Implementation of Innovative Food Prescription Programs in Older Adults: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Implementation of Innovative Food Prescription Programs in Older Adults (NCT06324630), a randomized na study. The primary outcome is Average Percentage of Prescriptions Redeemed.

2. Clinical Question

3. Trial Design

The registry describes a randomized, parallel study with three programs: Produce Prescription Mobile Market, Produce Prescription Delivery, and Healthy Meal Kit Delivery. Masking is listed as none. The registry records an enrollment of 168 and lists the study as completed. The recorded start date is 2024-09-09, and the primary completion date is 2025-02-17.

The programs were intended to address food access for older adults. In the mobile market program, a clinician prescribed funds for fruit and vegetables from designated mobile market providers. The produce delivery program sent a customizable box to the participant’s home, with a regular box described as the alternative when a participant did not select produce. The meal kit program delivered ingredients for meals and offered weekly meal choices. The registry describes weekly food distribution over a 12-week intervention.

The primary result summaries list 22 participants for the mobile market program, 22 for produce delivery, and 23 for meal kit delivery. The registry does not explain how these arm-summary counts relate to the enrollment figure, or describe a participant flow from enrollment through outcome analysis. The reason for the location or program choice is described in the study summary, but detailed site-selection procedures are not reported in the registry record.

The registry record does not report the allocation ratio, details of sequence generation or concealment, or the trial’s original sample-size assumptions. It identifies the study phase as not applicable. The posted design allows comparison of the three program groups, but the listed analysis does not establish whether randomization or outcome collection worked as intended in every case.

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: 168 eligible individuals were targeted for enrollment. Of 144 individuals contacted via opt-out letter, 3 opted out of being contacted by researchers. An additional 24 individuals were recruited directly via the clinic. Of these 165 participants, 39 were unreachable for recruitment and 26 declined to participate prior to randomization. One individual was paired with a spouse to participate, yielding 101 individuals contacted for enrollment. Of those contacted, 67 were enrolled.

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 Average Percentage of Prescriptions Redeemed, measured over Average over the 12-week intervention.

The primary endpoint is the average percentage of prescriptions redeemed, expressed as a percentage of the program redeemed. It is described as the average over the 12-week intervention. Redemption was measured weekly: participants were asked to confirm receipt of a delivery or redemption of a prescription through a usage survey. The registry says that automatic notifications followed deliveries, or were sent weekly for the mobile market program, with two reminder notifications if a participant did not initially confirm.

This endpoint captures engagement with the food program: whether participants confirmed that they received the delivery or used the prescription. It is not a direct measure of how much food participants ate, the nutritional quality of their overall diet, or a health outcome. The registry lists average fruit and vegetable use as a separate secondary outcome, which addresses food use rather than redemption.

Using a percentage across the intervention period gives a summary of repeated weekly program use. The definition depends on confirmation in the usage survey, however, so the endpoint represents confirmed redemption under the registry’s measurement approach. The registry does not report how unconfirmed weeks were classified or how missing confirmation data were handled. Those details matter when interpreting what a reported average represents.

7. Results Posted in the Registry

• Produce Prescription Delivery: mean 89.20 versus 28.30 on control; difference 60.90 (95% CI 59.03 to 62.77), standardized effect d = 19.27; z-test p = <0.001.
• Healthy Meal Kit Delivery: mean 89.20 versus 28.30 on control; difference 60.90 (95% CI 59.08 to 62.72), standardized effect d = 19.60; z-test p = <0.001.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Average Percentage of Fruit and Vegetables Used

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • Produce Prescription Delivery: mean 75.70 versus 24.90 on control; difference 50.80 (95% CI 35.95 to 65.65), standardized effect d = 2.02; z-test p = <0.001.
  • Healthy Meal Kit Delivery: mean 77.70 versus 24.90 on control; difference 52.80 (95% CI 38.31 to 67.29), standardized effect d = 2.13; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Produce Prescription Delivery than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Healthy Meal Kit Delivery than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The secondary results that are numerically described include average percentage of fruit and vegetables used. The group averages are higher for both delivery programs than for the mobile market program, a general pattern that aligns with the direction of the primary redemption result. The outcomes nevertheless measure different things: redemption concerns confirmation of program use, while the secondary measure concerns reported use of the food.

