Home-based Delivery of the Contraceptive Implant in Postpartum Guatemalan Women: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Home-based Delivery of the Contraceptive Implant in Postpartum Guatemalan Women (NCT04005391), a randomized na study. The primary outcome is Number of Participants With Implant Use at Three Months.

2. Clinical Question

The trial asks whether offering contraceptive methods during a home postpartum visit is associated with greater postpartum contraceptive uptake than routine postpartum care. Its central outcome is implant use at three months after childbirth. The broader question is whether bringing contraceptive options, including an implant, to women in their homes changes access and use in communities served by a community-based nursing program.

The registry description frames access as a practical barrier: travel, time, and cost may make contraceptive methods harder to obtain. The intervention tests a service-delivery approach rather than a comparison between different implant products. The record also lists contraceptive use at three months and satisfaction, continuation, and repeat pregnancy at twelve months as secondary outcomes. Results for these outcomes are not reported in the registry record, so the clinical question can be described, but the size and precision of any observed difference cannot be assessed.

3. Trial Design

This was a randomized, parallel, cluster-randomized trial in rural Guatemala. Communities, rather than individual women, were assigned to intervention or control conditions. The intervention clusters received an offer of participant’s choice of contraception during a home postpartum visit, while control clusters received routine postpartum care. The registry record lists the allocation as randomized and masking as none. It describes the study as completed, with a start date of 2018-10-23 and a primary completion date of 2020-02-19.

The intervention was integrated into a community-based nursing program. Nurses visited women for the postpartum visit, provided routine clinical care, and then offered contraceptive options at home in intervention clusters. The options listed were condoms, birth control pills, an injectable method, and the contraceptive implant. The record says implants had previously been available only in the closest town, about an hour away by vehicle, and that community nurses were trained to place them. Control clusters received routine postpartum care.

Cluster assignment can reduce the risk that an intervention offered within a community spills over to women assigned to a different condition. It also affects statistical analysis: outcomes among women in the same community may be more alike than outcomes among women from different communities. Analyses generally need to account for this clustering to avoid treating all participants as fully independent observations. The number of clusters, the assignment procedure, and the details of any cluster-adjusted analysis are not reported in the registry record.

The registry record lists an enrollment of 208. Its adverse-event entries give 101 participants at risk in the intervention group and 100 in the control group; the relationship between those entries and the enrollment figure is not explained in the registry record. The record does not report the number of communities, participant flow by arm, or the number included in each outcome analysis. Those omissions limit the ability to reconstruct how the enrolled population contributed to the reported outcomes, which themselves are not posted.

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 Number of Participants With Implant Use at Three Months, measured over Three months.

The primary endpoint is the number of participants with implant use at three months. It is a binary outcome at the participant level: each participant either has implant use recorded for the specified follow-up or does not. The registry labels the measure as a count of participants and gives the timeframe as three months.

This endpoint focuses on uptake of the implant, rather than use of any contraceptive method. That distinction matters because the intervention offered several methods, while the primary outcome isolates one of them. Implant use may therefore describe one aspect of the intervention’s effect on access and choice, but it does not by itself capture all postpartum contraceptive use. The registry record separately lists any contraceptive use at three months as a secondary outcome.

A count can describe how many participants experienced the outcome, but a comparison between trial groups also needs the corresponding group denominators and a suitable analysis. For a cluster-randomized study, the analysis should account for community assignment. The primary outcome’s arm-specific counts, denominators, comparative effect estimate, uncertainty interval, and p-value are not reported in the registry record. Consequently, the endpoint is defined, but its observed frequency and the precision of a group comparison cannot be evaluated from the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry identifies a cluster-randomized trial and names the primary endpoint, but it does not report a sponsor analysis or statistical methods for estimating the primary comparison. The general explanations below describe concepts relevant to this design; they should not be read as a claim about methods actually used by the trial team.

Why does cluster randomization matter?

In an individually randomized trial, assignment occurs separately for each participant. In a cluster-randomized trial, groups such as communities are assigned together. Participants in the same cluster may have shared access to services, local practices, or other contextual influences, so their outcomes may be correlated. When this within-cluster similarity is not accounted for, treating every participant as independent can make the estimated uncertainty too small. Appropriate analysis usually incorporates the cluster structure, using methods suited to the outcome and design.

For this trial, the registry says communities were randomized and explicitly cautions that a simple individual-level re-analysis would be misleading. The number of randomized communities, the method used to account for clustering, and the estimated degree of within-community correlation are not reported in the registry record. The sponsor’s own analysis is intended to take precedence over a simple recalculation for this design, but the analysis itself is not reported in the registry record.

What does a binary endpoint mean?

