This page provides an independent statistical analysis and educational interpretation of publicly reported results. ClinicalTrials.gov provides the official trial registry record. Numerical trial results on this page are restricted to the results posted in the ClinicalTrials.gov record; calculations added by Clinical Biostats are labelled as such.
1. Trial at a Glance
This page covers the registry results for Location Initiated Individualized Texts for Adolescent Health (LIITAH) (NCT03762135), a randomized na study. The primary outcome is Visits to Restaurants.
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT03762135 |
| Phase | NA |
| Condition | Overweight, Obese, Healthy |
| Allocation | Randomized |
| Design model | Parallel |
| Masking | None (open label) |
| Enrollment | 156 |
| Arms in the primary outcome | n/a |
| Lead sponsor | University of Michigan |
| Results posted | Yes |
2. Clinical Question
Population
Eligible adolescents were enrolled with a parent for approximately 6 weeks. The registry lists overweight, obese, and healthy conditions. The primary outcome is based exclusively on adolescent data; the registry does not report further eligibility criteria or the characteristics of the enrolled participants.
Intervention
The full version of the LIITAH app included enhanced location identification, self-reported nutrients using annotated photos, individually and culturally tailored point-of-purchase prompts, and tailored messages sent at other times. The description of those other message times is cut off in the registry record, so their schedule is not reported in the registry record.
Comparator
The comparison was a partial app version that included enhanced location identification and self-reported nutrients using annotated photos. It could detect restaurant presence and let users document purchases, but did not include point-of-purchase prompts encouraging healthy choices or messages at other times. This is an active app comparison, not a no-app control.
Primary question
The primary question is whether the full app version and partial app version differ in the mean number of restaurant visits recorded by the app over 6 weeks. The record identifies the measure as the number of FFR visits and specifies that it uses adolescent data. It does not report arm-level visit counts, an estimated difference, or a confidence interval, so the comparative result cannot be assessed from the registry record.
3. Trial Design
LIITAH was a randomized, parallel-group trial with no masking. The registry lists the study as completed and records enrollment of 156. The sponsor was the University of Michigan. The listed phase is NA. The study began on 2021-03-04, and primary completion was recorded as 2022-11-21. These administrative details describe the registered study; they do not establish when every participant completed follow-up or how the analysis was conducted.
The trial compared the full LIITAH app with a partial version containing enhanced location identification and the annotated-photo nutrient reporting feature. The full version also included tailored point-of-purchase prompts and messages sent at other times. Because both groups received app components, the comparison addresses the added features of the full version relative to the partial app, rather than app use versus no app use. The registry does not report whether participants, parents, or study staff were unaware of treatment assignment; masking is listed as none.
Adolescents participated with a parent for approximately 6 weeks, according to the study summary. The primary outcome concerns adolescents, while safety information is listed separately for adolescent and parent groups. The record lists 3 outcome measures and 1 analysis, but does not provide the full analysis plan or identify every outcome definition in the registry record for this account. It also does not report the randomization procedure, allocation ratio, site details, adherence summaries, or the number of participants included in each outcome analysis. Those details are not reported in the registry record.
Enrollment is a registry-level study figure and should not be treated as the number analyzed for the primary endpoint. The specific analyzed population, exclusions after randomization, and handling of participants with incomplete app records are not reported in the registry record. Randomization supports a planned comparison between assigned groups, but interpreting that comparison still depends on the outcome data and analysis details, neither of which is available for the primary result.
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
| Stage | Full Version of the LIITah App. | Partial App. (ELI and SNAP Only) |
|---|---|---|
| STARTED | 52 | 26 |
| COMPLETED | 52 | 26 |
| NOT COMPLETED | 0 | 0 |
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.
Population: With the exception of region of enrollment, baseline data shown are for the adolescent participants only because no age, BMI, or other baseline data shown in baseline characteristics were collected from parents. Region of enrollment data was available for parents because all parents in dyads were co-located with their children who were the object of the study.