The registry also lists eligible participants who were interested in the program and the percentage of eligible participants enrolled as secondary outcomes. Numerical results for these outcomes are not reported in the registry record, so they cannot be used to judge reach, interest, or recruitment performance from the posted results.

The sponsor-reported analysis for average food use is an ANOVA across the three groups, with p <0.001. Unadjusted recalculations compare each delivery group with the mobile market group. These results add context to the primary outcome, but they do not establish that greater redemption caused greater food use, or that either measure led to broader dietary or health changes.

Secondary outcomes generally carry less weight than a prespecified primary outcome when there are multiple outcomes and tests, especially when no adjustment strategy is reported. Each additional analysis creates another opportunity for a chance finding. The registry does not report a multiplicity plan or identify which secondary results were confirmatory. The secondary pattern is therefore best regarded as supportive descriptive context rather than independent confirmation of the primary comparison.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Average Percentage of Fruit and Vegetables Used
• Eligible Participants Who Were Interested in the Program
• Percent of Eligible Participants Enrolled

9. Statistical Interpretation

10. Statistical Methods Explained

The registry identifies the primary outcome as a continuous measure summarized by a mean and standard deviation. A mean describes the average observed value in a group. A standard deviation describes how dispersed individual values are around that group average; it is not the uncertainty interval around the mean and does not indicate the range of every participant’s value.

The reported sponsor analysis uses ANOVA across all three groups and gives p < 0.001. In general, ANOVA tests whether the observed group means are consistent with a common mean, given the model’s assumptions. A small p-value indicates that the observed pattern would be unusual under that common-mean model. It does not quantify the size or practical importance of a difference, and an overall ANOVA result is not a set of separate pairwise tests. Model details, including any covariates or assumption checks, are not reported in the registry record.

The posted recalculations compare each delivery group with the mobile market group using unadjusted mean differences. These are simple comparisons based on the posted group summaries, rather than an adjusted analysis from individual-level data. The recalculated mean difference is 60.9 for Produce Prescription Delivery versus Produce Prescription Mobile Market, with an interval from 59.03 to 62.77. For Healthy Meal Kit Delivery versus Produce Prescription Mobile Market, the recalculated mean difference is also 60.9, with an interval from 59.08 to 62.72. The recalculated p-value is <0.001 for each comparison.

In general, a confidence interval describes a range of values compatible with the data and the assumptions used in the calculation. The width reflects precision: narrower intervals indicate less statistical uncertainty under those assumptions. These recalculated intervals are not reported as sponsor-produced pairwise intervals. The confidence level for the intervals is not reported in the registry record. No adjustment for multiple pairwise comparisons is indicated for the recalculations, so their p-values should be treated as unadjusted.

What does over-dispersion mean?

In general, over-dispersion occurs when observed variability is greater than a statistical model expects. A model that understates variability can make estimates look more precise than they are and can affect tests of statistical significance. The posted summary reports standard deviations for the continuous outcomes, but it does not describe an over-dispersion assessment or a model that specifically addresses it. This general concern is not evidence that over-dispersion occurred in this study.

How should repeated weekly measurements be understood?

The primary outcome is described as an average over weekly redemption measurements during the 12-week intervention. Repeated measurements on the same participant may be related rather than independent. In general, analyses of repeated observations need to account for that dependence if they use the weekly records directly. The registry does not report whether the sponsor analyzed weekly observations individually, first summarized them for each participant, or used another approach. The recalculations use the posted arm-level summaries and cannot resolve that question.

The secondary continuous outcome, average percentage of fruit and vegetables used, is also summarized by arm mean and standard deviation. The registry reports an ANOVA across the three groups with p <0.001 for that outcome. Pairwise recalculations are separately described in the posted results, but they are unadjusted. In general, analyses of multiple outcomes and comparisons increase the chance of finding at least one small p-value by chance if no multiplicity approach is used. The registry does not report a multiplicity plan.

