Painted Playgrounds: Aim 2: Assessments: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Painted Playgrounds: Aim 2: Assessments (NCT03885518), a randomized na study. The primary outcome is Change in Moderate to Vigorous Activity (MVPA) During Recess.

2. Clinical Question

The question concerns a measured activity outcome over the study's baseline and follow-up period, not a clinical diagnosis or a direct measure of long-term health. The registry record describes the project as an assessment of whether playground stenciling could increase activity and improve motor skills; the posted primary outcome concerns change in recess MVPA. The comparison is between assigned groups, with the control group scheduled to receive the intervention later. The record does not establish whether every participant completed both assessments, how the analysis handled incomplete measurements, or whether other factors were adjusted for.

3. Trial Design

This was a completed, randomized, parallel-group study, with single masking recorded in the registry. The record does not identify who was masked, so the masking designation cannot be interpreted more specifically. Participants attended childcare centers randomized to either playground stencils or a wait-list control condition. The intervention arm was scheduled to receive stencil activities after baseline measurement; the wait-list arm was scheduled to receive them approximately 8 weeks after enrolling, following baseline and follow-up assessments.

The brief summary describes individual assessments at baseline and follow-up 6-8 weeks later. It lists height and weight, surveys, and wearing an accelerometer for 7 days. A parent or legal guardian was to provide consent and complete a brief survey about the child's lifestyle and habits. These procedures describe the assessment project, but the registry record does not give completion rates or detailed measurement protocols.

The stated enrollment is 51. The brief summary describes 72 children as participants, and the record does not explain the difference. The reported outcome groups include 32 children in the intervention arm and 19 in the control arm. The study is marked completed; the record lists a start date of 2018-12-15 and a primary completion date of 2019-06-30.

The primary outcome is change in moderate-to-vigorous physical activity during recess, expressed as percentage of time. No phase applies. The registry record lists two outcome measures but no secondary results are posted. It also lists zero analysis records. The posted arm summaries and comparison figures therefore need to be read as the results available in the registry, without assuming details about the full analysis plan, participant flow, or any unreported procedures.

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

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 Change in Moderate to Vigorous Activity (MVPA) During Recess, measured over Baseline and follow-up (6 to 8 weeks after playground stenciling).

The primary endpoint is change in the percentage of recess time spent in moderate-to-vigorous physical activity, abbreviated MVPA. Accelerometers were used to measure activity objectively. The record identifies the measurement time points as baseline and follow-up 6 to 8 weeks after playground stenciling. The endpoint is a continuous measure: each child's activity during recess is represented on a scale of percentage of time, and the group results are summarized with means and standard deviations.

Focusing on change allows the assessment to compare activity over the study period rather than relying only on a single measurement. Recess provides a defined context for observing children's activity, and an accelerometer avoids relying solely on a child's or parent's recollection. These are general reasons such measures can be useful; they do not establish how the activity monitor data were processed in this particular study. The registry record does not report the accelerometer thresholds, valid-wear rules, or the precise calculation used to form each participant's change score.

The endpoint is a behavioral measurement, not a direct measure of body weight, fitness, or later health. The registry record also describes height and weight assessments and motor skills as areas of interest, but no secondary results are posted. Interpretation should therefore stay focused on the reported recess MVPA outcome and its short follow-up window.

7. Results Posted in the Registry

• Intervention: mean 1.40 versus 6.20 on control; difference -4.80 (95% CI -7.05 to -2.55), standardized effect d = -1.25; z-test p = <0.001.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary measure is continuous: change in the percentage of recess time spent in MVPA. For continuous outcomes, a group mean describes the average recorded value, while a standard deviation describes how spread out individual values are around that mean. The intervention arm's mean is 1.4 with standard deviation 3.7, and the control arm's mean is 6.2 with standard deviation 4.1. Those summaries provide a compact description, but they do not reveal the complete distribution or whether a few values strongly influence the mean.

What does a mean difference represent?

A mean difference subtracts one group's average from the other's. In this comparison the intervention mean is 1.4 and the control mean is 6.2, producing the reported contrast of -4.8. The negative sign indicates that the intervention group's mean change value is lower than the control group's. The measure is on the percentage-of-time scale. Because the endpoint is change, the comparison concerns changes in activity rather than a direct contrast of follow-up activity alone.

