Virtual Advisors for Physical Activity Promotion in Underserved Communities: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Virtual Advisors for Physical Activity Promotion in Underserved Communities (NCT02111213), a randomized na study. The primary outcome is Change in Total Weekly Walking Minutes From Baseline to 12 Months.

2. Clinical Question

The primary outcome was defined as change in total minutes walked per week, measured by self-report with the CHAMPS Physical Activity Questionnaire. The registry record identifies the primary analysis population as per protocol. It also lists changes in sedentary behavior and moderate to vigorous physical activity from baseline to 12 months as secondary outcomes.

The clinical question is therefore about the comparative change in reported walking, not whether either intervention changed activity relative to no intervention. The record describes the two active approaches but does not include outcome estimates, confidence intervals, p-values or a conclusion about non-inferiority. It is not possible to determine from the registry record how large the difference in walking change was or how precisely it was estimated.

3. Trial Design

The study is listed as randomized, single-masked and parallel-group, with an enrollment of 245. Its status is completed. The listed phase is NA. The interventions were behavioral: a virtual advisor and a promotora for physical activity. The virtual advisor was named Carmen in the arm description, and both interventions involved weekly sessions at a community center.

The registry record also flags the study as cluster-randomized and cautions that a simple individual-level re-analysis would be misleading. That matters because participants assigned within the same community or group may have outcomes that are more alike than outcomes from participants in different groups. General statistical reasoning: treating correlated participants as independent can make uncertainty appear smaller than it is. The registry record does not explain the clustering units, the number of clusters, or the method used to account for clustering.

The record calls the masking single but does not say which people were masked. It also does not provide details about how randomization was generated or concealed. These design details are not reported in the registry record. The stated enrollment is a study-level figure; the adverse-event figures list 122 participants at risk in the promotora group and 123 in the Carmen System group, but the record does not separately describe the randomized group sizes or participant flow.

The registry summary states that the primary analysis was intended to assess non-inferiority of the virtual advisor relative to the promotora. Non-inferiority asks whether the difference is sufficiently compatible with a prespecified acceptable loss, rather than whether the interventions are identical. The acceptable margin and the detailed analysis plan are not reported in the registry record. Although the study is completed, its status alone does not establish what the outcome comparison found.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: 12-month Change in total minutes per week Per protocol

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 Total Weekly Walking Minutes From Baseline to 12 Months, measured over baseline, 12 months.

The primary endpoint is change in total weekly walking minutes from baseline to 12 months. It is a continuous measure expressed in minutes per week, based on self-report using the CHAMPS Physical Activity Questionnaire. The primary outcome population is described as the per-protocol population, and the record specifies the mean as the summary measure, with standard error as the dispersion measure.

Walking minutes are relevant to the study aim because the intervention was designed to encourage regular walking. Measuring change over time focuses on how reported weekly walking differs at the follow-up assessment from the baseline assessment. A continuous outcome can retain information about the size of changes rather than reducing the measure to a category such as increased or not increased.

General statistical explanation: a mean describes the average outcome in a group, while a standard error describes the precision of an estimated mean. A standard error is not the same as the spread of individual participants’ values. Self-report can capture participants’ reported activity, but it is not a direct device-based measure. The registry record does not report validation details, the exact scoring procedure, or how missing questionnaire responses were handled.

No numerical mean changes, between-group estimate, confidence interval or p-value for this endpoint are reported in the registry record. Thus, the endpoint and its measurement approach are specified, but the magnitude and precision of the observed comparison cannot be assessed from the record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry record describes a randomized, single-masked, parallel-group trial and labels the primary analysis as non-inferiority. It also flags the design as cluster-randomized. These features determine how the comparison should be interpreted, but the registry record does not give enough detail to reconstruct the analysis.

What does non-inferiority mean?

