Microenterprise Intervention to Reduce Sexual Risk Behaviors in Young Adults: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Microenterprise Intervention to Reduce Sexual Risk Behaviors in Young Adults (NCT03766165), a randomized na study. The primary outcome is Proportion of Participants in Both Groups Who Have Responded to 70% or More of the Weekly Text Message Surveys.

2. Clinical Question

This question concerns whether participants could be reached and would respond to repeated surveys during the study. Survey response is relevant to the practical conduct of a feasibility trial because low response can limit the availability of outcome data. It is not, by itself, evidence that the intervention changed sexual risk behaviors. The registry lists sexual-behavior measures among the secondary outcomes, including reports of unprotected and safer sex acts over specified periods, but the primary outcome is survey response.

The posted primary results show 5.0 participants meeting the threshold in the intervention group and 9.0 in the control group. The group comparison is therefore about this response threshold, not about whether participants received every intervention component or whether the intervention altered health outcomes. The registry record does not report further detail about the operational definition of a completed weekly survey or the handling of participants with incomplete survey histories.

3. Trial Design

The study is listed as a completed, randomized, parallel-group behavioral trial with no masking. The registry record identifies Johns Hopkins Bloomberg School of Public Health as the sponsor and classifies the phase as NA. Enrollment was 38. The brief study description says the team planned to enroll approximately 40 young adults; the posted enrollment is the recorded figure, while the approximate target is part of the study description.

Participants were assigned to one of two groups. The control group received job-opening text messages. The intervention group received job announcements along with educational sessions, mentoring, behavioral economic text messages, and a start-up grant. The study summary further describes HIV-prevention and business educational sessions, a mentored apprenticeship, and a grant provided in 6 payments. The record does not report the randomization sequence, allocation concealment procedures, or whether assignment was stratified.

The study start date is 2018-12-05, and the primary completion date is 2019-08-19. The record lists the study status as completed. The primary outcome was measured at week 26 and counted participants in both groups who responded to 70% or more of the weekly text-message surveys.

This is described as a feasibility trial, and the stated focus is the feasibility of implementing an enhanced microenterprise intervention. The registry record lists 15 outcome measures and 13 posted secondary outcomes. Those secondary measures include intervention engagement, such as educational-session attendance, mentor contacts, and grant-payment spending, as well as reported sexual behavior. The record does not report a detailed protocol for the trial's original sample-size justification, its planned statistical analysis, or any interim analyses. Those omissions limit how fully the design and analysis decisions can be reconstructed from the registry record 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.

Overall Study

Analysis population for the primary outcome, as defined in the registry: Participants in both groups

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 Proportion of Participants in Both Groups Who Have Responded to 70% or More of the Weekly Text Message Surveys, measured over Measured at week 26.

The primary endpoint counts participants in both groups who responded to 70% or more of the weekly text-message surveys, measured at week 26. It is a binary classification at the participant level: each participant either meets the stated response threshold or does not. The reported group values are counts, not percentages or average numbers of completed surveys.

A threshold-based response measure can be useful in a feasibility study because it gives a direct indication of whether participants contributed survey data regularly enough to meet a prespecified participation standard. In general, survey response matters because incomplete follow-up can leave less information for assessing outcomes and can complicate comparisons between groups. The endpoint therefore addresses one practical aspect of running the study.

It does not measure the quality of the intervention, the amount of change in sexual behavior, or the success of any particular intervention component. Although the registry lists sexual-risk measures among secondary outcomes, the primary endpoint concerns survey participation. The record describes the endpoint's timing and threshold but does not report the detailed rules used to determine each participant's eligible surveys, how missed or undelivered messages were handled, or how incomplete records were classified. Those details would help interpret exactly what meeting the threshold required.

7. Results Posted in the Registry

• Intervention: 26.3% (5/19) versus 47.4% (9/19) on control; risk difference -21.1 percentage points (95% CI -51.0 to 8.9), risk ratio 0.56 (0.23–1.35); unadjusted two-proportion z-test p = 0.179.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is a participant-level binary measure: meeting or not meeting the threshold for response to 70% or more of weekly text-message surveys by week 26. A binary outcome can be summarized by counting how many participants in each group meet the definition. The registry reports 5.0 in the intervention group and 9.0 in the control group, with 19.0 participants in each group.

What does the risk difference describe?

