Study of Household Purchasing Patterns, Eating and Recreation: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study of Household Purchasing Patterns, Eating and Recreation (NCT02073643), a registered phase not stated study. The primary outcome is Diet Quality of Household Food Purchases.

2. Clinical Question

3. Trial Design

The registry identifies the study as “Study of Household Purchasing Patterns, Eating and Recreation,” with the official title “Delay Discounting and Household Food Choices.” Rush University Medical Center is listed as the sponsor. The record describes a project examining behavioral and household characteristics associated with food purchasing patterns. The listed conditions are Dietary Habits, Adiposity, and Blood Pressure; these listings do not by themselves establish that the study tested a treatment for any of those conditions.

The record lists enrollment as 204, a start date of 2013-11, primary completion as 2016-11, and status as COMPLETED. It states that N=202 participants had food-purchase data available for analysis. The enrollment figure and the analysis-population description refer to different stages or sets in the record; the reason for the difference is not reported in the registry record.

This is not described as a randomized comparison, and allocation is not stated. The registry cautions that any arms are not a like-for-like control comparison. It would therefore be inappropriate to interpret a difference between any groups as a randomized treatment effect. The record does not provide enough detail to characterize the specific group definitions or the way participants were assigned or classified.

The primary outcome is continuous: the mean diet-quality score for household food purchases over 2 weeks. The registry lists 6 outcome measures and names diet quality, the home food environment, and the percentage of total energy purchased from non-store sources among the secondary outcomes. The registry record does not report the analysis population definition beyond the availability of purchase data, or give further detail on study procedures.

4. Participant Flow and Accounting

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

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: N=202 participants had food purchase data available for analysis.

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 Diet Quality of Household Food Purchases, measured over 2 weeks.

The primary endpoint is diet quality of household food purchases, expressed as units on a scale and summarized as a mean with a standard deviation. The registry says the score was calculated by applying the Healthy Eating Index-2015 (HEI-2015) scoring criteria to nutrient and food-group data for purchased foods and beverages. It describes HEI-2015 as assessing adherence to the Department of Health and Human Services’ 2015 Dietary Guidelines for Americans.

The scoring approach combines scores for 13 dietary components into a total score ranging from 0-100. Higher scores indicate closer adherence to the dietary guidelines. The measure is used to characterize the overall quality of foods and beverages purchased during the stated 2-week timeframe. It is a measure of household purchasing, not a direct measure of what each participant consumed, and the record does not establish that purchased items were eaten.

A continuous score can retain gradations across its scale rather than reducing the outcome to categories. Reporting a mean describes the average score in the analyzed data; the standard deviation describes variation around that mean. Neither statistic, on its own, indicates a causal effect. The registry record defines the endpoint but does not report its observed mean or standard deviation, so the magnitude and spread of the primary outcome cannot be assessed from the record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous and is specified as a mean. A mean is a measure of the central location of numerical observations. The standard deviation, the stated measure of dispersion, describes how spread out individual observations are around that mean. These are complementary descriptions: the mean conveys a typical level on the score scale, while the standard deviation conveys variation among observations. The registry record names these statistics but does not report their observed values.

What does the HEI-2015 score represent?

According to the registry description, the score applies HEI-2015 criteria to nutrient and food-group data for purchased foods and beverages. Adherence to recommended intakes for 13 key dietary components is scored on a continuous scale for each component; the component scores are summed to obtain a total from 0-100. A higher total denotes closer adherence to the dietary guidelines. This construction makes the endpoint a composite score: interpretation concerns the combined score, while a total alone would not reveal which components contributed most to it. The record does not report component-level results.

What can a continuous outcome show?

A continuous measure can distinguish degrees of score rather than only recording whether a threshold has been reached. If group summaries or associations are analyzed, their meaning depends on the study design, the definition of the groups, and the statistical model. Here, the registry record does not provide group-specific estimates or an analysis describing associations. No estimate of a group contrast, trend, or relationship can therefore be interpreted from the posted information.

Why does study design matter?

General statistical interpretation distinguishes association from causation. Random assignment can support causal comparisons when the design and analysis are appropriate, but randomization is not described for this study. The registry further warns that arms are not a like-for-like control comparison. A comparison between non-equivalent groups could reflect differences in their characteristics as well as differences in purchasing patterns. The record does not report adjustment methods or other procedures that might address such differences. Accordingly, an unreported group contrast cannot be treated as a treatment effect.