The comparison is unadjusted. In general, an unadjusted contrast compares the group summaries without accounting for additional variables in a statistical model. That can make the result easy to interpret, but it does not show whether baseline values or other characteristics were considered. The registry record does not report a model specification, covariate adjustment, or an analysis accounting for center-level randomization. The absence of those details means the result should be described as posted, not reconstructed as a more elaborate analysis.

How should the p-value be understood?

The reported unadjusted p-value is p < 0.001. In general, a p-value describes how often a result at least as incompatible with the null hypothesis could arise if the null model and the test assumptions were correct. It is not the chance that the result is due to chance, and it does not tell readers whether the difference matters in practice. Its interpretation depends on the test and assumptions. The registry record does not identify the test used, so a specific test procedure should not be inferred.

Why does the confidence interval matter?

A confidence interval describes a range of values compatible with the data and the method used to calculate the interval. The reported interval for the mean difference is -7.045 to -2.555. Its position relative to zero conveys the direction and statistical precision of the contrast under that method. It also shows that uncertainty remains: the estimate is not known exactly. A confidence interval is not a range containing a fixed proportion of individual children's outcomes, and it does not account for sources of bias that the analysis has not addressed.

Standard deviations and standard errors describe different kinds of variation. The standard deviation summarizes spread among participant values. A standard error describes uncertainty in an estimate, such as a group mean, under a statistical model. The comparison record lists standard errors of 0.941 and 0.654 for the control and intervention means, respectively. The standard errors help characterize how precisely those means are estimated, but do not replace the confidence interval for the between-group contrast.

What assumptions affect interpretation?

Any statistical comparison relies on assumptions about how observations were collected and how they relate to one another. General examples include whether measurements are independent, whether the model represents the outcome adequately, and whether missing values affect the comparison. In a study that randomizes childcare centers, measurements from children in the same center may be related. If such dependence is present, a method that treats every child as independent may understate uncertainty. The registry record does not say whether or how the analysis accounted for center-level grouping, so this remains an unresolved methodological detail rather than a basis for recalculating the result.

Other key details are also not reported in the registry record: the original statistical analysis plan, missing-data procedures, the analysis population, the handling of baseline measurements, and the method used to derive change scores. The record lists zero analysis records. The posted comparison should consequently be read as the available unadjusted summary, with its assumptions and limitations acknowledged rather than filled in by conjecture.

What is the role of the planning illustrations?

The sample-size illustrations use the observed effect as a reference and consider smaller fractions of it. They are planning calculations, not results about how much power the completed trial had. In general, power is the probability that a specified test will detect a specified effect under stated assumptions. The illustrations use a two-sided significance level of 0.05, equal allocation between arms, and a normal approximation. The original trial's own sample-size justification and design assumptions are not reported in the registry record. The calculations therefore cannot establish whether the study was originally planned around these assumptions or effects.

10. Confidence Intervals and Precision

The reported mean difference is -4.8, with a 95% confidence interval from -7.045 to -2.555. This interval describes the uncertainty around the estimated unadjusted difference under the method used to calculate it. All values in the interval are negative, so the interval is consistent with a lower mean change value in the intervention group than in the control group. The p-value is p < 0.001, which is consistent with the interval excluding zero for this comparison.

The confidence interval's width reflects sampling uncertainty, but it cannot describe every source of uncertainty. In particular, it does not resolve possible measurement error, missing follow-up data, center-level clustering, or bias from factors not included in the analysis. The registry record does not report the interval calculation method or a model that could clarify how such design features were handled. Its precision should therefore be understood as conditional on the statistical approach behind the posted comparison.

The group standard deviations are 3.7 in the intervention arm and 4.1 in the control arm, indicating variation in participant outcome values. The interval is about the group difference, not individual outcomes. It does not imply that every participant experienced a change within its bounds, nor does it show how effects varied across centers or children. The record does not provide further distributional summaries or subgroup intervals.

Statistical precision and practical importance are distinct. The interval conveys the range of group contrasts compatible with the analysis, while the registry record does not specify a threshold for a meaningful change in recess MVPA. The estimate can be described in the endpoint's scale, but the available information does not establish how large a difference would be important to children, families, or childcare centers.

11. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The planning figures are participants per arm, not total events. This is a continuous-outcome comparison, so the values describe the number of participants assigned to each arm under the planning assumptions. The calculation uses a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. It considers effects set at 100% of the observed effect, 75% of the observed effect, and 50% of the observed effect. The original trial's own design assumptions and sample-size justification are not reported in the registry record.

