile. The registry says children’s height and weight were measured and plotted on CDC Growth Charts to obtain BMI percentile for age and gender. Measurements were scheduled at baseline and posttest. The record specifies a mean as the outcome parameter and standard deviation as the dispersion measure.

In general, a percentile places a measurement in relation to a reference distribution. Using age and gender on a growth chart gives context to a child’s BMI as development varies across childhood. It is a growth-based measure, not a direct measurement of body composition, parent behavior, or overall health.

For a trial comparison, the mean can describe the group’s average endpoint, while the standard deviation describes variation among individual measurements. A comparison over time could also depend on how baseline values are incorporated and how repeated measurements are modeled. The registry record does not state the specific analysis method or report numerical means, standard deviations, changes, or between-group estimates. It lists baseline and posttest, and the outcome is not reduced in the posted results to a single comparison. Consequently, the direction, magnitude, and precision of any primary-outcome difference cannot be read from the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry record identifies a randomized parallel-group design and a continuous primary outcome summarized as a mean with standard deviation. It does not name the statistical model or report an inferential analysis for the primary outcome. The explanations below are general descriptions of methods relevant to this kind of question, not claims about analyses actually used in this trial.

What does random allocation contribute?

In general, random allocation is intended to make treatment assignment independent of participants’ measured and unmeasured characteristics at the time of assignment. It supports a fair comparison of groups, especially when the allocation process is implemented and concealed appropriately. Randomization does not guarantee that groups will be identical, nor does it prevent bias from missing data, outcome measurement, deviations from assigned intervention, or selective reporting. The registry record says allocation was randomized, but it does not describe the sequence-generation or concealment procedures.

How should a continuous outcome be described?

A mean gives the arithmetic average of a continuous measure within a group. A standard deviation describes how dispersed individual measurements are around that group mean. These statistics answer different questions: a mean concerns the group’s central level, while a standard deviation concerns variation among measurements. A group mean by itself does not show whether participants changed in similar ways or whether a subgroup had a different pattern. The registry record specifies mean and standard deviation, but does not report their values for the primary endpoint.

Why does the choice of contrast matter?

With measurements at baseline and posttest, a trial can describe posttest group means, within-group changes, or a between-group contrast in change. An analysis can also adjust for baseline values. These approaches estimate related but not necessarily identical quantities, and their precision can differ. In general, adjustment for baseline can improve precision when baseline measurements predict follow-up values, but the appropriate approach depends on the design, data, and prespecified analysis. The registry record does not specify the primary contrast or say whether baseline adjustment was used.

What does a confidence interval convey?

In general, a confidence interval expresses uncertainty around an estimated effect under a specified statistical model and its assumptions. A narrower interval indicates greater precision than a wider interval, but interpretation also depends on what differences would be meaningful in context. An interval that includes no difference does not establish that groups are equivalent; it may reflect uncertainty. Equivalence requires an appropriate design and prespecified margin. The registry record does not report a confidence interval or an equivalence framework for child BMI percentile.

When can over-dispersion matter?

Over-dispersion is a general issue for outcomes whose observed variability exceeds what a chosen probability model expects. It is especially relevant to count or binary outcomes when observations are more heterogeneous than a simple model allows. Child BMI percentile is recorded as a continuous measure, so count-model over-dispersion is not a direct description of this endpoint. More generally, an analysis should use a variance model suitable for the outcome and its dependence structure. The registry record does not state a variance model, and there is no basis to infer that over-dispersion was examined.

How should the planning illustrations be read?

The sample-size assumptions describe planning illustrations based on the observed effect, with a two-sided significance level of 0.05, equal allocation between arms, and a normal approximation; the effect to detect is a stated fraction of the observed effect. For non-time-to-event outcomes, the assumptions describe participants per arm. These are illustrative calculations, not evidence of the trial’s original design target or its actual statistical power. The registry record does not report the study’s sample-size justification or the numerical illustration results. A planning calculation based on an observed effect should not be interpreted as observed power or as proof that the study was adequately powered.