In general, a risk difference subtracts the outcome proportion in one group from the outcome proportion in the other. It is an absolute comparison on the probability scale: a negative estimate for intervention relative to control means the observed outcome proportion is lower in the intervention group. Here, the reported estimate is negative. The interval around that estimate spans zero, so values representing no difference remain compatible with the reported interval. The record does not identify the confidence level used for the interval, so no confidence level should be inferred from the posted result.

How should the p-value be read?

The reported p-value is unadjusted and equals 0.179. In general, a p-value describes how unusual data at least as inconsistent with a specified null hypothesis would be if that hypothesis and the test's assumptions held. It is not the probability that the null hypothesis is true, and it does not measure the size or practical importance of an effect. The registry record does not report the test procedure, so the p-value should not be attributed to a particular statistical test beyond the posted unadjusted label.

What do the relative measures add?

The registry also reports a risk ratio and an odds ratio, each with an interval. A risk ratio compares the outcome proportions as a ratio; an odds ratio compares the odds. General interpretation depends on the scale: the risk difference describes an absolute gap, while the ratios describe relative contrasts. The posted ratio intervals include 1, the null value for a ratio comparison. These results do not indicate a precise relative effect. The record does not provide a rationale for choosing or emphasizing one effect scale over another.

For binary outcomes, the observed count and group size determine the observed proportion, but uncertainty depends on the amount of information and the analysis method. With a small number of participants, a few outcomes can materially affect the group estimates. The interval communicates this uncertainty more directly than a point estimate alone. It should not be read as a range containing every plausible individual outcome or as a guarantee about the result of a future study.

Why does the feasibility context matter?

Feasibility studies often examine whether recruitment, delivery, engagement, and measurement can be carried out, rather than provide a definitive estimate of a clinical outcome. Here, the primary endpoint concerns survey response, while the intervention involves multiple components. A group comparison in this setting can describe what happened in the enrolled participants, but it does not by itself identify which component might explain the observed result. The registry record does not report a component-specific analysis or a detailed causal analysis plan.

The trial is randomized, which describes how the groups were assigned, but randomization does not eliminate uncertainty in a small sample. Nor does the registry's description of random assignment provide enough detail to assess sequence generation, concealment, or implementation. Those procedures are not reported in the registry record. Masking is listed as none, so the record does not describe masked assignment or outcome assessment.

Finally, the registry lists 15 outcome measures and 13 posted secondary outcomes. Multiple outcomes can raise a multiplicity concern: when many comparisons are examined, the chance of at least one apparently notable result can increase. The record does not report a multiplicity adjustment or a hierarchy for interpreting secondary outcomes. It also does not report a detailed missing-data approach or analysis-population definitions. General statistical interpretation therefore needs to remain anchored to the specific posted endpoint and avoid treating unreported analysis choices as known.

10. Confidence Intervals and Precision

The risk-difference estimate is negative, and its reported interval extends from a negative value to a positive value, crossing zero. This means the interval includes values compatible with no absolute difference between groups. It also includes differences in either direction. The interval is therefore consistent with substantial uncertainty about the size and direction of the underlying contrast. The registry record does not identify the interval's confidence level.

For the risk ratio and odds ratio, the reported intervals include 1, the null value for ratio measures. This likewise indicates that the relative comparisons are not tightly distinguished from their null values by the posted intervals. Different effect measures use different scales, so the intervals should be interpreted using the appropriate null value: zero for a difference and 1 for a ratio.

Precision is limited by the amount of information in the comparison. There are 19.0 participants in each group, and the endpoint is based on whether each participant meets a threshold. With a small feasibility sample, estimates can be sensitive to a small number of participants. The interval is important because the point estimate alone would give an incomplete impression of what the data can support.

An interval does not show the probability that the true effect lies within its bounds, and it does not establish that all effects inside the interval are equally plausible. It is a measure of uncertainty under the statistical procedure used. The registry record does not report the interval method or confidence level, so those details cannot be assessed from the posted record. The posted uncertainty supports a cautious description of the observed group contrast, rather than a definitive conclusion about an underlying effect.

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. They are illustrative calculations based on the observed effect, rather than a record of the original trial's design justification. The calculation assumptions listed are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set to the stated fraction of the observed effect. The trial's own original design assumptions are not reported in the registry record.

