A Mobile Phone Based Pilot Intervention to Prevent Obesity in Latino Preschool Children: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Mobile Phone Based Pilot Intervention to Prevent Obesity in Latino Preschool Children (NCT04261985), a randomized na study. The primary outcome is Child Weight.

2. Clinical Question

The trial was framed as a pilot to assess feasibility and preliminary effect sizes in preparation for a larger randomized trial. Its central clinical question is therefore exploratory: what pattern of child-weight measurements was observed in the two arms, and how precisely do the posted data estimate the between-arm difference? The registry also describes dietary and physical-activity changes as secondary interests, but results for those outcomes are not reported in the registry record.

The outcome record concerns weight rather than BMI. Weight is a direct measurement of body mass; BMI incorporates height as well as weight. The registry does not report a posted child-BMI result alongside the child-weight result. That distinction matters when interpreting whether the primary outcome described in the summary is the same measure as the primary outcome reported in the results.

3. Trial Design

This was a completed, randomized, parallel-group pilot trial with single masking. The registry does not identify who was masked, so the masking description cannot establish whether participants, caregivers, outcome assessors, or another group were unaware of allocation. The recorded enrollment was 59. The study began on 2020-06-08, and primary completion was recorded as 2021-07-01.

The intervention was a behavioral program using a web-based mobile-phone application to support healthy-weight behaviors. The intervention arm description says approximately 30 caregiver-child dyads would be randomized to that arm. Caregivers were to receive 4 interactive multimedia prompts each week for 4 weeks. The control description likewise refers to approximately 30 dyads, and describes the control as no intervention, but also says caregivers would receive prompts about managing common childhood illnesses. The record does not resolve that apparent ambiguity.

The registry summary describes a prospective control-group pilot among caregivers of Latino children aged 2 to 5 years. It identifies child BMI changes as the primary outcome of interest and dietary and physical-activity changes as secondary outcomes, measured at 6 months post-baseline. In the posted outcome results, however, the primary measure is Child Weight in pounds at 6-months post baseline. Caregiver Weight in Pounds is listed as a secondary measure at 6-months post-intervention.

The record identifies the sponsor as the University of California, Los Angeles, and lists the study status as completed. It does not report the original statistical analysis plan, the planned sample-size justification, the intended analysis population, or details of how allocation was generated or concealed. Those design details should not be inferred from the randomized label alone.

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: This study set out to enroll 60 parent-child dyads. Every parent-child dyad consists of one child between 2-years old and 5-years old and the child's primary caregiver. We, therefore, set out to enroll a total of 120 participants (60 children and 60 caregivers).

Baseline

6-month Follow-up

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 Child Weight, measured over 6-months post baseline.

The posted primary endpoint is Child Weight, measured in pounds at 6-months post baseline. The registry says child weight was measured on a digital scale, calibrated with a 5kg weight before each measurement, to the nearest 0.1 pounds. The reported summary is a mean with a standard deviation for each arm.

Weight is a continuous measure of body mass. In general, continuous outcomes can retain information about the range of measurements rather than reducing results to categories. The mean describes the central value in an arm, while the standard deviation describes the observed spread of individual measurements around that mean. These summaries help characterize the groups and support estimation of an average difference between arms.

The registry summary refers to BMI changes as the primary outcome in describing the study's aims, but the posted primary outcome result is weight in pounds. BMI and weight are not interchangeable: BMI also depends on height. A child-BMI result is not reported in the registry record. The endpoint therefore supports interpretation of the recorded weight summaries, not a conclusion about a posted BMI comparison.

Child weight was selected in the registry as the primary outcome measure for the posted results. The registry does not report why this measure was selected over other possible measures, how it was intended to relate to the intervention's goals, or whether weight change from baseline was analyzed. The posted result is a follow-up weight summary, not a reported change score.

7. Results Posted in the Registry

• Mobile Phone Obesity Intervention: mean 45.60 versus 44.90 on control; difference 0.70 (95% CI -4.10 to 5.50), standardized effect d = 0.08; z-test p = 0.775.

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.

