Portion Control Treatment for Obesity: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Portion Control Treatment for Obesity (NCT01451554), a randomized phase 2, phase 3 study. The primary outcome is Weight Change at 6 Months.

2. Clinical Question

3. Trial Design

This was a randomized, parallel-group clinical trial of a behavioral intervention for obesity in a primary-care setting. The registry lists the phase as PHASE2 and PHASE3, masking as NONE, and allocation as RANDOMIZED. The sponsor was Mayo Clinic. The study is marked COMPLETED.

The registry record lists enrollment of 65. The Portion Control Intervention arm had 33 participants and the Usual Care arm had 32. Participants assigned to the intervention were given a portion-control plate and dietary counseling. Participants assigned to usual care received self-help booklets on diet and exercise. The registry describes both interventions as behavioral.

The study start is listed as 2009-01, and primary completion is listed as 2010-06. The registry describes the work as a pilot study intended to assess the intervention in a general medicine primary-care practice. It also notes that, at the time described in the study summary, no studies had been published assessing portion-control interventions in that setting.

The registry reports two outcome measures and two analyses. Weight change at 6 months is the primary outcome, and weight change at 3 months is the posted secondary outcome. Both are continuous outcomes expressed as a percentage, reported as means with standard deviations. The registry record does not report the original sample-size justification, detailed allocation procedures, or a prespecified statistical analysis plan. The absence of those details in the record does not establish what may have been specified elsewhere.

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: Intent to treat population includes all randomzied subjects. Missing data were imputed using the last observation carried forward.

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 Weight Change at 6 Months, measured over 6 months.

The primary endpoint is weight change at 6 months, expressed as a percentage of baseline. The registry describes it as weight change at the post-6-month assessment and reports the mean and standard deviation for each randomized group. A percentage expresses change relative to a participant’s own starting weight rather than as an absolute weight amount. In general, a negative value represents a decrease from baseline and a positive value represents an increase.

For the intervention arm, the posted mean was -1.2, with a standard deviation of 3.1 among 33 participants. For usual care, the mean was -0.4, with a standard deviation of 3.2 among 32 participants. The posted comparison expresses the mean difference as usual care minus intervention, yielding 0.8. This direction means the reported group means were numerically more negative in the intervention arm; it does not by itself establish that the groups differed beyond the uncertainty in the estimate.

In general, a continuous endpoint such as mean percentage weight change can retain information about the magnitude of individual changes, rather than reducing outcomes to a binary category. A 6-month assessment gives a defined follow-up point for comparing the groups. The registry record does not report why this particular time point was selected or how it was chosen relative to the study’s intended clinical objectives.

7. Results Posted in the Registry

• Usual Care: mean -0.40 versus -1.20 on control; difference 0.80 (95% CI -0.73 to 2.33), standardized effect d = 0.25; z-test p = 0.306.

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.

Weight Change at 3 Months

• 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:
  • Usual Care: mean -0.40 versus -1.70 on control; difference 1.30 (95% CI -0.00 to 2.60), standardized effect d = 0.48; z-test p = 0.051.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Usual Care and the control. The interval gives the range of effects that remain compatible with the data.

The registry posts one secondary endpoint, weight change at 3 months. Its overall pattern is directionally similar to the primary endpoint in that the intervention group mean is more negative than the usual-care mean. The secondary comparison is less conclusive: its confidence interval reaches from a value just below zero to positive values, and its sponsor-reported p-value is 0.06. This is a separate time point and should not be treated as a replication independent of the primary comparison.

Considering the primary and secondary outcomes together, both point estimates favor a more negative average change in the intervention arm, but the primary result is uncertain and the secondary result is also close to the null boundary. The secondary observation may help describe the time course represented in the posted outcomes, but it does not resolve the uncertainty in the primary comparison. The registry record does not report a prespecified strategy for using the secondary finding to support the primary conclusion.

In general, secondary endpoints can provide context, test additional questions, or generate hypotheses. When several outcomes or time points are examined, unadjusted p-values do not account for the full set of opportunities for a chance finding. The registry lists two outcome measures and two analyses, but does not report a multiplicity adjustment or a testing hierarchy. This means the secondary result should carry less inferential weight than the designated primary result and should not be interpreted in isolation as confirmatory evidence.