What do uncertainty measures add?

In general, a confidence interval gives a range of values compatible with an estimate under the model and sampling assumptions used. Its width conveys precision, while the estimate itself conveys direction and magnitude. A p-value, when reported, summarizes compatibility with a null hypothesis under a specified statistical model; it is not a measure of the size or importance of a finding. The registry record reports no confidence interval, p-value, or other inferential analysis for the primary outcome. Precision and statistical evidence cannot be judged from the endpoint definition alone.

How should planning calculations be read?

The stated planning illustration assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The effect to detect is framed as a stated fraction of the observed effect. Such calculations are planning illustrations, not observed power, and they do not establish the study’s original design rationale. The registry record does not report a sample-size justification, and it does not report the primary observed effect needed to assess the basis of an effect-scaled illustration. No planning sample-size value is reported in the registry record. The assumptions should not be mistaken for the study’s own statistical plan or proof that a particular analysis was adequately powered.

Over-dispersion is a general issue for outcomes analyzed with models that assume a particular level of variability, especially count outcomes: greater variation than the model assumes can make standard errors too small and uncertainty appear less than it is. The primary endpoint is described as continuous and summarized by a mean and standard deviation; the registry does not report a model or variance assessment. There is no basis in the record to say whether over-dispersion was assessed or relevant to any specific analysis.

Overall, the methods information supports an explanation of the score and the general statistical concepts, but not a reconstruction of an analysis. The statistical model, covariates, handling of repeated or clustered observations, and inferential procedure are not reported in the registry record.

10. Confidence Intervals for Each Arm

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

R code and output

arm <- c("Main Cohort")
n   <- c(202)
m   <- c(57.88)
sp  <- c(15.22)
sd  <- sp      # posted standard deviations
for (i in seq_along(n)) {
  se <- sd[i] / sqrt(n[i]); h <- qt(0.975, n[i] - 1) * se
  cat(sprintf("CARM|%s|%d|%.3f|%.3f|%.3f|%.3f\n", arm[i], n[i], m[i], sd[i], m[i] - h, m[i] + h))
}

CARM  Main Cohort  202  57.880  15.220  55.768  59.992

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 6 outcome measures, with the primary outcome identified as diet quality of household food purchases. The named secondary outcomes include diet quality of dietary intake, the home food environment, and the percentage of total energy purchased from non-store sources. When several outcomes are examined, multiplicity can arise because multiple statistical tests increase the opportunity for apparently notable findings by chance. In general, study teams may specify a hierarchy of outcomes or adjust inference for multiple testing. The registry record does not report a multiplicity strategy, a testing hierarchy beyond identifying the primary outcome, or analyses for the listed outcomes.

The record states that N=202 participants had food-purchase data available for analysis, while enrollment was 204. The reason for this difference is not reported in the registry record. Missing-data methods are also not reported: the record does not state whether missing observations were excluded, imputed, or handled in another way. The available information does not establish completeness for each secondary outcome or whether all participants with purchase data contributed to every analysis.

The record gives no analysis-population definitions beyond the purchase-data statement, and no sensitivity analyses addressing missingness are reported. In general, missingness can affect estimates when the availability of data is related to participant characteristics or outcomes. Whether that issue arose in this study cannot be determined from the registry record.

No statistical analyses are reported in the registry record. As a result, there are no posted outcome-specific denominators, missingness summaries, or multiplicity-adjusted estimates to interpret. The enrollment and purchase-data figures should not be used to infer an unreported missing-data mechanism or to reconstruct analysis populations.

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

The record establishes what the investigators intended to examine and how the primary score was defined. It describes a measure of diet quality based on purchased foods and beverages over 2 weeks, scored according to HEI-2015 criteria. It also identifies the enrolled population and the number of participants with food-purchase data available for analysis. These registry entries characterize the study and its endpoint; they do not convey the observed diet-quality score.

Because the registry record does not report the primary mean, standard deviation, group estimates, or statistical analyses, it cannot establish the level, variability, or statistical precision of the primary outcome. Nor can it support a conclusion about whether household characteristics were associated with food-purchase quality. The secondary outcomes are named, but their numerical findings are not reported in the registry record.