Caregiver Weight in Pounds

• 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:
  • Mobile Phone Obesity Intervention: mean 176.90 versus 178.30 on control; difference -1.40 (95% CI -19.18 to 16.38), standardized effect d = -0.04; z-test p = 0.877.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Mobile Phone Obesity Intervention and the control. The interval gives the range of effects that remain compatible with the data.

Caregiver Weight in Pounds is the one secondary outcome with posted results. The registry summary also describes dietary and physical-activity changes as secondary interests, but results for those outcomes are not reported in the registry record. The overall secondary-outcome evidence is therefore limited to the caregiver-weight measure, rather than a complete assessment of the secondary aims described in the summary.

The secondary outcome is distinct from the primary child-weight measure because it records caregiver weight rather than child weight. Taken together, the posted results can describe measurements in both caregivers and children, but they do not provide a broad evaluation of dietary behavior, physical activity, or other pathways mentioned in the study summary. The registry does not report whether the secondary result was intended to inform a particular mechanism or how it was expected to relate to child weight.

Secondary outcomes generally carry less evidential weight than a prespecified primary endpoint. They can be useful for understanding patterns and generating hypotheses, but interpretation is less secure when many outcomes may be examined and no multiplicity plan is reported. The registry does not report a multiplicity adjustment or a prespecified hierarchy among secondary outcomes. The single listed secondary result should therefore be treated as exploratory.

The caregiver-weight result does not replace the child outcome, and it cannot resolve uncertainty in the primary child-weight estimate. Nor does a secondary result establish a change in dietary or physical-activity behavior, since those results are not reported. The pilot framing and incomplete reporting of the broader secondary aims call for caution in drawing conclusions from the secondary evidence.

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

• Caregiver Weight in Pounds

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous, and the registry reports a mean and standard deviation for each arm. A mean is the arithmetic average of the observations in a group. A standard deviation describes how dispersed those observations are around the mean. They answer different questions: the mean describes the group's central measurement, while the standard deviation describes variation among participants. Neither alone describes the precision of the between-arm estimate.

The reported mean difference compares the intervention-arm mean with the control-arm mean. The posted estimate is 0.7 lbs. The comparison is identified as unadjusted, meaning it is not presented as controlling for baseline measurements or other covariates. The registry does not report whether any adjusted model was planned or conducted. An unadjusted comparison is straightforward to interpret, but it may not answer the same question as a prespecified adjusted analysis when baseline values or other prognostic factors are relevant.

A confidence interval gives a range of estimates compatible with the observed data under the method's assumptions. Its endpoints reflect both the estimated difference and sampling uncertainty. A wider interval indicates less precision than a narrower interval. The 95% interval for the child-weight difference extends from -4.103 to 5.503 lbs. Since it includes zero and values on both sides, it does not identify a single direction with precision. In general, the interval should be considered together with the estimated difference, study design, measurement, and analysis plan.

The unadjusted p-value is 0.775. In general, a p-value measures how inconsistent the observed data are with a specified null model, under the assumptions of the statistical test. It does not measure the size or clinical importance of an effect, and it is not the probability that the null model is true. The registry does not report a full statistical methods description for the comparison, so details beyond the unadjusted nature of the estimate are not reported in the registry record.

For continuous outcomes, a pooled standard deviation can be used to express a mean difference relative to the variability observed across arms. The posted comparison lists a pooled standard deviation of 9.116 lbs. Such standardization can help compare effects measured on different scales, but it does not replace the original-unit estimate. The registry does not report that this standardized quantity was a prespecified primary analysis, so the pounds-scale difference and its confidence interval remain the most direct descriptions of the child-weight result.

General statistical context: in a randomized trial, random allocation is intended to make groups comparable on average, including for characteristics that are not measured. In a pilot with limited outcome counts, chance differences may still occur, and estimates can be imprecise. Randomization does not remove uncertainty, prevent missing outcomes, or establish that the people with recorded follow-up measurements represent everyone enrolled. The registry does not report details of allocation concealment, baseline balance, or an analysis population.

General statistical context: over-dispersion describes variability greater than a model expects. It matters because standard errors and confidence intervals may be too narrow if the model understates variability. The posted child outcome is summarized as a continuous measure with standard deviations, and no over-dispersion assessment is reported in the registry record. It would therefore be inappropriate to claim that over-dispersion was present or that a correction was needed in this trial.