The posted secondary outcome is the only secondary measure identified in the registry record. The record does not report other secondary endpoint results, so no broader pattern across unposted outcomes can be assessed. Its relationship to the primary outcome is therefore best described as directionally consistent at the level of the group means, while both estimates retain uncertainty.

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

• Weight Change at 3 Months

9. Statistical Interpretation

10. Statistical Methods Explained

The primary outcome is continuous: percentage weight change at 6 months. The registry reports a mean and standard deviation for each arm. A mean describes the average value in a group, while a standard deviation describes how spread out individual values are around that average. In general, a mean difference compares the two group averages in the units of the outcome. Here, the registry’s comparison is usual care minus the Portion Control Intervention arm, so a positive difference corresponds to the usual-care mean being numerically higher than the intervention mean.

The reported primary means were -1.2 for the intervention arm and -0.4 for usual care. The comparison estimate was 0.8. The group standard deviations were 3.1 and 3.2, respectively. These summaries give a view of both the average contrast and the variation among participants, but they do not reveal the shape of each group’s outcome distribution or individual trajectories.

The registry reports a two-sided t-test for the primary comparison. In general, a t-test evaluates whether the observed difference between group means is inconsistent with a null hypothesis of no difference, under the test’s assumptions. A two-sided test considers departures in either direction rather than only a prespecified direction. The registry reports p = 0.31. A p-value is not a measure of the size or importance of a difference, and it is not the probability that the null hypothesis is true.

The reported 95% confidence interval for the primary comparison extends from a negative value to a positive value. In general, a confidence interval is a range of estimates compatible with the data and the statistical procedure under its assumptions. An interval that includes zero indicates that the data do not rule out a zero mean difference at the corresponding conventional two-sided threshold. It also shows that the estimate has uncertainty in both directions. The interval does not mean there is a 95% probability that the fixed true value lies inside this particular interval.

The recalculated comparison uses posted summary statistics and is described as unadjusted. It gives an estimate of 0.8 and p = 0.306. This is a simple recalculation, not a reanalysis using participant-level observations. It cannot reproduce procedures that depend on individual data, covariates, stratification, or other details that are not in the registry record. The sponsor’s reported analysis remains the relevant reported trial analysis.

The outcome summaries are means and standard deviations, and the reported analysis is a t-test. In general, methods based on means are most straightforward to interpret when the outcome distribution and sampling behavior are suitable for the method, or when the sample size supports a useful approximation. The registry record does not report diagnostic checks, transformations, covariate adjustments, or alternative analyses, so it is not possible to determine whether such procedures were used or considered.

The stated primary analysis population is intent to treat and includes all randomized subjects. In general, an intent-to-treat approach aims to preserve the randomized group comparison by analyzing participants according to their assigned groups, regardless of subsequent adherence. The registry says missing data were imputed using last observation carried forward. In general, this approach substitutes a participant’s last recorded observation for a later missing measurement. Its validity depends on assumptions about how outcomes would have changed after the last observation; the registry record does not report supporting assumptions or sensitivity analyses.

The registry reports an overall enrollment of 65, with 33 in the intervention arm and 32 in usual care. Those are the group counts listed with the primary outcome summaries. The record does not provide a separate accounting of the number with observed 6-month measurements, the number whose values were imputed, or reasons for missing measurements. Consequently, the impact of missingness cannot be quantified from the posted information.

In general, random allocation helps make groups comparable at the start of a trial, on average, but it does not guarantee balance in every feature, especially in a small study. The registry identifies the allocation as randomized but does not report how the sequence was generated or concealed. Masking is listed as none. For a behavioral intervention, masking participants or intervention providers may not be feasible, but the registry does not give further detail. It also does not report whether outcome assessment or analysis was masked.

