New Jersey Healthcare Essential Worker Outreach and Education Study - Testing Overlooked Occupations: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for New Jersey Healthcare Essential Worker Outreach and Education Study - Testing Overlooked Occupations (NCT04766333), a non-randomized na study. The primary outcome is Number of Participants Who Complete COVID-19 Testing.

2. Clinical Question

3. Trial Design

NJ HEROES TOO is a parallel, non-randomized study of two behavioral outreach strategies. The record lists Healthcare Worker Focused Outreach Intervention Strategy and Community Organization Led Outreach. Allocation is recorded as non-randomized, and masking is recorded as none. This means the record does not describe randomized assignment or masking of participants and study personnel. The registry explicitly cautions that the arms are not a like-for-like control comparison.

The study is marked completed, with a start date of 2021-05-03 and a primary completion date of 2021-12-31. Enrollment is recorded as 2017. The phase is listed as NA. Rutgers, The State University of New Jersey, is the sponsor. These registry entries describe the study record, but they do not provide the way participants were recruited, the criteria for eligibility, or how outreach was delivered.

The stated primary outcome is a count: the number of participants who complete COVID-19 testing, described as participants who return their saliva testing kit. Its timeframe is 1 year. The registry record lists one outcome measure and one analysis, but the analysis method, analysis population, and arm-specific primary outcome results are not reported in the registry record.

The brief study summary describes a mixed methods evaluation of effectiveness and cost, comparing the outreach strategies and exploring contextual factors related to testing implementation and scalability. Specific qualitative methods, cost measures, and other implementation measures are not reported in the registry record. The design and summary therefore establish the broad comparison and its aims, but not enough methodological detail to reconstruct how the evaluation was conducted.

4. Participant Flow and Accounting

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

Before assignment: Some participants (n=917) chose not to participate in the questionnaire data collection and as a result were not assigned to a study arm after consent.

Overall Study

Reasons for not completing this period:

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 Who Complete COVID-19 Testing, measured over 1 year.

The primary endpoint is the number of participants who complete COVID-19 testing. The registry description operationalizes completion as returning a saliva testing kit, and specifies a timeframe of 1 year. This is a count outcome: it records how many participants experience the defined event. The event is kit return, rather than a stated measure of test positivity, infection, or a clinical outcome.

Using a concrete behavior as an endpoint can make an implementation question observable: it captures whether participants return the testing kit within the stated timeframe. The registry summary places the endpoint in a study of outreach approaches intended to support COVID-19 testing implementation. In general, a count can help describe the volume of an outcome, but its interpretation depends on the population and observation process. For a comparison between groups, the numbers eligible or observed in each group and the way follow-up is handled can matter. Those details for this endpoint are not reported in the registry record.

The record does not give the count of kit returns in either group, a denominator for either group, an effect estimate, or an uncertainty interval. It also does not say whether returning a kit required additional steps for the outcome to count as completed. Accordingly, the endpoint definition can be described, but the degree of difference between outreach strategies cannot be judged from the primary outcome information in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does a count outcome represent?

The primary endpoint is a count of participants who return a saliva testing kit. In general, a count records the number of occurrences of a defined event within an observation unit or group. Here, the event is kit return, and the stated observation period is 1 year. The record does not report the group-specific counts or the numbers of participants observed for this endpoint. Without those details, no rate, proportion, or between-group estimate can be described from the record.

General count-data methods can include models for counts, but the appropriate method depends on how observations are structured, how much variability is present, and what comparison is being estimated. The registry record does not state which statistical model or test was used. The outcome description alone is not enough to identify the analysis method. In particular, a count endpoint should not automatically be interpreted as a rate: a rate requires a defined exposure or observation basis, and the record does not report one for the primary comparison.

Why can non-randomized allocation complicate comparison?

In general, random allocation is used to make intervention groups comparable in expectation with respect to factors known and unknown at the time of assignment. In a non-randomized study, the process that determines which strategy is received may be related to participant, organization, or community characteristics. If those characteristics also relate to returning a testing kit, a crude contrast between groups may not isolate the outreach strategy's contribution.

The record explicitly notes that the arms are not a like-for-like control comparison. It does not describe the allocation process, baseline characteristics, or a covariate-adjustment plan. Consequently, readers cannot determine from the registry record which potential differences were measured or accounted for. Statistical adjustment can address measured covariates under its assumptions, but it cannot by itself guarantee comparability or remove the influence of unmeasured factors. No specific adjusted result is reported.

What does uncertainty mean for an estimated contrast?