The arm summaries include 26.0 intervention participants and 31.0 control participants for child weight. The registry reports standard errors for the arm means as 1.902 and 1.545, respectively. A standard error describes uncertainty in an estimated mean, rather than the spread of individual measurements. It is generally smaller than the standard deviation because it reflects precision of the mean, which depends on both variability and the amount of information. The registry does not describe how outcome availability was determined or how missing measurements were handled.

The trial is described as randomized and single masked, but no analysis plan is listed. No reported analyses are listed in the registry record. The outcome comparison is nevertheless posted as an unadjusted estimate. The record does not explain whether this comparison was specified in advance, whether any interim analyses took place, or whether multiple candidate analyses were considered. These omissions limit assessment of the degree to which the posted analysis followed a prespecified plan.

The sample-size planning illustration uses a two-sided significance level of 0.05, equal allocation between arms, and a normal approximation. It considers effects defined as a stated fraction of the observed effect. These are planning assumptions for an illustration, not the original design assumptions of the trial; the original sample-size justification is not reported in the registry record. Planning values based on an observed pilot estimate are particularly uncertain because the pilot estimate itself may be unstable.

General statistical context: a clinical result should be interpreted by considering the design, outcome definition, precision, analysis population, missing data, and multiplicity together. A p-value alone cannot establish whether an effect is important, and a point estimate alone cannot show how precisely it is known. Here, the record supports description of the posted unadjusted child-weight contrast, but does not provide enough methodological detail to reconstruct a complete prespecified analysis strategy.

11. Confidence Intervals and Precision

The child-weight mean difference is 0.7 lbs, and its 95% confidence interval runs from -4.103 to 5.503 lbs. The interval includes zero and extends in both directions. It therefore conveys substantial uncertainty about the direction and size of the underlying difference. The point estimate is one estimate within that interval, not a precise statement of the effect.

A confidence interval is a measure of statistical precision, not a guarantee that the true effect lies inside a particular interval. In general, intervals are constructed by a method that would cover the target parameter at the stated rate across repeated use under its assumptions. The registry does not report the full interval-construction method for this comparison, beyond identifying the estimate as unadjusted.

The observed standard deviations were 9.7 lbs in the intervention arm and 8.6 lbs in the control arm. They describe spread among the recorded child weights, not uncertainty in the mean difference itself. The endpoint sample sizes were 26.0 and 31.0. Both the spread of measurements and the number of observations contribute to precision, but the confidence interval is the clearest posted summary of uncertainty about the contrast.

The unadjusted p-value of 0.775 is consistent with the interval's inclusion of zero, but the interval is more informative about the range of estimates compatible with the data. Neither statistic alone establishes whether differences within the interval would be clinically important. The registry does not report a threshold for a meaningful child-weight difference or a precision target for this pilot.

Because this was a pilot, its role was described as estimating feasibility and preliminary effect sizes for planning further research. A wide interval is important in that setting: the observed difference may not be a stable guide to the size of an effect in a larger study. The record does not report a minimum detectable effect, a planned confidence-interval width, or a formal sample-size justification.

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, not total events. The assumptions listed for the illustration are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to be detected is set to the stated fraction of the observed effect. The original sample-size assumptions for the trial are not reported in the registry record.

The 80% power column gives the number of participants per arm that the planning calculation estimates would be needed for an 80% chance of detecting the chosen effect under the stated assumptions, if that effect and model assumptions were correct. The 90% power column expresses the corresponding planning target for a 90% chance. Power is a design property calculated for an assumed effect, not a measure of the result's credibility.

The planning entries consider 100%, 75%, and 50% of the observed effect. For child weight, planning for 100% of the observed effect gives 2,663 participants per arm for 80% power and 3,565 participants per arm for 90% power. Planning for 75% gives 4,734 participants per arm for 80% power and 6,337 participants per arm for 90% power. Planning for 50% gives 10,651 participants per arm for 80% power and 14,258 participants per arm for 90% power.