For planning illustrations, the stated assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, a normal approximation, and an effect to detect set to a stated fraction of the observed effect. These assumptions apply to the illustrative calculations, not necessarily to the trial’s design or sponsor analysis. The original design assumptions are not reported in the registry record. The illustrations are planning calculations based on observed results, not evidence about the trial’s power before it began.

11. Confidence Intervals and Precision

The recalculated comparisons for the primary outcome show a mean difference of 60.9 percentage points for each delivery program versus the mobile market program. The interval for Produce Prescription Delivery versus Produce Prescription Mobile Market runs from 59.03 to 62.77; for Healthy Meal Kit Delivery versus Produce Prescription Mobile Market, it runs from 59.08 to 62.72. These are unadjusted recalculations from the posted summary statistics.

In general, a confidence interval conveys uncertainty around an estimated effect: the interval gives a range of values compatible with the data under the method’s assumptions. A narrower interval indicates greater precision than a wider interval, but it does not rule out bias, limitations in measurement, or differences between this study setting and other settings. The confidence level and the procedure used for the sponsor’s overall ANOVA are not reported in the registry record. The intervals should therefore be understood as recalculated summaries, not as a full account of uncertainty from the sponsor’s analysis.

The arm means are far apart in the posted summaries, and the recalculated intervals for the primary comparisons do not include zero. The unadjusted recalculated p-values are each <0.001. These results indicate a clear statistical separation in the posted data under the simple comparison approach. Statistical precision does not establish the cause of that separation or its durability beyond the intervention. It also does not address uncertainty from missing outcome confirmations, analysis-population choices, or multiplicity, for which the registry does not report methods.

The standard deviations describe variation among observations within each arm, not uncertainty in the differences. Confidence intervals for the group means themselves are not listed in the registry record. The registry also does not report a clinically important threshold for interpreting the size of the primary difference.

12. 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 illustrations express sample size as participants per arm, not as a total across arms or as total events. They use the observed difference as a reference and show planning scenarios for detecting 100% of the observed effect, 75% of the observed effect, and 50% of the observed effect. The listed assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The trial’s original design assumptions and sample-size justification are not reported in the registry record.

The 80% power column describes the illustrative number of participants per arm for a design intended to have an 80% chance of detecting the specified effect under those assumptions, if that effect and the model assumptions are correct. The 90% power column uses the corresponding 90% target. These are planning targets, not guarantees that a future study will detect an effect. Smaller effects need more participants to detect than larger effects, all else held constant.

For the primary comparisons, the displayed illustrations give 1 participant per arm for each stated effect fraction in both power columns. Such very small figures are driven by the unusually large observed contrast relative to the reported variability and the calculation’s assumptions. They should not be treated as a realistic enrollment recommendation or as evidence that a small study would reliably estimate the effect. The illustrations are not observed power.

The plotted planning curve represents the same general relationship between the assumed effect size and the required sample size. A curve based on observed effects is sensitive to the size of the observed effect and the chosen assumptions; it is not a validation of the study design or a forecast of a future study’s result.

13. How the Sample Size Is Derived

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

Formula

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

Worked calculation for this trial

1. Observed difference Δ = 60.900; pooled standard deviation σ = 3.160.
2. n = 2 × (1.96 + 0.842)² × 3.160² / 60.900² = 0.0, rounded up to 1 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
delta <- 60.9                      # observed difference in means
sigma <- 3.15990506186499                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(6324630)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 1 (80% power), 1 (90% power)
 75% of observed effect: n per arm = 1 (80% power), 1 (90% power)
 50% of observed effect: n per arm = 1 (80% power), 1 (90% power)
power.t.test: 1.5 
Simulated power at n = 1 per arm: NA (20000 replicates)

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

14. Analyses Reported by the Sponsor

The sponsor-reported primary analysis is an ANOVA across all three groups, with p < 0.001. The posted recalculations instead compare each delivery program with the mobile market program using unadjusted differences in means. Each recalculated mean difference is 60.9, and each recalculated p-value is <0.001. These analyses address related but different questions: the ANOVA is an overall test across the three groups, whereas the recalculations are two specific comparisons against the mobile market group.