The 80% power column gives the number of participants per arm in the planning illustration for a design with 80% power under those assumptions. In general, power is the chance that a study will detect an effect of the specified size using the specified analysis, if that effect is present and the assumptions hold. The 90% power column gives the corresponding per-arm planning figure for 90% power. These are design calculations, not evidence about the probability that this completed trial's result is correct.

The rows consider planning for 100%, 75%, and 50% of the observed effect. For 100% of the observed effect, the figures are 82 participants per arm for 80% power and 109 for 90% power. For 75% of the observed effect, they are 150 and 200 participants per arm, respectively. For 50% of the observed effect, they are 345 and 461 participants per arm, respectively. The pattern illustrates the general principle that smaller effects require more participants to detect, all else equal.

This is not observed power. The figures do not change the observed result, establish what the original study was designed to detect, or imply that the study failed or succeeded at a design target. The original sample-size justification is not reported in the registry record.

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, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.474; treatment proportion p₁ = 0.263; average p̄ = 0.368.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6822 = 1.3371.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.6657 = 0.5603.
4. n = (1.3371 + 0.5603)² / (-0.2105)² = 81.2, rounded up to 82 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
p0 <- 0.473684210526316                          # control proportion
p1 <- 0.263157894736842                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^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 (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(3766165)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 82 (80% power), 109 (90% power)
 75% of observed effect: n per arm = 150 (80% power), 200 (90% power)
 50% of observed effect: n per arm = 345 (80% power), 461 (90% power)
power.prop.test: 81.2 
Simulated power at n = 82 per arm: 0.798 (20000 replicates)

The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-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 lists 15 outcome measures and 13 posted secondary outcomes. These include measures of intervention reach and engagement, such as receiving informational text messages, responding to surveys, attending educational sessions, having mentor contacts, and spending grant payments. They also include reports of unprotected sex and safer sex over specified periods. Considering multiple outcomes creates a multiplicity issue in general: if many hypotheses are tested, some results may appear notable by chance even when there is no underlying effect.

The registry record does not report a multiplicity adjustment, a prespecified hierarchy for outcomes, or a strategy for prioritizing secondary comparisons. The primary outcome is identified, but the record does not provide enough detail to determine how secondary analyses were intended to inform conclusions. The analysis count is listed as 0, while primary group values and a comparison are posted. This makes it important to distinguish the recorded outcome information from an undocumented analysis plan; it does not justify guessing what analyses were planned or performed.

Missing-data methods are not reported in the registry record. This matters particularly for a survey-response endpoint: some participants may have incomplete survey records, but the posted result does not explain how missing or undelivered surveys were treated when determining whether the 70% threshold was met. The record also does not report whether imputation, complete-case analysis, or another approach was used. None should be assumed.

Analysis populations are likewise not reported in the registry record. The posted results give group sizes of 19.0 each, but they do not specify whether the comparison used all randomized participants, participants with available endpoint information, or another defined population. The record does not report an adjusted analysis or covariates. These omissions limit assessment of how missing information and analysis-set choices may have affected the estimate, and they argue for treating the posted group comparison as a descriptive result with uncertainty.

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 list 19 participants at risk in each group. There were 0 serious events affecting participants in the intervention group and 0 in the control group. The figures also list 0 other adverse events affecting participants in either group, and 0 deaths in each group. No serious-event terms are listed.

These counts describe what the registry reports; they do not establish that no adverse events occurred outside the categories or reporting periods captured in the record. The registry record does not report further detail about safety-event definitions, collection procedures, follow-up duration for safety, or how events were assessed. Zero reported events in a small feasibility study should therefore be read as a description of the posted record, not as proof that an intervention has no safety risks.

The two groups each have 19 participants at risk in the safety summary. The record does not provide enough detail to assess whether safety monitoring was comparable in duration or completeness across groups. The absence of listed serious-event terms reflects the empty term list in the registry record and should not be expanded into claims about unreported events or specific causes.

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

The result shows that 5.0 participants in the intervention group and 9.0 in the control group met the survey-response threshold at week 26, among 19.0 participants in each group in the posted primary results. The estimated risk difference is negative for intervention relative to control, but its interval crosses zero, and the unadjusted p-value is 0.179. These findings describe an observed contrast with substantial uncertainty; they do not establish a definitive underlying group difference or equivalence.

The outcome is about repeated survey response, not sexual behavior. It cannot be used on its own to claim that the intervention increased or reduced unprotected sex, safer sex, HIV risk, or other health outcomes. Nor does the primary result determine whether participants attended sessions, interacted with mentors, spent grant payments, or benefited from a particular intervention component. Those are separate feasibility or behavioral measures.