Smaller effects require more participants to detect under the same assumptions, which is why the planning counts rise as the effect fraction decreases. These figures are a planning illustration based on the observed pilot effect, not the trial's original design calculation. They are not observed power. The registry does not report the original sample-size justification, and the observed effect used for planning may be imprecise.

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 = 0.700; pooled standard deviation σ = 9.116.
2. n = 2 × (1.96 + 0.842)² × 9.116² / 0.700² = 2,662.5, rounded up to 2,663 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 <- 0.700000000000003                      # observed difference in means
sigma <- 9.11646861454587                     # 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(4261985)
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 = 2,663 (80% power), 3,565 (90% power)
 75% of observed effect: n per arm = 4,734 (80% power), 6,337 (90% power)
 50% of observed effect: n per arm = 10,651 (80% power), 14,258 (90% power)
power.t.test: 2663.5 
Simulated power at n = 2,663 per arm: 0.799 (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 registry does not report a multiplicity strategy. Multiplicity arises when several outcomes, comparisons, or analyses are assessed: without a plan to account for those tests, the chance of obtaining a seemingly notable result by chance can increase. The summary describes child BMI, dietary behavior, and physical activity as areas of interest, while the posted outcome results include child weight and caregiver weight. The record does not explain the relationship between these sets of measures or identify a prespecified hierarchy for interpreting them.

No reported analyses are listed in the registry record. The record does include an unadjusted comparison for the posted primary outcome and a comparison for caregiver weight, but it does not describe the complete analysis plan, identify which analyses were prespecified, or state whether additional analyses were conducted. Interim analyses are not reported in the registry record.

Missing-data methods are also not reported. The child-weight summaries include 26.0 participants in the intervention arm and 31.0 in the control arm, whereas total enrollment was 59. The registry does not state why outcome counts differ from enrollment, whether measurements were missing, or whether any missingness was related to participant characteristics or outcomes. It does not describe imputation, complete-case analysis, or sensitivity analyses for missing data.

The analysis population is not reported in the registry record. It is therefore unclear whether the posted summaries follow an intention-to-treat population, include only participants with available follow-up measurements, or use another definition. The registry also does not report baseline comparisons or an analysis that adjusts for baseline weight.

These omissions do not establish that multiplicity, missingness, or analytic choices biased the results. They mean that readers cannot evaluate those issues from the registry record. The randomized design is an important feature, but the result's interpretation still depends on outcome availability, the analysis population, and whether the analysis followed a prespecified plan.

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 adverse-event record lists 54 participants at risk in the Mobile Phone Obesity Intervention group and 64 in the Control group. It records zero serious adverse events in each group, zero other adverse events in each group, and zero deaths in each group. The registry lists no serious adverse-event terms.

These figures describe what was entered in the registry for the stated at-risk groups. The at-risk counts differ from the arm sizes reported for the weight outcomes, and the registry does not explain the relationship between those counts. They should not be assumed to be the same participant sets as those contributing to the efficacy summaries.

Zero recorded events does not establish that no events occurred outside the registry's definitions or observation procedures. The record does not report detailed event definitions, collection methods, follow-up duration for safety, or whether events were actively solicited. The figures should therefore be read as registry-recorded counts, not as a complete assessment of safety or proof that the intervention had no adverse effects.

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

The posted child-weight data show an intervention-arm mean of 45.6 lbs and a control-arm mean of 44.9 lbs at 6-months post baseline. The unadjusted estimated difference is 0.7 lbs, with a 95% confidence interval from -4.103 to 5.503 lbs. The interval includes values in both directions, so the estimate is not precise about the direction or size of the difference.

This result does not establish that the mobile-phone intervention caused a change in child weight. The posted comparison is unadjusted, the analysis population and missing-data handling are not reported, and the record does not provide a child-weight change-from-baseline analysis. The outcome listed in the results is weight, while the registry summary describes BMI changes as the primary outcome of interest. No child-BMI result is reported in the registry record.

The trial was explicitly described as a pilot intended to assess feasibility and preliminary effect sizes in preparation for a larger randomized trial. Pilot estimates can help frame later research, but this estimate should not be treated as a definitive answer about intervention efficacy. The registry does not report a feasibility outcome or the original sample-size justification. The planning figures based on the observed result are illustrative, not evidence that the trial had a particular level of power.