The score concerns purchased foods and beverages, not confirmed consumption. Household purchases may be informative about the food environment, but the registry endpoint alone does not show which foods were consumed, by whom, or in what amounts. The record’s description of a purchase-based score should not be extended to claims about individual dietary intake or health outcomes.

The study is not described as randomized, and the registry cautions that arms are not a like-for-like control comparison. Therefore, even if a group difference were available elsewhere, the design information recorded would not justify interpreting it as a causal effect without further methodological detail. No treatment effect is reported in the registry record.

The registry lists zero serious and zero other events, including zero affected participants, for the Main Cohort fields. Those entries describe what is recorded in the registry; they do not establish how completely events were collected or whether the study provides a comprehensive safety assessment. In sum, the record supports a description of the study and measurement strategy, but not a claim about efficacy, causal impact, or the clinical importance of an observed result.

13. Why This Trial Matters Statistically

This study is statistically useful as an example of the distinction between defining an endpoint and reporting evidence about that endpoint. The registry gives a detailed description of the primary measure: a purchase-based HEI-2015 score, summarized as a mean and standard deviation. Yet no numerical primary result or statistical analysis is reported. Readers can understand what was intended to be measured without being able to assess the observed level, variation, or uncertainty.

The study also illustrates why design labels and comparisons matter. The registry does not describe randomization and explicitly cautions that arms are not a like-for-like control comparison. Statistical contrasts do not acquire a causal interpretation simply because a numerical outcome can be summarized or modeled. The group definitions, allocation process, and analytical adjustments would be necessary context for judging any comparison, and those details are not reported in the registry record.

The distinction between enrollment and outcome availability matters as well. The record lists enrollment of 204 and food-purchase data for N=202, but does not explain the difference or report missing-data handling. Transparent reporting of analysis populations and missing observations helps readers assess which data support each estimate. Without that information, outcome-specific completeness and possible selection effects remain unknown.

Finally, listing 6 outcome measures raises a general need to report how multiple outcomes were prioritized and interpreted. The primary outcome is identified, but no multiplicity approach or numerical secondary findings are reported. Overall, the record makes the measurement concept visible while leaving the statistical evidence unavailable for evaluation.

14. 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 principal limitation for interpreting the study from its registry record is the absence of numerical outcome results. The record describes the primary endpoint but does not report its mean, standard deviation, confidence interval, p-value, or any model-based estimate. It also reports no statistical analyses. The direction, magnitude, and precision of findings therefore cannot be assessed.

Design information is limited. The record states that this is not a randomized comparison, that allocation is not stated, and that arms are not a like-for-like control comparison. Specific group definitions, any analysis of associations, and any adjustment for differences between groups are not reported in the registry record. These omissions prevent interpretation of a comparative or causal effect.

The registry reports 204 enrolled participants and N=202 with food-purchase data available, but does not explain the difference. It does not describe missing-data procedures, outcome-specific denominators, or sensitivity analyses. It also does not state whether the purchase data captured every relevant purchasing source or how the data were collected beyond the endpoint’s description. These details should not be inferred from the scoring definition.

The outcome is based on food and beverage purchases and is not described as a direct measure of consumption. The composite HEI-2015 total also does not disclose component-specific patterns in the absence of component results. The registry record does not report a sample-size justification, a complete statistical plan, or a multiplicity strategy. These limitations concern the information available in the registry record; they do not establish what may have been done outside it.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Study of Household Purchasing Patterns, Eating and Recreation — NCT02073643.
• Registry record last updated 2019-03-25; status last verified 2019-03.
• Results first posted 2019-03-25.
• 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.

18. Record Summary

The registry record identifies a completed study sponsored by Rush University Medical Center, with enrollment of 204 and dates of 2013-11 to 2016-11 for study start and primary completion. Its stated focus is behavioral and household characteristics associated with food purchasing patterns. The primary outcome is the mean diet quality of household food purchases over 2 weeks, scored using HEI-2015 criteria; higher scores indicate closer adherence to the dietary guidelines.

The record states that N=202 participants had food-purchase data available for analysis and lists 6 outcome measures. It does not report numerical primary or secondary outcome findings, statistical analyses, missing-data procedures, or a sample-size justification. It also cautions that the study is not a randomized comparison and that arms are not a like-for-like control comparison. The record supports an account of the study objective and measurement approach, but not a quantitative conclusion about the outcomes.