The 80% power column gives the illustrative participants per arm for a calculation with 80% power to detect the stated effect fraction under those assumptions. The 90% power column gives the corresponding participants per arm for 90% power. Power is a property of a planned test under specified assumptions; it is not a measure of the probability that the observed result is correct. These figures are planning illustrations based on the observed effect, not observed power for the completed study.

The figures increase as the assumed effect becomes smaller. That pattern is expected in general: a smaller difference is harder to distinguish from sampling variation, so more participants are needed to detect it at a given power level. These calculations do not show what sample size was intended when the study was designed, and they should not be treated as proof that the enrolled sample was adequate or inadequate. They also do not account for design features that are not included in the listed assumptions, such as a possible center-level correlation.

12. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = -4.800; pooled standard deviation σ = 3.852.
2. n = 2 × (1.96 + 0.842)² × 3.852² / -4.800² = 10.1, rounded up to 11 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 <- -4.8                      # observed difference in means
sigma <- 3.85176874292572                     # 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(3885518)
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 = 11 (80% power), 14 (90% power)
 75% of observed effect: n per arm = 18 (80% power), 25 (90% power)
 50% of observed effect: n per arm = 41 (80% power), 55 (90% power)
power.t.test: 11.2 
Simulated power at n = 11 per arm: 0.794 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

13. Multiplicity, Missing Data and Analysis Populations

The registry record lists two outcome measures, but no secondary results are posted. It identifies change in recess MVPA as the primary outcome. It does not report whether the study prespecified additional outcomes, how outcomes were prioritized, or whether any correction for multiple comparisons was planned. When multiple outcomes or analyses are tested, the chance of at least one apparently unusual result can increase; methods for handling this issue depend on the analysis plan. No such plan is available in the registry record, so no adjustment should be assumed.

The record lists zero analysis records. It gives arm summaries and an unadjusted comparison, but does not document a full statistical analysis plan, analytic population, model, or test procedure. It also does not report whether all randomized children were included in the comparison or whether the analysis followed assignment regardless of intervention receipt.

Missing-data handling is not reported in the registry record. The brief summary describes baseline and follow-up assessments, but does not state how many children completed each assessment, how incomplete accelerometer records were treated, or how any missing outcome values were handled. Complete-case analysis, imputation, or other approaches cannot be inferred. These omissions matter because the interpretation of a group comparison can depend on who contributed data and why measurements are unavailable.

The record describes centers as randomized, but does not report whether the statistical analysis accounted for children being grouped within centers. It also does not describe allocation procedures beyond randomization, or identify who was masked. These gaps do not negate the reported summary; they limit how fully its assumptions and possible sources of uncertainty can be assessed.

14. Safety Results

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

Deaths

Other (non-serious) adverse events

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

The serious adverse event figures report zero affected participants among 32 at risk in the intervention group and zero among 19 at risk in the control group. Deaths are reported as zero in both groups. The record also reports zero participants with other adverse events in each group.

These counts describe what was entered in the registry record; they are not evidence that no unrecorded events occurred. The record does not provide event narratives, severity categories beyond the serious and other groupings, follow-up completeness for safety, or an explanation of how events were collected. No serious-event terms are listed. The figures should therefore be read as the reported counts for the groups and participants at risk, without extrapolating beyond the recorded safety information.

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

The posted data show that the mean change value for recess MVPA was 1.4 in the intervention arm and 6.2 in the control arm. The unadjusted mean difference was -4.8, with a 95% confidence interval from -7.045 to -2.555 and p < 0.001. In this comparison, the intervention group's reported mean change value was lower. The estimate concerns the outcome as recorded over the baseline and follow-up period; it does not compare absolute activity levels at follow-up alone.

The result does not establish why the groups differed. The registry record does not report enough analytic detail to determine how center-level grouping, baseline measurements, missing observations, or other variables were handled. Nor does the comparison tell whether differences in implementation or measurement contributed to the result. A statistically clear contrast under the reported unadjusted analysis is not the same as a complete account of causal effects.

The finding is limited to the participating preschool-aged children and the short assessment period described in the record. It does not establish whether any observed difference persisted, whether it generalizes to other settings, or what it means for motor skills, weight, or longer-term health. Although the project description discusses motor skills and other assessments, no secondary results are posted.