In general, a confidence interval expresses the statistical uncertainty around an estimate under the assumptions of the method used. A relatively wide interval indicates that a range of effects is compatible with the data and method; a narrower interval indicates greater precision. An interval does not repair design limitations such as non-random allocation, and it does not describe every source of uncertainty. The registry record does not report a primary-outcome estimate or confidence interval, so precision cannot be assessed for the outreach comparison.

A significance test, in general, evaluates how compatible data are with a specified null hypothesis under the model and assumptions. A p-value is not the probability that the null hypothesis is true, nor does it measure the practical importance of an effect. The registry record lists one analysis but does not state the test, null hypothesis, test statistic, or p-value for the primary endpoint. No significance conclusion can therefore be drawn from the record.

Why can over-dispersion matter for counts?

In general, count data may vary more than a simple model assumes. This is called over-dispersion: the observed variability exceeds the model's expected variability. If a model does not account for such extra variability, standard errors and uncertainty intervals may be too small, making estimates appear more precise than warranted. Some count models allow for over-dispersion, while other approaches use robust variance estimates or different outcome formulations. These are general options, not a description of the analysis in this study; the registry record does not report whether over-dispersion was assessed or how it was handled.

What do the planning assumptions say?

The study metadata describes planning illustrations 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. The numerical planning outputs and the observed effect itself are not reported in the registry record. These assumptions describe a planning exercise, not observed power. In general, sample-size planning illustrates how a design might perform under specified assumptions; it does not establish how precise a completed study's estimate is, and it cannot substitute for reporting the outcome data and uncertainty.

The registry does not report the study's original sample-size justification, whether the planning illustration reflects the original design, or whether interim analyses were conducted. Those details cannot be inferred from the listed assumptions. The sponsor's own analysis would take precedence over simple unadjusted recalculations if a discrepancy were identified, but the registry record does not provide outcome summaries that would permit such a recalculation.

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("Healthcare Worker Focused Outreach Intervention St", "Community Organization Led Outreach")
n      <- c(63, 1037)
events <- c(23, 211)
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  Healthcare Worker Focused Outreach Intervention St  63  23  36.5  24.7  49.6  25.7  48.9  25.7  48.9
ARM  Community Organization Led Outreach  1037  211  20.3  17.9  22.9  18.0  22.9  18.0  22.9

11. Multiplicity, Missing Data and Analysis Populations

The registry record lists one outcome measure and one analysis. It does not report whether the primary endpoint was prespecified in a protocol or whether other analyses or outcomes were considered outside the listed record. A multiplicity procedure is not reported in the registry record.

In general, multiplicity arises when multiple outcomes, comparisons, subgroups, or repeated tests are examined. Conducting many tests can increase the chance of finding at least one apparently unusual result by chance. A prespecified analysis plan and an appropriate adjustment or interpretation strategy can help readers understand this issue. The available registry entries do not establish what approach, if any, was used.

Missing-data handling is not reported in the registry record. For a kit-return endpoint, the record does not explain how participants without a recorded return were handled, how follow-up completeness was assessed, or whether the outcome could be missing for reasons other than non-return. In general, these distinctions matter because an unobserved outcome is not necessarily the same as a confirmed absence of the event.

The analysis population is also not reported in the registry record. The record does not state whether the primary analysis included everyone enrolled, only participants eligible for a particular outreach strategy, or another defined group. It does not describe exclusions, protocol deviations, or the handling of participants whose group assignment or outcome status was uncertain. Without these details and the outcome results, readers cannot assess the analysis population or reproduce the primary comparison.

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 adverse-event record lists the Healthcare Worker Focused Outreach Intervention Strategy group with 23 at risk for serious adverse events and 0 affected; it lists 23 at risk for other adverse events and 0 affected. For Community Organization Led Outreach, it lists 211 at risk for serious adverse events and 0 affected, and 211 at risk for other adverse events and 0 affected. Deaths are recorded as 0 in each group. No top serious-event terms are listed.

These are the registry's safety figures, not evidence that adverse events were impossible or that every type of harm was assessed. In general, a zero recorded count means no event was recorded within the reporting scope and observation process represented in the record. It does not establish that the underlying risk is zero. The registry record does not describe safety surveillance, event definitions, the observation period for these safety counts, or the completeness of reporting. The at-risk counts shown for safety should not be treated as the primary-outcome group sizes, which are not reported in the registry record.

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

The record establishes that the study compared Healthcare Worker Focused Outreach with Community Organization Led Outreach in a completed, non-randomized, parallel study. It identifies return of a saliva testing kit within 1 year as the primary outcome and describes broader aims concerning effectiveness, cost, contextual factors, and scalability. It also records zero affected for the listed serious and other adverse-event categories, with the at-risk counts reported by group.