The primary outcome counts participants with implant use at three months. A binary outcome records whether each participant met the outcome definition. Group counts can be expressed as proportions when denominators are available, and a comparison can be reported using a measure such as a difference in proportions or a relative measure. General statistical principle: the choice of effect measure should match the scientific question and the analysis design. The registry record does not provide the outcome counts, denominators for the primary outcome, or a comparative effect estimate, so no such measure can be interpreted.

How should uncertainty be understood?

A confidence interval describes a range of values compatible with the data under the statistical model and its assumptions. A narrower interval indicates greater precision; a wider interval indicates greater uncertainty. A p-value addresses how compatible the observed data are with a specified null hypothesis under the analysis assumptions, but it is not a measure of effect size or clinical importance. Neither a confidence interval nor a p-value for the primary comparison is reported in the registry record. Without these results, the precision and statistical evidence for a group difference cannot be assessed.

What is over-dispersion, and why might it matter?

General statistical principle: a model may be over-dispersed when observed variation is greater than the model expects. This can arise when outcomes are more heterogeneous or correlated than the model allows. If over-dispersion is not addressed, standard errors and uncertainty intervals can be misleading. In a cluster trial, dependence among participants is one reason that a model’s assumptions about variation need careful consideration. Whether the trial analysis assessed or adjusted for over-dispersion is not reported in the registry record.

What do the planning assumptions say?

The registry 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. Such planning figures are illustrative calculations, not observed power and not necessarily the trial’s own design justification. The sample-size justification and the actual planning calculations are not reported in the registry record. Since the outcome results and observed effect are also not reported, a reader cannot assess how those assumptions relate to the trial’s findings.

What analysis details remain unknown?

The registry record lists 0 analyses. It does not report the model, covariates, handling of cluster size, missing-outcome approach, analysis population, or treatment of protocol deviations. Interim analyses and the prespecified statistical analysis plan are not reported in the registry record. These details matter because analysis choices can affect estimates and uncertainty, particularly in a cluster-randomized study. The absence of these details does not show that no such procedures existed; it means they are not reported in the registry record.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Postpartum Contraceptives Offered to Intervention ", "Routine Care Offered to Control Clusters")
n      <- c(101, 100)
events <- c(28, 2)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Postpartum Contraceptives Offered to Intervention   101  28  27.7  19.3  37.5  19.9  37.1  19.9  37.2
ARM  Routine Care Offered to Control Clusters  100  2  2.0  0.2  7.0  0.6  7.0  0.6  7.0

11. Multiplicity, Missing Data and Analysis Populations

The registry lists one primary outcome and four secondary outcomes. It does not report whether the statistical plan specified a hierarchy among them, adjusted for multiple comparisons, or treated secondary analyses as exploratory. When several outcomes are tested, the chance of at least one apparently notable result can increase. General statistical principle: a prespecified multiplicity strategy helps readers understand how to interpret a family of comparisons. The registry record does not report such a strategy, and no outcome-specific statistical results are posted.

Missing-data procedures are also not reported in the registry record. There is no account of how many participants completed each follow-up, whether outcome information was unavailable, or how missing values were handled. The record does not describe an intention-to-treat, per-protocol, or other analysis population. It also does not report participant flow by randomized group, so the relation between enrollment and the population contributing to each outcome cannot be evaluated.

These omissions are especially relevant because the trial randomized communities. The registry record does not state whether the analysis included all randomized clusters, how participants who moved or missed follow-up were handled, or whether cluster-level losses occurred. Without those details, readers cannot assess the potential impact of missingness or determine whether the analysis preserved the randomized comparison.

The record lists 0 analyses, so no sponsor analysis or adjustment strategy is available to review. This does not prove that analyses or plans were not conducted; they are simply not reported in the registry record. Interpretation of all listed outcomes is therefore constrained by the absence of results, analysis populations, and missing-data information.

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.

The registry’s adverse-event entries list 0 serious events and 0 other events for the intervention group, with 101 participants at risk. The control group entries list 0 serious events and 0 other events, with 100 participants at risk. Deaths are listed as 0 in both groups, and no top serious-event terms are listed.

These entries describe what the registry record reports; they do not provide a detailed safety analysis. The record does not explain the adverse-event collection methods, observation window, event definitions, or how events were assessed. It also does not state whether all participants were followed for safety throughout the same period. A recorded 0 is not equivalent to proof that an event could not occur, and it cannot establish that the groups had identical safety experience.

The at-risk counts in the adverse-event entries should not be assumed to be the denominators for the primary endpoint. The registry gives separate enrollment and adverse-event figures, and does not explain their relationship. These safety entries therefore cannot be used to infer implant use, contraceptive uptake, or the comparative effectiveness of the service-delivery approach.

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

The registry record describes a cluster-randomized evaluation of offering contraceptive options during a home postpartum visit in rural Guatemala. The intervention combined routine care with an offer of participant’s choice among several contraceptive methods, including an implant. The control condition was routine postpartum care. The primary outcome was implant use at three months, with additional outcomes listed for contraceptive use at three months and satisfaction, continuation, and repeat pregnancy at twelve months.