The confidence interval conveys uncertainty in the group estimate, but the registry record does not report a threshold for a practically important change. Readers can assess the direction and statistical precision of the posted contrast, but cannot determine from these data alone whether its magnitude is meaningful in daily practice. The safety record reports no serious adverse events, other adverse events, or deaths in either arm, while leaving the completeness and collection details unreported.

Accordingly, the result is best understood as a short-term, unadjusted comparison in this trial, rather than a broad claim about the effectiveness of playground stenciling. It describes the posted measurements and the uncertainty attached to their group contrast, while important design and analysis details remain unreported.

16. Why This Trial Matters Statistically

This trial illustrates why a result should be read through both its outcome definition and its study design. The primary endpoint is change in a particular setting—recess—and measures the percentage of time spent in MVPA. That specificity matters: the result is not a measure of all-day activity, fitness, motor skill, or long-term health. Describing the measurement precisely helps prevent a narrow outcome from being treated as a broader conclusion.

The randomized, parallel-group design offers a structured comparison between children attending intervention and wait-list control centers. At the same time, the registry record does not say whether the analysis accounted for center-level grouping. When assignment happens at the center level, the relationship among children within a center can affect uncertainty. This general design issue makes clear why analysis details are essential alongside the numerical estimate.

The reported difference and confidence interval provide complementary information: the estimate gives the direction and size of the group contrast on the measured scale, while the interval communicates its statistical precision. Neither alone answers whether the difference is practically important. That judgment would require context that the registry record does not report, including a meaningful-change threshold and a fuller account of implementation and measurement.

The enrollment figure also deserves careful reading. The record states enrollment of 51, while the brief summary describes 72 children. No explanation is given. A reader should preserve that distinction rather than assuming which figure represents the analyzed sample. The arm summaries report 32 and 19 participants, but the record does not describe participant flow or follow-up completion.

Finally, the result demonstrates the boundary between posted statistics and a full analysis report. The registry contains useful group summaries and a comparison, but no analysis records, secondary results, or detailed missing-data and multiplicity plans. Transparent interpretation states what the figures show while keeping those unknowns visible.

17. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The registry record does not explain why the stated enrollment of 51 differs from the 72 children described in the brief summary. The outcome summaries report 32 participants in the intervention group and 19 in the control group, but the record does not provide a participant-flow account, the number completing follow-up, or the number with usable accelerometer data. Those details are necessary to understand how the analyzed groups relate to enrollment.

The intervention was assigned by childcare center, but no center counts or center-level analysis details are reported. The record does not state whether the comparison accounts for within-center similarities among children. It also does not identify who was masked despite recording single masking. These missing details limit assessment of the design and the uncertainty around the group comparison.

The accelerometer procedures are only described generally. The registry record does not report wear-time rules, data-processing thresholds, or the exact method used to derive change in MVPA. It also does not provide a detailed model, test, baseline adjustment, or missing-data method. The lack of posted analysis records and secondary results further limits review of planned versus reported analyses.

The follow-up period is short, and no later outcome is reported. The registry record also provides no threshold for a practically meaningful change in the primary measure. These limitations constrain interpretation to the posted short-term comparison; they do not establish that unreported procedures were inadequate or that unreported outcomes had any particular result.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Painted Playgrounds: Aim 2: Assessments — NCT03885518.
• Registry record last updated 2024-12-24; status last verified 2024-11.
• Results first posted 2024-12-24.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

21. Record Summary

Painted Playgrounds: Aim 2: Assessments is a completed randomized, parallel-group study of playground stenciling in preschool-aged children attending Louisiana childcare centers. The registry record reports single masking and an enrollment of 51; its brief summary describes 72 children, with no explanation of the difference. The intervention group was scheduled for stenciling after baseline assessment, while the wait-list control group was scheduled to receive it after follow-up.

The primary outcome is change in the percentage of recess time spent in MVPA, measured with accelerometers. The posted arm means are 1.4 for intervention and 6.2 for control. The unadjusted mean difference is -4.8, with a 95% confidence interval from -7.045 to -2.555 and p < 0.001. The registry record lists zero analysis records and no secondary results. It reports zero serious adverse events, other adverse events, and deaths in both groups. Details of missing-data handling, center-level analysis, and the original sample-size justification are not reported in the registry record.