General explanation: a non-inferiority analysis asks whether an intervention is not worse than a comparator by more than an agreed margin. The margin must be chosen in advance and expressed on the scale of the outcome or treatment contrast. The analysis then evaluates whether the uncertainty around the estimated contrast rules out losses beyond that margin. This is not the same as testing whether the two interventions have exactly equal effects, and it is not equivalent to finding no statistically significant difference.

For this trial, the comparator was the promotora intervention and the primary outcome was change in total weekly walking minutes from baseline to 12 months. The registry record does not state the margin, the direction in which the contrast was calculated, or the confidence interval and test used for the non-inferiority decision. It also does not report the estimate. Consequently, the method’s stated purpose is known, but its decision rule and conclusion cannot be checked.

Why does clustering matter?

General explanation: cluster randomization assigns groups rather than treating every participant as an independently randomized unit. Participants in the same cluster may share characteristics or experiences, producing correlated outcomes. An analysis that ignores this correlation can understate uncertainty and overstate precision. Appropriate methods account for the randomization and dependence structure, for example by analyzing at the cluster level or using a model or variance estimate that accounts for clustering. Those are general approaches, not claims about the method used in this study.

The registry record specifically cautions that a simple individual-level re-analysis would be misleading and says only the sponsor’s own analysis is shown. It does not identify the cluster definition, how many clusters were involved, or the sponsor’s statistical method. The numerical sponsor analysis is not reported in the registry record. Therefore, no individual-level re-calculation should be substituted for the trial’s cluster-aware comparison.

What do the outcome summaries represent?

The primary outcome is continuous, and the record identifies the mean as its summary measure and standard error as its dispersion measure. General explanation: the mean represents an average, while its standard error expresses how precisely that average is estimated. The standard error does not describe how widely individual walking values vary. A confidence interval, when reported, combines an estimate with its uncertainty to show a range of values compatible with the data under the statistical method. No primary-outcome confidence interval is reported in the registry record.

Because the outcome is a change from baseline to 12 months, an analysis could compare changes or model follow-up values while accounting for baseline. These are general possibilities only. The registry record does not report which approach was used, whether covariates were included, or how standard errors were calculated for the clustered design.

How should the planning illustration be read?

The record describes a planning illustration based on the observed effect, with a two-sided significance level of 0.05, equal allocation between arms, and a normal approximation. It says the effect to detect is a stated fraction of the observed effect. General explanation: changing the assumed effect changes the number of participants needed to reach a chosen precision or power target, while the significance level and allocation assumptions also influence the calculation. These are hypothetical planning inputs, not observed trial outcomes.

The record distinguishes the illustration from the trial’s own design. The registry record does not report the original sample-size justification or its assumptions. The illustration must not be interpreted as observed power or as proof that the study had adequate power. The numerical planning counts are not reported in the registry record. Any planning count in such an illustration would be a design calculation, not a participant count observed in the trial.

Which analysis details remain unknown?

The record identifies the primary population as per protocol but does not describe the criteria for inclusion in that population. It does not report an intention-to-treat analysis, how participants with missing endpoint data were handled, or whether sensitivity analyses were performed. It also does not report interim analyses, the detailed statistical analysis plan, or adjustment for multiple outcomes. These omissions limit reproducibility and prevent assessment of whether the analysis matched a prespecified plan.

The registry lists three outcome measures and two secondary outcomes, but the number of analyses is recorded as zero. That entry does not establish that no statistical analyses were performed; the registry record does not explain the entry. General statistical practice would distinguish the number of outcomes from the number of models or tests and would prespecify how multiple comparisons and missing data are handled. The record does not provide those details for this trial.

10. Confidence Intervals for Each Arm

No two-arm comparison is shown for this trial, but each arm's mean can be given with a t-based 95% confidence interval computed from the posted mean, spread and number of participants.