The registry record does not give enough information to verify model assumptions, reproduce an analysis, or evaluate robustness. In particular, no outcome estimates, uncertainty measures, adjustment details, or analysis code are reported in the record. The statistical descriptions above therefore explain concepts relevant to interpreting a randomized continuous-outcome trial without attributing an undocumented method to NOURISH.

10. Multiplicity, Missing Data and Analysis Populations

The registry record names child BMI percentile as the primary outcome and lists child feeding, child quality of life, parental BMI, and parental dietary intake of fat as secondary outcomes. It reports five outcome measures and five analyses, but does not specify how those analyses correspond to the named outcomes or time points. It does not report a multiplicity procedure, a hierarchy of hypotheses, or which comparisons were designated confirmatory. When several outcomes or contrasts are tested, the chance of at least one apparently notable result can increase; in general, prespecification and multiplicity methods help readers distinguish confirmatory from exploratory evidence. The record does not say whether such methods were used.

The primary outcome description includes baseline and posttest, while the posted results are not reduced to one comparison. The registry record does not identify a prespecified primary time-point contrast or say how repeated measurements were modeled. It also does not report numerical estimates or tests for the primary or secondary outcomes. Without those details, readers cannot assess the relationship between the planned and reported analyses.

Missing-data information is not reported in the registry record. There are no reported endpoint denominators, amounts or patterns of missingness, reasons for missing measurements, or methods for handling missing data. The analysis population is also not reported: the record does not say whether results were based on all randomized participants, participants who completed the intervention, or another defined group. These omissions matter because exclusion or imputation choices can affect estimates and uncertainty. They do not establish that data were missing or that any particular analysis choice was made; they mean the registry record does not describe those matters.

11. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

The safety listing reports 92 participants at risk in the NOURISH group and 92 in the Wellness Group. For each group, it records 0 serious adverse events and 0 other adverse events. The registry record supplies no serious adverse-event terms.

These entries describe what was recorded in the registry, not proof that no adverse experiences occurred. The record does not report the adverse-event collection period, definitions, ascertainment procedures, or whether the listing covers every event collected during the study. It also does not provide detail on severity categories beyond the serious and other event fields.

The death field is null for both groups, so death counts are not reported in the registry record. A null entry should not be read as a reported zero. The at-risk entries are safety denominators and should not be treated as proof that the same number completed the study or contributed primary-outcome measurements. The safety information therefore supports only a narrow description: the registry listing records no affected participants in its serious or other adverse-event fields, while deaths and important details of safety monitoring are not reported.

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

The registry record describes a randomized evaluation of NOURISH, a parent-focused behavioral intervention, against the Wellness Group. It identifies child BMI percentile as the primary outcome and describes measurement from children’s height and weight plotted on CDC Growth Charts for age and gender. It also identifies several secondary outcome domains. These details define the intended question and the outcome framework.

The record does not report a numerical primary-outcome comparison. It therefore cannot establish the direction or size of a difference between groups, how precisely an effect was estimated, or whether a statistical test supported a particular conclusion. No claim that NOURISH changed child BMI percentile, or that it did not, is justified by the reported endpoint information. The same caution applies to the listed secondary outcomes.

Even if an outcome estimate were available, a statistical contrast would not by itself establish the practical importance of a difference. General interpretation would consider the magnitude and uncertainty of the estimate, the measurement scale, the population studied, and the analysis choices. The registry record does not report a threshold for a meaningful difference or sufficient numerical results for that assessment.

The trial’s randomized design is relevant to the intended comparison, but design labels alone do not resolve questions about implementation, missing data, outcome analysis, or reporting. Masking is listed as none, and the registry record does not report allocation concealment or analysis populations. The safety listing records zero serious and zero other adverse events in each arm, but that limited entry is not a complete account of safety without ascertainment details; death counts are not reported.