| Characteristic | Unit | Full Version of the LIITah App. | Partial App. (ELI and SNAP Only) | Total |
|---|---|---|---|---|
| Participants analysed | 52 | 26 | 78 | |
| Age, Continuous | years | 15 (13 to 17) | 15 (13 to 17) | 15 (13 to 17) |
| Sex: Female, Male: Female | Participants | 38 | 15 | 53 |
| Sex: Female, Male: Male | Participants | 14 | 11 | 25 |
| Race (NIH/OMB): American Indian or Alaska Native | Participants | 0 | 0 | 0 |
| Race (NIH/OMB): Asian | Participants | 0 | 1 | 1 |
| Race (NIH/OMB): Native Hawaiian or Other Pacific Islander | Participants | 0 | 0 | 0 |
| Race (NIH/OMB): Black or African American | Participants | 10 | 5 | 15 |
| Race (NIH/OMB): White | Participants | 33 | 17 | 50 |
| Race (NIH/OMB): More than one race | Participants | 7 | 3 | 10 |
| Race (NIH/OMB): Unknown or Not Reported | Participants | 2 | 0 | 2 |
| Race/Ethnicity, Customized: Hispanic or Latino | Participants | 6 | 2 | 8 |
| Race/Ethnicity, Customized: Middle Eastern | Participants | 1 | 0 | 1 |
| Race/Ethnicity, Customized: Not Hispanic, Latino, or Middle Eastern | Participants | 45 | 24 | 69 |
| Region of Enrollment: United States | Participants | 52 | 26 | 78 |
| Region of Enrollment: United States | parents of participants | 52 | 26 | 78 |
| Estimated number of fast food restaurant visits per week prior to study | FFR Visits | 5 (3 to 10) | 5 (3 to 12) | 5 (3 to 12) |
| BMI Percentile | BMI (kg/m^2) Percentile | 87.2 (52.9 to 99.9) | 87.4 (65.7 to 99.7) | 87.3 (52.9 to 99.9) |
| Ethnic Identity Score | units on a scale | 3.2 (2.3 to 3.8) | 3.0 (2.2 to 3.6) | 3.2 (2.2 to 3.8) |
6. Primary Endpoint
The registry lists the primary outcome as Visits to Restaurants, measured over over 6 weeks.
| Element | Registry entry |
|---|---|
| Result type | Mean |
| Measure of spread | Standard Deviation |
| Unit | Number of FFR Visits |
| Endpoint classification | Continuous Endpoint |
The primary endpoint is the number of restaurant visits over 6 weeks, recorded through the app. The registry describes it as the number of FFR visits and states that it is based exclusively on adolescent data. Its stated summary is a mean with standard deviation. The endpoint therefore concerns recorded visit frequency during the study period, not the number of calories purchased, the nutritional composition of purchases, or body mass index.
A visit measure can be useful for studying a behavioral pathway that an app is intended to influence: restaurant visits create occasions at which app prompts or self-monitoring features may be used. However, a visit count alone does not establish what a participant purchased or ate, whether a visit involved a meal, or whether food choices changed. The registry summary describes broader goals involving healthy food choices, calories purchased, restaurant visits, and BMI, but the primary endpoint is specifically restaurant visits.
In general, reporting a mean and standard deviation describes the average observed count and the variability of counts among participants. Interpretation also depends on how app-recorded visits were defined and whether recording was complete. Those operational details, along with the primary outcome values for each group, are not reported in the registry record. The registry lists BMI percentile as a secondary outcome, but it does not provide the primary endpoint results needed to estimate or judge the difference in restaurant visits between app versions.
7. Why No Re-analysis Is Shown
8. Statistical Interpretation
The registry record identifies a randomized comparison and defines restaurant visits as the primary outcome, but the primary outcome results are not reported in the registry record. In particular, no group means, standard deviations, estimated contrast, confidence interval, or test result are included in the registry record for this analysis. Consequently, the direction and size of any difference in recorded visits cannot be established from this record.
A randomized design is intended to make the assigned groups comparable on average, so a difference in a prespecified outcome can be interpreted as evidence about the intervention contrast when the trial is conducted and analyzed appropriately. Here, the relevant contrast is the full app against the partial app. Since the partial app contains location detection and photo-based purchase documentation, any estimated difference would relate to adding the full version's prompts and other tailored messages to those shared features. It would not, by itself, estimate the effect of using an app compared with not using one.
Precision is also not available for the primary result. In general, a confidence interval describes the range of effect values compatible with the data and analysis, under the method used. Without an estimate and interval, readers cannot assess whether the result is precise, whether a range of materially different effects remains plausible, or how the data compare with a threshold regarded as important. No such threshold is reported in the registry record either.