Those details do not establish the result of the primary comparison. Arm-specific kit-return counts, a contrast between strategies, and uncertainty around that contrast are not reported in the registry record. It is therefore not possible to say from the record whether kit return differed between the strategies, how large any difference was, or how precisely it was estimated. The absence of a reported result should not be interpreted as evidence of no difference.

The non-randomized design also limits causal interpretation. In general, differences between groups may reflect how participants or organizations came to receive each strategy as well as the outreach itself. The registry explicitly warns that the arms are not a like-for-like control comparison. The record does not give the allocation process or adjustment details needed to evaluate how measured group differences were handled.

The primary outcome is a behavioral implementation measure, not a measure of test positivity or a clinical outcome. The broader study aims do not amount to reported findings: cost results, contextual findings, and evidence about scalability are not reported in the registry record. The safety counts should likewise be read as recorded counts within an unspecified reporting scope, not as proof that no safety concerns could occur.

Overall, the registry record makes the study question and endpoint understandable, but it does not contain enough primary results or analysis detail to support a conclusion about comparative effectiveness, cost, or causal impact.

14. Why This Trial Matters Statistically

This study raises an important statistical issue in implementation research: an outreach strategy is evaluated through a behavior that can be counted, while the setting and pathway into each strategy may differ. The registry describes testing implementation and scalability as part of the study's purpose. Understanding how outreach relates to kit return requires attention not only to the event count but also to who was included, how groups were formed, and how outcomes were observed.

The non-randomized design makes the distinction between association and causal effect especially important. A group contrast may be informative about the observed settings, but without random assignment or sufficiently described adjustment, it cannot automatically be attributed to the outreach approach. The registry's own warning that the arms are not a like-for-like control comparison is therefore central to statistical interpretation.

The endpoint also illustrates why operational definitions matter. The primary measure is kit return, a concrete behavior within a stated timeframe. That definition helps specify what was counted, but does not itself convey the denominator, comparison estimate, uncertainty, or broader meaning of testing behavior. Complete reporting of counts and analysis details is necessary for readers to judge both the magnitude and precision of a comparison.

Finally, the registry's description of mixed methods, cost, contextual influences, and scalability signals that implementation questions extend beyond a single count. The record does not present those findings, so their relevance remains a stated motivation rather than a reported conclusion. The statistical lesson is to keep the study aim, observed measure, design, and available results distinct when interpreting a registry entry.

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 registry record does not report the primary outcome counts by intervention strategy, the number observed for that endpoint in each group, an effect estimate, or an interval. These omissions prevent assessment of the observed testing-completion contrast and its precision. The record also does not provide the statistical method or define the estimand, meaning the specific comparison the analysis was intended to quantify.

Allocation was non-randomized, and the registry states that the arms are not a like-for-like control comparison. Details of how the strategies were assigned or accessed, participant characteristics, organizational characteristics, and any adjustment for differences are not reported in the registry record. Masking is recorded as none, but the record does not explain the people involved or whether outcome ascertainment could be influenced by awareness of the strategy.

The endpoint definition is limited to returning a saliva testing kit. The record does not describe how return was verified, how follow-up was maintained, or how a missing return was distinguished from an unobserved outcome. Missing-data methods and analysis populations are not reported. No protocol, sample-size justification, interim analysis information, or detailed statistical plan is reported in the registry record.

The summary describes cost evaluation and exploration of contextual factors and scalability, but those measures and findings are not reported. The safety record gives event counts and at-risk counts, but does not describe event definitions, surveillance, or safety follow-up. These limitations are specific to the information available in the registry record; they do not establish that the study did not collect the missing details or data.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: New Jersey Healthcare Essential Worker Outreach and Education Study - Testing Overlooked Occupations — NCT04766333.
• Registry record last updated 2023-03-10; status last verified 2023-03.
• Results first posted 2023-03-10.
• 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

NJ HEROES TOO (New Jersey Healthcare Essential Worker Outreach and Education Study - Testing Overlooked Occupations), NCT04766333, is recorded as completed and sponsored by Rutgers, The State University of New Jersey. It is a parallel, non-randomized study with no masking, comparing Healthcare Worker Focused Outreach Intervention Strategy with Community Organization Led Outreach. Enrollment is recorded as 2017, and the phase is NA.

The primary outcome is the number of participants who return a saliva testing kit within 1 year. The registry summary describes evaluation of outreach effectiveness and cost, alongside exploration of contextual factors related to testing implementation and scalability. Primary-outcome results, analysis methods, missing-data handling, and analysis populations are not reported in the registry record. The record lists zero affected for serious and other adverse events in both groups, with the safety at-risk counts reported separately.