The registry lists one primary and one secondary outcome measure, each with a reported analysis. It does not report a multiplicity adjustment, a detailed hierarchy among tests, or an analysis plan specifying how multiple comparisons would be handled. In general, testing several outcomes can increase the chance that at least one result appears notable by chance. This makes unadjusted secondary findings less secure as stand-alone evidence, especially when they are interpreted after looking across multiple outcomes or time points.

Planning figures are derived from the observed group contrast and stated planning assumptions; they are not a reconstruction of the trial’s original design calculation. The registry record does not report the trial’s own sample-size justification or its original assumptions about the effect to detect. The planning figures therefore describe hypothetical future study sizes under their stated conditions, rather than the achieved power of this trial.

11. Confidence Intervals and Precision

The primary mean difference is 0.8, defined as usual care minus the intervention arm. Its reported 95% confidence interval crosses zero, extending from a negative value to a positive value. That interval conveys important uncertainty: the observed estimate points in one direction, but the range of values compatible with the data includes no difference and values in the opposite direction.

The interval is relatively broad in relation to the point estimate, so the data do not locate the group contrast precisely. This is consistent with the modest enrollment of 65 and the variability represented by standard deviations of 3.1 and 3.2. The interval should be read as a range of plausible values under the statistical procedure, not as a guarantee about the true difference and not as a range containing most individual participants’ changes.

In general, confidence interval width depends on both variability and sample size, as well as the analysis method. More variable outcomes and smaller samples tend to produce less precise estimates. A confidence interval can therefore be informative even when a test does not cross a conventional significance threshold: it shows the range and direction of uncertainty, while a p-value condenses the evidence against a null hypothesis into a single measure.

The sponsor reports p = 0.31 for the primary comparison. The recalculated interval also spans zero, and its p-value is 0.306. The registry does not report the sponsor’s numerical confidence-interval bounds, so the posted confidence interval cannot be compared numerically with the recalculated bounds. The registry-reported estimate and test should be given priority when describing the sponsor’s analysis.

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 figures are participants per arm, not total events. This is a continuous-outcome comparison, so the figures describe hypothetical participants needed in each of two equally allocated groups. The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between the arms, and a normal approximation. The effect to detect is set to the stated fraction of the observed effect. The trial’s own original sample-size assumptions are not reported in the registry record.

For the primary outcome, planning for 100% of the observed effect gives 244 participants per arm for 80% power and 326 participants per arm for 90% power. Planning for 75% of the observed effect gives 433 participants per arm for 80% power and 580 participants per arm for 90% power. Planning for 50% of the observed effect gives 974 participants per arm for 80% power and 1,303 participants per arm for 90% power.

In general, 80% power means that, if the assumed effect and statistical assumptions were correct, a study of the stated size would have an 80% chance of detecting that effect at the stated significance level. The 90% column describes the corresponding chance as 90%. These are properties of a hypothetical design under its assumptions, not probabilities that the trial result is correct. The figures are not observed power for the completed study.

Smaller effects require more participants to detect with the same power under the same assumptions. A curve, if used to display these planning results, should be understood as a visual representation of how required sample size changes with the effect being planned for; its values inherit the same assumptions and are not a separate analysis of the completed trial.

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 = 0.800; pooled standard deviation σ = 3.150.
2. n = 2 × (1.96 + 0.842)² × 3.150² / 0.800² = 243.3, rounded up to 244 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 <- 0.8                      # observed difference in means
sigma <- 3.14960314960472                     # 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(1451554)
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 = 244 (80% power), 326 (90% power)
 75% of observed effect: n per arm = 433 (80% power), 580 (90% power)
 50% of observed effect: n per arm = 974 (80% power), 1,303 (90% power)
power.t.test: 244.3 
Simulated power at n = 244 per arm: 0.797 (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’s reported primary analysis is a two-sided t-test with p = 0.31. The registry does not report a sponsor-provided numerical estimate or confidence-interval bounds within its analysis entry; the group outcome summaries and comparison estimate are posted separately. The recalculated unadjusted comparison based on those summaries gives a mean difference of 0.8 and p = 0.306, with a confidence interval spanning zero.