R code and output

arm <- c("Promotora for Physical Activity", "Carmen System")
n   <- c(114, 117)
m   <- c(134.8, 158.6)
sp  <- c(18, 20.1)
sd  <- sp * sqrt(n)      # standard errors converted to SDs
for (i in seq_along(n)) {
  se <- sd[i] / sqrt(n[i]); h <- qt(0.975, n[i] - 1) * se
  cat(sprintf("CARM|%s|%d|%.3f|%.3f|%.3f|%.3f\n", arm[i], n[i], m[i], sd[i], m[i] - h, m[i] + h))
}

CARM  Promotora for Physical Activity  114  134.800  192.187  99.139  170.461
CARM  Carmen System  117  158.600  217.415  118.789  198.411

11. Multiplicity, Missing Data and Analysis Populations

The registry record lists a primary outcome and two secondary outcomes: change in sedentary behavior and change in moderate to vigorous physical activity from baseline to 12 months. It also reports three outcome measures and records zero analyses. The record does not explain how the analysis count relates to the outcome listings. The estimates for the secondary outcomes are not reported in the registry record.

When several outcomes or statistical tests are examined, general statistical reasoning indicates that the chance of at least one apparently noteworthy finding can increase. A prespecified hierarchy, adjustment procedure or clear distinction between confirmatory and exploratory analyses can help readers interpret multiple results. The registry record does not report whether multiplicity was addressed, whether secondary outcomes had distinct analysis plans, or what role they played in the study’s conclusions.

The primary analysis population is labeled per protocol. The record does not define who was included in that population or report whether an intention-to-treat analysis was also conducted. It does not report the number of participants with endpoint data, losses to follow-up, reasons for missingness, imputation methods, or sensitivity analyses. The method for handling missing data is therefore not reported in the registry record.

These details are important in a non-inferiority study because different analysis populations and missing-data assumptions can influence the comparison. General explanation: missing outcomes can create bias when the likelihood of being observed is related to participants’ outcomes or intervention experience. Comparing analysis populations and testing plausible assumptions can help assess robustness. No such comparison or sensitivity analysis is reported in the registry record, so the robustness of the primary finding cannot be evaluated.

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.

Most frequent non-serious adverse event terms

The registry record lists serious adverse events affecting zero participants in each group and deaths affecting zero participants in each group. For other adverse events, the record lists four affected participants among 122 at risk in the promotora group and three among 123 at risk in the Carmen System group. These are the counts as recorded; the registry record does not provide event descriptions for the other events.

The distinction between serious and other adverse events should be retained when reading these figures. The serious-event counts are recorded separately from the other-event counts, and the record’s list of top serious event terms is empty. An empty list does not supply event details beyond the reported counts. The record does not describe how events were collected, the observation period for safety, their severity beyond the serious classification, or whether investigators judged them related to an intervention.

These counts are descriptive safety information, not an estimate of the effect on walking and not a test of non-inferiority. General statistical explanation: small event counts can be imprecise, and counts alone do not establish a causal relationship. The registry record does not report a comparative safety analysis or uncertainty intervals for these figures. They should therefore be read as posted event counts rather than as evidence that one intervention caused more or fewer events.

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

The record establishes that the trial compared a computer-based virtual advisor with weekly support from a human promotora, with the aim of encouraging regular walking among inactive midlife and older Latino adults. It specifies change in self-reported total weekly walking minutes from baseline to 12 months as the primary outcome and identifies the primary analysis as non-inferiority. It also notes a cluster-randomized design, making the handling of clustering central to the interpretation.

The record does not establish whether the virtual advisor was non-inferior, because it does not report the primary estimates, their uncertainty, the non-inferiority margin or the statistical decision. It also does not establish that either approach increased walking, or that one approach was superior. Those conclusions require outcome data and an interpretable analysis, neither of which is reported in the registry record.

General statistical explanation: absence of a reported difference is not proof that two approaches are equivalent. Equivalence and non-inferiority require prespecified margins and analyses that show the estimated contrast is sufficiently precise relative to those margins. A finding of no statistical significance in a superiority test would not answer the non-inferiority question on its own.

The completed status and enrollment of 245 describe the trial’s status and scale, not its efficacy result. The adverse-event counts describe recorded events, but they do not determine the walking outcome or establish causal safety differences. The secondary outcomes are named, but their estimates are not reported.