The registry summary says the study aimed to examine healthy food choices, calories purchased, restaurant visits, and BMI. The recorded primary endpoint is visits, and BMI percentile is listed as a secondary outcome. A change in visits would not alone show a change in calories purchased, diet quality, or BMI. Conversely, the absence of a reported visit result does not establish that there was no difference. The registry record does not provide enough outcome data to draw a comparative conclusion.
The study is listed as completed, but completion status is not a result. Likewise, the enrollment figure does not show how many adolescents contributed usable endpoint data, and the adverse-event figures do not substitute for efficacy results. The responsible reading is therefore limited: the registry describes the comparison and its intended primary measure, while the outcome estimate and its uncertainty are not reported in the registry record.
9. Statistical Methods Explained
The registry identifies the primary endpoint as a continuous measure summarized by a mean and standard deviation. The endpoint itself is a count of app-recorded visits. This distinction matters: the statistical summary describes how the registry intended to express the measure, while the underlying observations are counts. No group-level summaries or treatment-effect estimate are reported in the registry record, so the methods below explain how such summaries are generally interpreted rather than describing a reported result from LIITAH.
What does a mean represent for this endpoint?
In general, a group mean is the arithmetic average of the recorded values for participants included in that analysis. For a visit count, it can convey average recorded use over the stated observation period. The mean does not describe every participant's pattern: participants may have different counts, and a few relatively high counts can affect the average. The standard deviation describes the spread of participant values around the mean. It is not the uncertainty in the mean, and it does not indicate how precisely the treatment groups differ.
Comparing means between randomized groups is a common way to summarize a continuous endpoint. The estimated contrast would describe the difference in average recorded visits under the analysis used. Its interpretation would depend on the definition of a visit, the completeness of app recording, and which participants were included. Those operational and analysis details are not reported in the registry record. No comparison estimate is available.
Why can visit counts need special consideration?
As a general statistical matter, count data are nonnegative and may have a skewed distribution. A mean and standard deviation can still summarize counts, but they may not describe the full pattern well when many observations are low and a smaller number are high. Over-dispersion means that variability exceeds what a particular model assumes; ignoring it can make uncertainty estimates too small or otherwise poorly calibrated. This is a general consideration, not evidence that LIITAH's data were over-dispersed. The registry record does not report a distributional assessment or identify a model used for the endpoint.
Counts may also vary with the time each participant is observed or with the opportunity to record a visit. The stated timeframe is over 6 weeks, but the registry record does not describe whether all participants had the same amount of usable app observation, how missed app use was handled, or whether the visit count was verified independently. Such information is relevant when interpreting a count as behavior rather than as a combination of behavior and recording.
What would a confidence interval add?
In general, a confidence interval communicates uncertainty around an estimated effect. A narrow interval indicates greater precision under the stated analysis; a wide interval indicates less precision. An interval should be considered alongside the point estimate and the outcome's practical meaning, rather than treated as a pass-or-fail label. The registry record does not report a confidence interval for the primary outcome, so its precision cannot be evaluated.
A p-value, if reported, would address compatibility between observed data and a specified statistical null model, subject to the analysis assumptions. It would not measure the size or importance of an effect. No primary-outcome p-value or test is reported in the registry record. Statistical significance therefore cannot be inferred from the design, enrollment, completion status, or safety counts.
How should planning illustrations be understood?
Any sample-size illustrations associated with the posted results are planning exercises based on an observed effect, using a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. They describe participants per arm for 80% power or other stated planning targets, with the target effect expressed as a fraction of the observed effect. Such illustrations are not the trial's original sample-size justification, and that justification is not reported in the registry record. They are not observed power and do not establish that the trial was adequately powered. No particular illustration value is included in this account.
These assumptions are simplified representations. A planning calculation based on an observed estimate inherits uncertainty from that estimate, and a different effect target changes the planning question. The registry does not report whether the trial used those assumptions in its original design, whether sample-size calculations were performed, or whether the study included interim analyses. Those matters are not reported in the registry record.
What can be concluded from the available statistical record?
The design is randomized and parallel, and the primary endpoint's summary type and timeframe are stated. Yet the actual endpoint summaries, treatment contrast, uncertainty interval, and analysis details are absent from the record details used. General explanations of means, count distributions, confidence intervals, and planning assumptions should not be mistaken for findings about LIITAH. A quantitative conclusion about the primary comparison requires the trial's posted outcome data and sufficient analysis information to interpret them.