What the posted record does not show is the result for any of those outcomes. It does not report the number of participants with implant use in either group, a comparison between groups, or an estimate with an uncertainty interval. Therefore, it does not allow readers to determine whether implant use was more frequent in one group, how large any difference might have been, or how precisely it was estimated. Missing results should not be interpreted as a null result.

The study’s setting and intervention may be relevant to questions about delivery of postpartum contraception through community nursing. The record’s rationale describes travel, time, and cost as access barriers, and notes that implants had been available in a nearby town about an hour away by vehicle. These details explain the service-delivery question; they are not evidence that the intervention changed uptake or improved any health outcome.

The completed status and listed completion date do not resolve the absence of results. Nor do the adverse-event counts answer the primary efficacy question. The safety entries record 0 serious events, 0 other events, and 0 deaths in both groups, but do not establish the completeness of safety ascertainment or provide a comparison of contraceptive outcomes.

The appropriate reading is limited: the registry specifies a relevant question and trial design, but the reported information is insufficient to assess the observed primary effect or secondary outcomes. Findings should not be inferred from the intervention description, enrollment, or planning assumptions.

14. Why This Trial Matters Statistically

This trial is statistically notable because assignment occurred by community while the primary outcome was measured for individual participants. That design makes the connection between the unit of randomization and the unit of outcome analysis important. General statistical principle: outcomes within a community may be correlated, so methods need to account for clustering when estimating uncertainty. The registry itself warns that a simple individual-level re-analysis would be misleading.

The trial also illustrates the difference between a clearly specified outcome and a reported result. The primary endpoint is named as implant use at three months, but the record does not give the outcome counts or comparative analysis. An endpoint definition tells readers what was meant to be measured; it does not reveal what was observed. Without effect estimates and uncertainty, the size and precision of any group difference remain unknown.

There is a further distinction between the primary endpoint and the wider intervention question. The intervention offered multiple contraceptive methods, while the primary endpoint isolates implant use. The registry lists any contraceptive use separately as a secondary outcome. In general, looking at both can help distinguish uptake of a particular method from uptake of contraception overall, but no results for either measure are reported in the registry record.

Finally, the record describes planning assumptions based on an observed effect, but does not report a statistical analysis or the observed outcome estimate. Planning illustrations should not be confused with evidence from the trial. The record’s missing analyses, results, and design details make this a useful example of why outcome definitions, cluster-aware methods, and transparent reporting all matter for interpreting randomized evidence.

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 main limitation for interpreting this trial record is the absence of posted outcome results. The primary endpoint is named, but arm-specific counts, denominators, effect estimates, confidence intervals, and p-values are not reported in the registry record. Secondary outcomes are listed without results. The size, direction, and precision of the findings therefore cannot be assessed.

Important design details are also missing. The number of communities, the number assigned to each condition, the randomization procedure, and the handling of differences in cluster size are not reported in the registry record. Although the record identifies a cluster-randomized design and cautions against simple individual-level re-analysis, it does not describe the sponsor’s statistical model or show its output.

Participant accounting is unclear from the posted information. The record lists an enrollment of 208, while the adverse-event entries give 101 participants at risk in the intervention group and 100 in the control group. The record does not explain how these figures relate, and it does not provide outcome-specific denominators or participant flow. Follow-up completion, missing data, and analysis populations are not reported in the registry record.

The registry also does not report details of outcome ascertainment, the statistical analysis plan, any interim analyses, multiplicity handling, or the sample-size justification. The safety entries lack descriptions of collection methods and observation periods. These limitations do not establish that the trial lacked such procedures; they indicate that the registry record does not report them. Together, the omissions prevent a full assessment of potential bias, analytic assumptions, and the reliability of any treatment comparison.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Home-based Delivery of the Contraceptive Implant in Postpartum Guatemalan Women — NCT04005391.
• Registry record last updated 2021-07-02; status last verified 2021-06.
• Results first posted 2020-11-24.
• 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.

19. Record Summary

The registry record describes NCT04005391, a completed, randomized, parallel, cluster-randomized trial of home-based postpartum contraceptive provision in rural Guatemala. The intervention clusters received an offer of participant’s choice of contraception during the routine forty day postpartum visit after routine care; control clusters received routine postpartum care. The record lists enrollment of 208 and identifies implant use at three months as the primary outcome.

Secondary outcomes include any contraceptive use at three months, satisfaction and continuation at twelve months, and repeat pregnancy at twelve months. The record lists 0 analyses and does not report primary or secondary outcome results, comparative estimates, or statistical uncertainty. Adverse-event entries report 0 serious events, 0 other events, and 0 deaths in both groups, with 101 and 100 participants at risk, respectively. These entries do not replace outcome results or provide a complete safety assessment.