The interpretation is further limited by absent details about the clustering method, missing data, analysis populations beyond the per-protocol label, multiplicity and the original sample-size rationale. The appropriate conclusion is limited: the registry record describes the comparative objective and the planned outcome, but does not report enough numerical or methodological information to judge the clinical result or its precision.

14. Why This Trial Matters Statistically

This trial raises a useful statistical question about evaluating a computer-based approach against an active human-delivered intervention. Its stated objective was not simply to detect a difference, but to assess whether the virtual advisor was non-inferior to the promotora. That distinction changes what evidence is needed: the comparison requires an interpretable estimate, uncertainty and a prespecified margin, not merely a non-significant test of difference.

The cluster-randomized designation is also important. Participants treated within the same community or group may have correlated outcomes, so the analysis needs to reflect the unit and structure of randomization. The registry record explicitly cautions against a simple individual-level re-analysis. This makes transparent reporting of the cluster-aware method especially relevant to readers assessing precision.

The outcome has a direct connection to the study aim: change in weekly walking minutes, assessed with a self-report questionnaire. At the same time, a clear outcome definition does not substitute for reporting the estimates or the details needed to interpret them. The listed secondary measures broaden the activity-related outcomes, but the record does not provide their results or describe how multiple outcomes were handled.

Statistically, the record illustrates why registration details and numerical results serve different purposes. The design description identifies the intended comparison; the outcome definition clarifies what was measured; and the analysis results are needed to judge the size and precision of the comparison. Here, the first two are described, while the numerical primary result and key analysis details are not reported in the registry record. As a result, the stated non-inferiority question remains unanswered by the posted information.

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 most direct limitation is that the registry record does not report the primary outcome estimates or the statistical comparison. Without the mean changes, between-group estimate, confidence interval, p-value and non-inferiority margin, readers cannot assess the direction, size or precision of the primary finding. The completed status does not fill this gap.

Some design and analysis details are also absent. The record identifies the study as cluster-randomized but does not describe the clusters, their number, or the method used to account for clustering. It labels the trial single-masked without specifying who was masked. The randomization procedure and allocation concealment are not reported in the registry record.

The outcome is based on self-report using the CHAMPS Physical Activity Questionnaire. The registry record does not report questionnaire administration details, scoring rules, or whether other measurement methods were used. The primary population is described as per protocol, but its membership criteria and the handling of participants without 12-month outcome data are not reported. The record also does not provide participant flow or baseline characteristics.

The record names secondary outcomes but does not report their estimates or specify how multiplicity was handled. It does not describe the original sample-size justification, interim analyses, a detailed statistical analysis plan, or missing-data sensitivity analyses. These gaps limit the ability to reproduce the analysis or judge whether the findings are robust to different assumptions.

Finally, the safety listing gives counts but no event descriptions for the other adverse events, collection details, attribution assessment or comparative uncertainty. These limitations are specific to the information recorded and should not be read as evidence that the unreported procedures or analyses did not occur.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Virtual Advisors for Physical Activity Promotion in Underserved Communities — NCT02111213.
• Registry record last updated 2020-11-10; status last verified 2020-10.
• Results first posted 2019-10-18.
• 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

NCT02111213 is a completed randomized, single-masked, parallel-group study of a virtual advisor and a promotora intervention for physical activity. The record lists enrollment of 245 and describes weekly community-center sessions in both groups.

The primary outcome is change in total weekly walking minutes from baseline to 12 months, measured by self-report with the CHAMPS Physical Activity Questionnaire. The primary analysis is described as non-inferiority, and its population is labeled per protocol. The record also flags the study as cluster-randomized and cautions that individual-level re-analysis would be misleading.

The registry record does not report the primary estimates, non-inferiority margin, confidence interval, p-value or analysis details needed to interpret the comparison. It lists secondary outcomes but does not report their estimates. Safety counts include zero serious events and zero deaths in each group, with other-event counts of four and three.