10. Multiplicity, Missing Data and Analysis Populations
The registry entries list 3 outcome measures and identify BMI percentile as a secondary outcome, alongside the primary outcome of restaurant visits. They do not give the complete definitions and time points for all outcomes. The record notes that the primary outcome has several categories or time points and is not reduced to one comparison. Therefore, no single primary contrast can be reconstructed from the available information.
Multiplicity arises when several outcomes, time points, or comparisons are tested: the chance of at least one chance finding can increase if no adjustment or hierarchy is used. In general, a prespecified outcome hierarchy or a multiplicity adjustment can help address that issue. The registry record does not report whether such a hierarchy or adjustment was planned or used, so no claim about control of multiplicity is possible. It also does not report a complete statistical analysis plan.
Missing-data handling is not reported in the registry record. For an app-based visit outcome, incomplete recording could leave uncertainty about whether a missing entry reflects no visit, a visit not captured by the app, or a participant who did not contribute follow-up data. This is a general interpretive concern, not a claim that any particular pattern occurred in LIITAH. The record does not describe imputation, sensitivity analyses, reasons for missingness, or the amount of missing primary-outcome data.
The analysis population is also not reported in the registry record. The randomized design does not by itself establish whether the analysis included all assigned participants, only those with usable app data, or another defined group. Without these details and the outcome summaries, readers cannot assess how missing observations or analysis-population choices might affect the comparison.
11. Safety Results
The registry reports serious adverse events as affected participants divided by participants at risk.
| Arm | Participants with serious adverse events | Participants at risk | Percentage |
|---|---|---|---|
| Full Version of the LIITah App. (Adolescents) | 0 | 52 | 0.0% |
| Full Version of the LIITah App.(Parents) | 0 | 52 | 0.0% |
| Partial App. (ELI and SNAP Only) (Adolescents) | 0 | 26 | 0.0% |
| Partial App. (ELI and SNAP Only) - Parents | 0 | 52 | 0.0% |
Deaths
| Arm | Deaths (participants affected of at risk) |
|---|---|
| Full Version of the LIITah App. (Adolescents) | 0 of 52 |
| Full Version of the LIITah App.(Parents) | 0 of 52 |
| Partial App. (ELI and SNAP Only) (Adolescents) | 0 of 26 |
| Partial App. (ELI and SNAP Only) - Parents | 0 of 26 |
Other (non-serious) adverse events
Participants with at least one non-serious event at or above the registry's 0% reporting threshold.
| Arm | Participants affected of at risk |
|---|---|
| Full Version of the LIITah App. (Adolescents) | 0 of 52 |
| Full Version of the LIITah App.(Parents) | 0 of 52 |
| Partial App. (ELI and SNAP Only) (Adolescents) | 0 of 26 |
| Partial App. (ELI and SNAP Only) - Parents | 0 of 52 |
The registry lists serious adverse events, other adverse events, and deaths separately for adolescent and parent groups. For adolescents assigned to the full app version, 0 serious adverse events and 0 other adverse events are listed among 52 at risk, with 0 deaths. For parents in the full app group, the corresponding figures are 0 and 0 among 52 at risk, with 0 deaths. For adolescents in the partial app group, 0 serious adverse events and 0 other adverse events are listed among 26 at risk, with 0 deaths. For parents in the partial app group, the corresponding figures are 0 and 0 among 52 at risk, with 0 deaths.
These are the counts recorded in the registry; they do not show that the probability of an adverse event is zero. A zero count can occur even when an event remains possible, and the figures do not provide a precise estimate of rare-event risk. They also do not describe event timing, severity details beyond the serious-event classification, or how events were collected. The registry lists no serious-event terms. The figures should be read as reported counts in the listed groups, not as proof that either app version is free of risk or as evidence about the primary outcome.
12. What the Result Does, and Does Not, Mean
The registry record establishes that LIITAH was a completed, randomized, parallel-group comparison of a full app version with a partial app version. The primary endpoint was the app-recorded number of restaurant visits over 6 weeks, based on adolescent data. The partial app contained location identification and photo-based purchase documentation; the full app added tailored point-of-purchase prompts and other tailored messages. This makes the comparison relevant to the added features of the full app relative to the partial app.
What the record does not establish is whether those groups differed in restaurant visits. No group means, estimated contrast, confidence interval, or primary-outcome test are reported in the registry record. Without those results, the direction, magnitude, and precision of the comparison cannot be described. A completed study status is not evidence of a positive, negative, or null result.