The study's aims included dietary and physical-activity outcomes, but results for those measures are not reported in the registry record. A caregiver-weight result is posted as a secondary outcome, but that does not answer whether the intervention affected children's dietary behavior or physical activity. The available outcome reporting thus addresses only part of the broad set of aims described in the summary.

Finally, the safety record contains zero recorded serious adverse events, other adverse events, and deaths in the listed groups. Those entries are descriptive counts and do not establish the absence of risk. The appropriate interpretation is limited to the posted measurements and their uncertainty, with the registry's omissions taken into account.

17. Why This Trial Matters Statistically

This trial is statistically informative as an example of how a pilot estimate and its uncertainty should be read together. The child-weight point estimate is easy to state, but the confidence interval is wide and spans differences in both directions. That uncertainty is central to interpreting a pilot intended to generate preliminary effect-size information.

The registry also illustrates why outcome definitions require close attention. The study summary describes child BMI changes as the primary outcome, while the posted primary result is Child Weight in pounds at a follow-up timepoint. Since BMI and weight are different measures, an interpretation should not silently treat the recorded weight result as a BMI result or as a change score.

Planning calculations based on an observed pilot effect can illustrate the scale of a later study under stated assumptions. They do not substitute for the trial's original sample-size justification, which is not reported in the registry record, and they do not convert a pilot result into a reliable estimate. The size of the planning counts also emphasizes how assumptions about the effect to be detected shape sample-size requirements.

Finally, the record leaves key analytic questions unanswered: the analysis population, missing-data handling, multiplicity strategy, and detailed statistical plan are not reported. This does not invalidate the posted summaries, but it limits what can be inferred from them. Clear registry reporting of outcome definitions and analysis choices is important for readers assessing precision, reproducibility, and the strength of evidence.

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 primary limitation is the mismatch between the outcome emphasized in the registry summary and the primary outcome result posted. The summary refers to child BMI changes, whereas the result is child weight in pounds at 6-months post baseline. A BMI result and a change-from-baseline result are not reported in the registry record, so the posted outcome cannot answer every aspect of the stated primary aim.

The child-weight estimate is imprecise, as reflected by its confidence interval. The study was described as a pilot, and its enrollment was 59. The outcome summaries include 26.0 intervention participants and 31.0 control participants; the record does not explain outcome availability or missingness. This makes it difficult to assess the potential effects of incomplete follow-up.

Important design and analysis details are absent. The registry does not report who was masked, allocation concealment, the original sample-size justification, analysis-population definitions, missing-data methods, multiplicity handling, interim analyses, or a complete statistical analysis plan. It also does not report results for dietary or physical-activity outcomes, despite describing them as secondary aims.

The control-arm description is not fully clear: it calls the condition no intervention but also describes prompts about common childhood illnesses. The registry does not clarify the nature or delivery of those prompts. This limits precise characterization of the contrast between arms. Finally, adverse-event counts are available, but details about event ascertainment and follow-up are not reported, limiting interpretation of the safety entries.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: A Mobile Phone Based Pilot Intervention to Prevent Obesity in Latino Preschool Children — NCT04261985.
• Registry record last updated 2024-10-16; status last verified 2024-10.
• Results first posted 2024-10-16.
• 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

NCT04261985 is a completed, randomized, parallel-group, single-masked pilot trial sponsored by the University of California, Los Angeles. It enrolled 59 participants and evaluated a mobile-phone intervention supporting healthy-weight behaviors among Latino caregivers of children aged 2 to 5 years.

The posted primary outcome is child weight in pounds at 6-months post baseline. The unadjusted mean difference was 0.7 lbs, with a 95% confidence interval from -4.103 to 5.503 lbs and an unadjusted p-value of 0.775. Caregiver weight is listed as a secondary outcome. Results for dietary and physical-activity outcomes are not reported in the registry record.

The confidence interval indicates substantial uncertainty around the child-weight estimate. The registry does not report the original sample-size justification, analysis population, missing-data methods, or multiplicity strategy. The summary describes child BMI changes as the primary outcome of interest, but a child-BMI result is not reported.