The recalculated p-value is close to the sponsor-reported value, and both analyses convey uncertainty about the difference. The small numerical distinction is compatible with the fact that the sponsor’s reported p-value is rounded to two decimal places, while the recalculation is displayed to three. The registry does not document enough analysis detail to establish whether the two calculations use precisely the same procedures.

The recalculation is useful as a transparent check based on the posted means, standard deviations, and group sizes. It is not a replacement for the sponsor’s analysis and cannot capture unreported participant-level methods or adjustments. Because the discrepancy indicator is false, there is no recorded conflict requiring the sponsor result to be displaced; the sponsor’s reported analysis remains the main result to cite.

15. Multiplicity, Missing Data and Analysis Populations

The registry identifies weight change at 6 months as the primary outcome and weight change at 3 months as a secondary outcome. It reports one analysis for each. The record does not report a multiplicity adjustment, a formal hierarchy for testing the outcomes, or a rule governing how findings across time points would be combined. In general, when multiple hypotheses are tested, the chance of at least one apparently unusual result can increase. This is why an unadjusted secondary p-value is usually interpreted more cautiously than the result for a prespecified primary endpoint.

The registry describes the primary population as intent to treat and says it includes all randomized subjects. It also reports that missing data were imputed using last observation carried forward. The record does not report how many values were missing, when they were missing, the reasons for missingness, or whether missingness differed between arms. It does not report sensitivity analyses using other missing-data assumptions. These details matter because the estimated group means can depend on how missing observations are handled.

In general, carrying the last observed value forward assumes that this value is an adequate stand-in for a later unobserved value. That assumption may or may not be appropriate for a particular outcome and follow-up period. The registry record does not provide enough information to evaluate the assumption or to judge whether an alternative approach would change the comparison. The stated intent-to-treat population and imputation method should therefore be reported together, rather than treating the analysis as if all outcome values had been directly observed.

The registry record also does not report a detailed statistical analysis plan, analysis population definitions beyond the primary intent-to-treat description, interim analyses, or a sample-size justification. These omissions do not establish that such procedures were absent from the study’s broader documentation; they mean they cannot be evaluated from the registry record. Interpretation of the posted p-values and confidence intervals should remain tied to the analyses actually described there.

16. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 2% reporting threshold.

The registry reports serious adverse events for 33 participants at risk in the Portion Control Intervention arm and 32 participants at risk in Usual Care. It lists zero serious adverse events in each arm. For other adverse events, it likewise lists 33 and 32 participants at risk, with zero events in each respective arm.

These are the adverse-event counts posted in the registry record. They indicate that no serious or other adverse events were recorded in these categories for the listed groups in this record. They do not establish that no events occurred outside the reported categories or observation and reporting procedures. The registry does not report deaths for either arm; those values are not reported in the registry record.

In general, a zero count in a trial of this size does not prove that an event is impossible or that risk is absent. Adverse-event interpretation depends on how events were defined, collected, monitored, and reported, and those details are not given in the posted record. These figures are descriptive safety counts, not a statistical comparison demonstrating equivalent safety between the groups.

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

The registry reports a randomized comparison of a portion-control plate and dietary counseling with usual care for people with obesity in a primary-care setting. At 6 months, the intervention group’s mean percentage weight change was -1.2 and the usual-care mean was -0.4. The reported contrast was 0.8 for usual care minus intervention. The sponsor’s two-sided test gave p = 0.31, and the 95% confidence interval spans both negative and positive values.

Those findings show a numerical difference between the posted group means, but the uncertainty is substantial. The data do not establish that the groups differed, and they do not establish that the groups were identical. The estimate is compatible with a range of possible group contrasts. A non-significant test should not be read as proof of no effect, just as a directionally favorable point estimate should not be treated as proof of a meaningful effect.

The trial was described as a pilot study and enrolled 65 participants. Its findings can be read as preliminary evidence about the observed group averages in this study, not as a definitive answer for every primary-care setting or every population with obesity. The registry record does not report enough information about recruitment, participant characteristics, adherence, or missingness to determine how closely the enrolled group represents other settings.