The registry does not report sponsor-produced pairwise estimates, confidence intervals, or p-values for those two contrasts. Thus, the recalculated estimates should not be presented as results from the sponsor’s analysis. The registry does not flag a discrepancy between the posted results and the recalculations. Differences in the displayed p-value thresholds are also consistent with the distinct analyses and reporting formats; they do not alone establish a contradiction.

The sponsor analysis is the trial’s reported statistical result. The recalculations are useful as transparent, unadjusted comparisons of the posted summary statistics, but they do not replace a full analysis using participant-level data or add details about the sponsor’s model that are absent from the registry record.

15. Multiplicity, Missing Data and Analysis Populations

The registry reports one overall ANOVA for the primary outcome and one overall ANOVA for the numerically described secondary outcome. It also contains unadjusted recalculations for two comparisons against the mobile market program for each outcome. No multiplicity adjustment or hierarchy among comparisons and outcomes is reported in the registry record.

In general, multiplicity refers to the increased chance of at least one false-positive result when several hypotheses are tested. An adjustment can control that risk, but different approaches address it in different ways. Because no plan is reported, the recalculated pairwise p-values should be read as unadjusted; the registry does not establish whether the sponsor used another approach in analyses not described in the record.

Missing-data procedures are not reported in the registry record. That matters because primary redemption depended on participants confirming delivery or prescription use through a usage survey, with reminder notifications after an initial non-confirmation. The record does not explain how an absent confirmation was classified, how missing weekly information was handled, or whether the average was calculated for all randomized participants or only those with available observations.

The analysis populations are also not reported in the registry record. The primary arm summaries list 22 participants for the mobile market group, 22 for produce delivery, and 23 for meal kit delivery, while the registered enrollment is 168. The record does not provide a flow accounting for these figures or explain which participants were included in each analysis. The summaries alone cannot show whether exclusions, missing outcomes, or a different analysis population account for the relationship between enrollment and the arm-specific counts.

These omissions limit assessment of whether the reported comparisons preserve the benefits of randomization and how sensitive the results may be to missing information or analytic choices. They do not demonstrate that the analyses were inappropriate; they identify details needed to evaluate the results more fully.

16. 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 no serious adverse events, no other adverse events, and no deaths in any of the three program groups. The serious-event group counts at risk are 22 for Produce Prescription Mobile Market, 22 for Produce Prescription Delivery, and 23 for Healthy Meal Kit Delivery. The other-event group counts at risk are the same as those listed for the corresponding groups.

These are observed event counts in the registry record, not proof that no adverse events could occur. The record does not provide event terms, further detail on how events were collected, or a description of the safety-monitoring procedures. With no events listed, the data cannot estimate the frequency of particular types of harm or distinguish risks that might emerge in other populations or settings. The figures should be read as a report of what was recorded for these groups during the study, not as a general safety guarantee.

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

The posted results show higher average confirmed prescription redemption in both delivery groups than in the produce prescription mobile market group during the 12-week intervention. The sponsor-reported overall ANOVA indicates evidence of differences among the three group means. Unadjusted recalculations comparing each delivery group with the mobile market group also show large positive mean differences in the posted data.

These findings concern engagement with the programs as measured by weekly confirmation of delivery or prescription redemption. They do not show how much of the food was consumed, whether participants changed their overall diet, or whether there were effects on health. The average percentage of food used is a separate secondary outcome, and the registry does not report numerical results for eligible participants’ interest or enrollment.

The study does not demonstrate that one delivery format is better than the other: both have the same posted primary mean, and the registry does not report a direct comparison designed to establish equivalence or superiority between them. Nor does a statistically clear difference in this study establish that the same pattern would occur outside the studied setting. The registry describes one clinical setting in the East Side of Buffalo and does not report results from other locations.