Random assignment is part of the recorded design, but details of randomization and the analysis populations are not reported in the registry record. The small group sizes and the width of the uncertainty around the comparison constrain how confidently the result can be generalized beyond these participants. The record also does not report the missing-data approach, an adjusted analysis, or a multiplicity strategy for the many listed outcome measures.

The findings are best understood as a feasibility-trial observation about survey participation. They may inform questions about data collection and engagement in a future study, but the registry record does not provide a basis for concluding that the intervention is effective or ineffective. It also does not report the original sample-size justification, so the planning illustrations should not be mistaken for the trial's intended target or used to infer observed power.

16. Why This Trial Matters Statistically

This trial illustrates why outcome definition matters in a feasibility study. The primary endpoint is not a clinical event or a sexual-risk measure; it is the number of participants who meet a survey-response threshold. That makes the result relevant to the practical question of whether repeated text-message surveys generated sufficient participant response, while keeping it separate from claims about changes in behavior.

The comparison also shows the value of reading a point estimate alongside its interval. The observed counts differ between groups, but the risk-difference interval crosses zero, the ratio intervals include their null values, and the unadjusted p-value is 0.179. Reporting the direction of the point estimate without its uncertainty would overstate what can be learned from the comparison. Conversely, uncertainty does not prove that there is no difference.

With 19.0 participants per group, the study's results are also a reminder that estimates from feasibility trials can be imprecise. The sample-size illustrations demonstrate, under their stated planning assumptions, how requirements rise when targeting smaller effects. They are planning examples based on the observed effect, not a substitute for the original design rationale, which is not reported in the registry record.

Finally, the trial has multiple intervention components and a range of secondary measures. Without reported analysis populations, missing-data methods, or a multiplicity strategy, a reader cannot fully assess how those choices shape the secondary findings. Statistically, the key contribution of the posted primary result is therefore a carefully bounded description of response to surveys, together with an explicit acknowledgment of uncertainty and reporting gaps.

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 primary comparison is based on 19.0 participants per group, limiting the amount of information available for estimating differences. The interval around the risk difference crosses zero, and the relative-effect intervals include their null values. The result is therefore imprecise and should not be treated as a definitive estimate of the group contrast.

The endpoint reflects survey participation, not the sexual-risk outcomes named among the secondary measures. The registry record does not report detailed rules for determining which surveys counted toward the 70% threshold or how missing surveys were classified. It also does not report the missing-data strategy or analysis populations, making it difficult to assess the effect of incomplete response on the comparison.

The intervention contains several elements, including educational sessions, mentoring, text messages, and a start-up grant. The primary group comparison does not isolate the contribution of any one component. Further, the registry describes no masking, and details of random sequence generation, allocation concealment, and outcome assessment are not reported in the registry record.

The record lists multiple outcome measures but does not report a multiplicity plan, a detailed statistical analysis plan, or the original sample-size justification. The posted planning illustrations use the observed effect and stated assumptions, and they cannot establish the intended design target. Finally, the registry record does not provide further detail about the population's characteristics, which limits assessment of how representative the enrolled participants were of other young adults.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Microenterprise Intervention to Reduce Sexual Risk Behaviors in Young Adults — NCT03766165.
• Registry record last updated 2020-10-22; status last verified 2020-09.
• Results first posted 2020-10-22.
• 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

NCT03766165 is a completed, randomized, parallel-group behavioral feasibility trial titled “Microenterprise Intervention to Reduce Sexual Risk Behaviors in Young Adults.” The sponsor is Johns Hopkins Bloomberg School of Public Health. The record lists 38 participants enrolled, no masking, and a phase classification of NA. The study start date is 2018-12-05, and the primary completion date is 2019-08-19.

The intervention combined job announcements with educational sessions, mentoring, behavioral economic text messages, and a start-up grant; the control group received job announcements only. The primary outcome counted participants who responded to 70% or more of weekly text-message surveys at week 26. The posted counts are 5.0 in the intervention group and 9.0 in the control group, with 19.0 participants in each group. The risk-difference interval crosses zero, and the unadjusted p-value is 0.179.

The registry lists 15 outcome measures and 13 posted secondary outcomes. The original sample-size justification, detailed analysis plan, missing-data methods, and analysis populations are not reported in the registry record.