The posted safety counts are zero serious adverse events and zero other adverse events in each arm, among the listed participants at risk. Those counts are reassuring as descriptions of what the registry record reports, but they do not demonstrate that adverse events cannot occur or that the two approaches have equivalent safety.

The findings do not establish a treatment recommendation, a long-term outcome, or the effect of the plate separately from counseling. The intervention combined those components, and the comparison was with booklets on diet and exercise. The registry record reports outcomes at 3 and 6 months, not longer-term follow-up. Its statistical results should be understood within those limits.

18. Why This Trial Matters Statistically

This trial is statistically informative because it illustrates the difference between the direction of a point estimate and the strength and precision of the evidence. The group means at 6 months are numerically different, with a more negative value in the intervention arm, but the confidence interval for the contrast crosses zero and the sponsor-reported p-value is 0.31. The estimate and its uncertainty need to be considered together.

The pilot scale is also relevant. With enrollment of 65, an estimate of the mean difference may be imprecise when compared with the variability in individual outcomes. A trial can produce a potentially useful estimate while still being unable to distinguish reliably among several plausible effect sizes. In general, that is one reason pilot results should be treated as groundwork for later study planning rather than as a final test of a clinical question.

The planning illustrations make the dependence of sample size on the effect of interest explicit. Under the stated assumptions, planning for a smaller fraction of the observed effect requires more participants per arm. This emphasizes that a future sample-size calculation should reflect the effect considered scientifically meaningful and the desired power, rather than simply copying an observed estimate from a small trial.

The record also highlights reporting issues that affect interpretation: the stated intent-to-treat population, last-observation-carried-forward imputation, the absence of reported missingness details, and the lack of a reported multiplicity strategy. These are not merely technical details. They shape how confidently readers can interpret the comparison and how strongly the secondary result should influence the overall conclusion.

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 registry record leaves important design and analysis details unreported. It does not give the original sample-size justification, the effect the investigators planned to detect, or the detailed statistical analysis plan. Sequence generation and allocation concealment are not described. Masking is listed as NONE, but the record does not explain whether outcome assessment or analysis was masked.

The primary outcome analysis is described as intent to treat with last observation carried forward for missing data. The number and timing of missing observations, reasons for missingness, and sensitivity analyses are not reported. Without those details, it is not possible to assess the extent to which imputation may have influenced the group summaries.

The registry reports a pilot study with 65 enrolled participants, and the confidence interval for the primary comparison spans values on both sides of zero. This limits precision. The record also does not report participant characteristics, adherence, or other information that would help evaluate how broadly the findings might apply. The intervention combines a plate with dietary counseling, so the posted comparison cannot separate the contributions of those components.

The registry lists one secondary outcome, weight change at 3 months, but does not report a multiplicity adjustment or testing hierarchy. The secondary result should therefore be read cautiously. The record reports adverse-event counts but does not detail collection methods, event definitions, or follow-up procedures. It does not report deaths for either arm. These limitations concern what can be assessed from the registry record and do not imply that unreported procedures or information were absent from other study materials.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Portion Control Treatment for Obesity — NCT01451554.
• Registry record last updated 2011-11-28; status last verified 2011-10.
• Results first posted 2011-11-28.
• 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

NCT01451554 is a completed randomized, parallel-group study sponsored by Mayo Clinic, listed as PHASE2 and PHASE3 and with masking listed as NONE. It enrolled 65 participants with obesity in a primary-care setting. The Portion Control Intervention combined a portion-control plate and dietary counseling; Usual Care consisted of self-help booklets on diet and exercise.

The primary outcome was mean percentage weight change at 6 months. The posted means were -1.2 for the intervention arm and -0.4 for usual care. The sponsor-reported two-sided t-test gave p = 0.31; the 95% confidence interval for the mean difference spans zero. The registry also reports weight change at 3 months as a secondary outcome. The primary analysis population included all randomized subjects, with missing data imputed using last observation carried forward.

The registry reports zero serious adverse events and zero other adverse events in each arm. Original sample-size justification, detailed missing-data information, and a full statistical analysis plan are not reported in the registry record.