Interpretation also depends on information not reported in the registry record, including the missing-data approach, analysis populations, and details of the statistical model. The primary outcome relies on participant confirmation, so it reflects confirmed redemption under the recorded measurement method. In short, the data describe program redemption in the analyzed groups; they do not establish long-term use, broad effectiveness, or health benefit.

18. Why This Trial Matters Statistically

This trial raises statistical questions that are common in evaluations of service-delivery programs. A randomized comparison can help separate program differences from other influences, but interpretation still depends on clear definitions of the outcome, complete reporting of the analysis, and a transparent account of who contributed data. Here, the primary measure is confirmed redemption, an operational indicator of engagement rather than a direct measure of nutrition or health.

The distinction between an overall test and pairwise comparisons is important. The registry reports an overall ANOVA across three groups, while the unadjusted recalculations focus on each delivery program versus the mobile market program. Those are not interchangeable tests. Readers also need to know whether multiple comparisons were anticipated and how they were handled; that information is not reported in the registry record.

The difference between registered enrollment and the arm counts in the outcome summaries makes participant flow and analysis-population reporting especially relevant. Without that accounting, readers cannot assess how the analyzed observations relate to the full enrolled group or how missing confirmations were treated. Such reporting helps readers evaluate whether the result is precise and whether it reflects the randomized comparison.

Finally, planning illustrations based on observed effects can be informative about assumptions, but they are not a substitute for an original design rationale. The registry does not report the trial’s sample-size justification. Distinguishing those retrospective illustrations from prospective planning helps prevent an observed result from being mistaken for evidence about the study’s design quality or power.

19. 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 posted outcome summaries cover fewer participants in their arm-specific counts than the registered enrollment figure. The registry does not report a participant-flow account explaining the relationship. As a result, it is not possible from the record to identify the analysis population or determine how many enrolled participants had usable primary outcome data.

The primary outcome depends on confirmation through a usage survey. Although the registry describes automatic notifications and reminders, it does not report how nonresponse or incomplete weekly records were handled. The endpoint may therefore reflect both program use and the availability of confirmation, and the record does not explain how those components were distinguished.

The design is listed as unmasked, and the outcome involves participant confirmation. The registry does not report steps taken to reduce potential measurement or reporting influences. The setting is a single clinical center in the East Side of Buffalo, which limits how confidently the results can be generalized to other service systems or communities.

The record does not report the original sample-size rationale, detailed randomization procedures, the full statistical model, multiplicity handling, analysis-population definitions, or missing-data methods. The recalculated pairwise results are unadjusted and based on summary statistics rather than participant-level analysis. These information gaps limit assessment of assumptions and robustness; they do not by themselves establish that the results are biased.

The primary outcome measures redemption over the 12-week intervention, not longer-term participation or health outcomes. The registry does not report results for the listed secondary outcomes of program interest and eligible-participant enrollment. These limits define what can be concluded from the posted record.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Implementation of Innovative Food Prescription Programs in Older Adults — NCT06324630.
• Registry record last updated 2026-06-10; status last verified 2026-06.
• Results first posted 2026-06-10.
• 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.

23. Record Summary

The registry describes a completed randomized, parallel, unmasked study of three food prescription programs for older adults: a produce prescription mobile market, produce prescription delivery, and healthy meal kit delivery. The registered enrollment is 168. The recorded study start date is 2024-09-09, and the primary completion date is 2025-02-17.

The primary outcome is average prescription redemption over the 12-week intervention. The sponsor-reported analysis is an ANOVA across the three groups with p < 0.001. The posted arm means are 28.3 for the mobile market group and 89.2 for each delivery group. Unadjusted recalculations show a mean difference of 60.9 for each delivery group versus the mobile market group.

The registry also reports an overall ANOVA for average percentage of fruit and vegetables used, with p <0.001. No serious adverse events, other adverse events, or deaths are listed. Details on analysis populations, missing data, multiplicity, and the original sample-size rationale are not reported in the registry record.