Even if a visit difference were available, the endpoint would address recorded restaurant visits, not every goal in the study summary. It would not by itself establish a change in calories purchased, the quality of food choices, or BMI. BMI percentile is listed as a secondary outcome, but its results are not reported in the registry record. Nor can a result from this particular app comparison automatically be generalized beyond the enrolled adolescents and study conditions; the record does not provide enough detail about participant characteristics to assess broader applicability.
The safety counts are also limited to the adverse-event information listed in the registry. Zero recorded events in the listed categories do not demonstrate absence of risk. The defensible conclusion is that the registry describes a randomized app comparison and its primary measure, but does not report the efficacy results needed to judge the comparative effect or its uncertainty.
13. Why This Trial Matters Statistically
LIITAH is statistically notable as a comparison of app feature sets rather than a comparison of an app with no app. The partial version included location identification and annotated-photo documentation, while the full version added tailored prompts and messages. If an outcome contrast were reported, it would answer a focused question about the difference between these versions. It would not isolate the effect of every app component separately, because the record describes a package of features in each group.
The primary measure also illustrates the distinction between an intended behavioral target and the outcome actually analyzed. The study summary describes interest in healthy food choices, calories purchased, restaurant visits, and BMI, but the listed primary measure is the number of restaurant visits. The endpoint can inform a question about visit frequency, while leaving purchase content and health outcomes as separate questions. BMI percentile is listed as secondary, and the registry entries do not report its result.
For biostatisticians and clinical researchers, the record is a reminder that design labels do not replace outcome reporting. Randomization and completion describe important aspects of a trial, but interpretation requires the estimate, uncertainty, outcome definitions, analysis population, and missing-data approach. Those primary-result and analysis details are not reported in the registry record. Without them, readers should not infer a treatment effect from the stated aims, enrollment, or safety counts.
The record also raises general issues relevant to app-based endpoints: event definition, completeness of digital capture, and the relationship between an observed app record and the underlying behavior. These are questions for interpreting the measurement, not claims that the trial's data had a particular flaw. The registry entries available for this account do not resolve them.
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 most important limitation for interpreting the trial is that the primary outcome results are not reported in the registry record. There are no arm-level means or standard deviations, estimated comparison, confidence interval, or test result in the registry record for this account. Accordingly, an effect's direction, size, and precision cannot be assessed.
The endpoint is described as the number of FFR visits obtained from the app, but the registry record does not define the visit-capture rules or explain how incomplete app use was handled. For an app-recorded measure, the observed record may depend on both behavior and recording; the registry entries do not allow those contributions to be separated. The analysis population and missing-data methods are not reported.
The design was unmasked. That fact does not show that outcome recording was biased, but it means masking cannot be invoked as a safeguard against influence from awareness of assignment. The record does not report whether the primary measure was independently validated or whether other protections were used.
The full app description is truncated after noting tailored messages sent at other times, so the details of that component are not reported in the registry record. The record also does not provide full definitions for all 3 outcome measures, the complete statistical plan, or whether multiplicity was addressed. The study summary describes adolescents enrolled with a parent for approximately 6 weeks; this short stated study period does not answer questions about longer-term behavior or outcomes. Finally, the available participant details are insufficient to assess how broadly the findings might apply, and the absence of primary results prevents evaluating that question against observed effects.
15. Related Tutorials
16. Related Statistical Calculators
17. Sources
- ClinicalTrials.gov: Location Initiated Individualized Texts for Adolescent Health (LIITAH) — NCT03762135.
- Registry record last updated 2024-08-26; status last verified 2024-08.
- Results first posted 2024-08-26.
- 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.
Continue through the Clinical Biostats statistical pathway
Use this trial's endpoint as a starting point for deeper study of effect measures, confidence intervals, and sample-size planning.
18. Record Summary
LIITAH (NCT03762135) is listed as a completed, randomized, parallel-group trial with no masking, sponsored by the University of Michigan. Enrollment was 156. The listed phase is NA; the recorded start date is 2021-03-04, and primary completion was 2022-11-21. Adolescents participated with a parent for approximately 6 weeks.
The comparison was the full LIITAH app versus a partial app containing enhanced location identification and annotated-photo nutrient reporting. The primary outcome was the number of app-recorded FFR visits over 6 weeks, based on adolescent data and summarized as a mean with standard deviation. BMI percentile is listed as a secondary outcome. The registry record does not report the primary outcome values, the estimated contrast, or its uncertainty, and the analysis population and missing-data approach are not reported in the registry record.