The most defensible conclusion is that the registry record documents a completed randomized trial and its stated outcome question, but does not report enough primary outcome evidence to determine the result. The record should not be used to infer benefit, lack of benefit, or equivalence.

13. Why This Trial Matters Statistically

This trial is statistically interesting because it places a parent-focused behavior-change intervention alongside a group comparator while measuring a child-level growth outcome. That creates a distinction between the intervention’s intended mechanism—parent role modeling and teaching healthy behaviors—and the endpoint used to evaluate the trial, child BMI percentile. A measure of the proposed mechanism and a measure of the clinical outcome answer different questions. The registry record does not report numerical results for either type of outcome.

The intervention description also includes NOURISH durations of 12 and 6 weeks across different participant waves, with the same concepts covered. This makes it important to know how duration and wave were treated in the analysis. The registry record does not report whether those features were modeled, whether duration-specific outcomes were compared, or how they contributed to the main estimate. Without that information, the intervention contrast is not fully characterized analytically.

More broadly, the record illustrates why a trial’s design and outcome definitions are not substitutes for its results. Random allocation describes the intended basis for comparison, and the endpoint description explains what was measured. Neither provides the estimated group contrast, its uncertainty, or details needed to assess missing data and analysis populations. Those elements are essential for a statistical reading of the evidence.

The record identifies secondary outcomes as well as a primary outcome, but does not explain the analysis hierarchy or multiplicity approach. That omission makes it difficult to know how findings across outcomes should be interpreted if numerical results are encountered elsewhere. In this registry record, the central statistical contribution is therefore the documented research question and design, while the quantitative evidence needed to answer the question is not reported.

14. 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 limitation for interpreting this trial from the registry record is the absence of numerical primary-outcome results. The record does not provide group means, changes, effect estimates, confidence intervals, or a test result for child BMI percentile. The endpoint is described at baseline and posttest, but no single comparison is reported. This prevents evaluation of direction, magnitude, and precision.

The NOURISH intervention was delivered in durations of 12 and 6 weeks to different participant waves. Although the registry says the concepts were the same, it does not report how duration was handled in the analysis or whether results were examined separately by duration. The record also does not describe whether participants received the intended intervention as planned or how adherence was assessed.

Masking is listed as none. The registry does note that the Wellness Group moderator was blinded to the study aims and hypotheses, but does not describe blinding of outcome assessors or participants. It does not report allocation concealment, baseline outcome values, analysis populations, or missing-data procedures. These details are relevant to judging possible bias and the robustness of the comparison.

The registry lists secondary outcomes and five analyses, but does not report a multiplicity strategy or clarify the relation between analyses, outcomes, and time points. The safety listing is also limited: it records no serious or other affected participants in either group, but does not report event-collection details or death counts. Finally, the sample-size assumptions describe planning illustrations based on an observed effect, not the trial’s design justification; numerical planning results are not reported in the registry record for this record.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: NOURISH: Nourishing Our Understanding of Role Modeling to Improve Support and Health — NCT00628030.
• Registry record last updated 2015-01-19; status last verified 2015-01.
• Results first posted 2015-01-09.
• 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.

18. Record Summary

NOURISH (NCT00628030) is a completed randomized, parallel-group study sponsored by Virginia Commonwealth University. The registry record lists enrollment of 184 and study dates of 2008-04 through primary completion in 2010-04. The intervention was parent-focused NOURISH, compared with the Wellness Group.

The primary outcome was child BMI percentile, derived from measured height and weight plotted on CDC Growth Charts for age and gender, with baseline and posttest listed as time points. Secondary outcomes included child feeding, child quality of life, parental BMI, and parental dietary intake of fat.

Numerical primary and secondary outcome results, analysis populations, missing-data methods, and the statistical analysis plan are not reported in the registry record. The safety listing records zero serious and zero other adverse events in each group; death counts are not reported. The record documents the trial question and design but does not provide the quantitative results needed to judge the primary comparison.