A Randomized, Double-Blind, Placebo-Controlled Study of Oral Milk Immunotherapy for Cow's Milk Allergy: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Randomized, Double-Blind, Placebo-Controlled Study of Oral Milk Immunotherapy for Cow's Milk Allergy (NCT00465569), a randomized phase 1, phase 2 study. The primary outcome is The Median Milk Threshold Dose Inducing a Reaction.

2. Clinical Question

3. Trial Design

The registry describes a randomized, parallel-group study comparing oral cow’s milk powder with placebo. Its title identifies the study as double-blind, while the registry’s masking classification is quadruple. The identities of the people or roles covered by that masking classification are not reported in the registry record. The study is listed as Phase 1 and Phase 2, and its status is completed.

The stated purpose was to determine whether small oral doses of milk protein were safe and effective in decreasing sensitivity to cow’s milk in allergic children. The active-treatment description specifies pre-measured doses of dry, nonfat powdered milk prepared by clinical research-registered dieticians. The placebo description is blank, and the dose schedule, administration details, and treatment duration are not reported in the registry record.

The registry lists an enrollment of 20. The study start is recorded as 2006-08 and primary completion as 2008-06. One participant in the active-treatment arm did not complete the study because of persistent eczema during dose escalation. The number of participants included in each outcome analysis, and the number completing each assessment, are not reported in the registry record.

The primary outcome is the median milk threshold dose inducing a reaction, with a stated timeframe of baseline and 23 weeks. Changes in Cow Milk-IgE and Cow Milk Immunoglobulin G4 (IgG4) are listed as secondary outcomes. The record does not report a statistical analysis plan, allocation procedures beyond randomization, or details about how the outcome assessments were conducted.

4. Participant Flow and Accounting

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

Before assignment: Eligibility criteria were a positive skin prick test (SPT) response to milk extract (wheal ≥ histamine control) or milk immunoglobulin E (IgE) level of \> 0.35 kilounits per liter (kU/L) and a positive milk challenge result at baseline defined as reacting with clear signs, symptoms, or both to a cumulative dose of 2.5 g or less of milk protein.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: One participant in the active treatment arm did not complete the study due to persistent eczema during dose escalation. The median milk threshold dose in both groups was 40 with a full range of 40-1340 at the baseline challenge.

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 The Median Milk Threshold Dose Inducing a Reaction, measured over Baseline and 23 weeks.

The primary endpoint is described as the median milk threshold dose that induces a reaction. A threshold dose is the amount of milk associated with a reaction during a challenge; the endpoint is intended to capture how much milk a participant can receive before a reaction is induced. The unit is recorded as “miligrams.” The registry states that the endpoint was assessed at baseline and 23 weeks.

As a general statistical concept, a threshold can summarize response on a dose scale, while the median describes the middle of the observed distribution. This can be useful when individual thresholds vary or when a typical value is more informative than an arithmetic mean. The full range gives the lowest and highest reported values, but does not show how observations are distributed between those endpoints.

The posted primary-outcome description reports that both groups had a baseline median of 40, with a full range of 40-1340. It does not provide the corresponding 23-week values or a treatment-group comparison. The endpoint’s stated timeframe alone does not establish that follow-up results were reported. Consequently, the record does not permit an assessment of change in the median threshold or of the uncertainty around a between-group effect.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry identifies a randomized, parallel-group study with active treatment and placebo. Randomization is a design method for assigning participants to groups by chance. In general, this can help make groups comparable with respect to measured and unmeasured characteristics, but the registry record does not report the sequence-generation method, allocation concealment, or evidence about balance between groups. The study title says double-blind; the registry classifies masking as quadruple. The roles masked and the procedures used to maintain masking are not reported in the registry record.

What does the reported median describe?

The primary endpoint is the median milk threshold dose inducing a reaction. In general, the median is the middle value after observations are ordered. It describes a central point without requiring that the data follow a particular symmetric shape. The registry reports a baseline median of 40 in each group and a full range of 40-1340 in each group. The range gives only the minimum and maximum; it does not indicate how observations are distributed between them. The record does not provide further distributional summaries or participant-level results.

What would a group comparison require?

In general, an estimate of treatment effect would need to define the contrast between groups and the time point or change being compared. A confidence interval can communicate the range of effect sizes compatible with the data and the analysis assumptions; its width reflects precision. A p-value addresses compatibility with a specified null hypothesis under an analysis model, but does not measure effect size or clinical importance. The registry record reports no primary-outcome effect estimate, confidence interval, or p-value. It also does not specify whether the intended comparison was based on 23-week values, change from baseline, or another approach. No such analysis should be inferred from the baseline summaries.

Why does the analysis model matter?

As a general principle, the choice of analysis should reflect the outcome’s distribution, the design, and the question being asked. Threshold measurements may be summarized or modeled in different ways, and an analysis of change can differ from an analysis of follow-up values. The registry does not report a statistical analysis plan, model, adjustment variables, or assumptions for the primary endpoint. It therefore does not establish which approach was intended or used. General statistical explanations do not fill that gap.

How should the secondary outcomes be understood?

Changes in Cow Milk-IgE and Changes in Cow Milk Immunoglobulin G4 (IgG4) are listed as secondary outcomes. The registry record does not provide their numerical results, analysis methods, or comparisons. In general, secondary outcomes can add information about other measured responses, but their interpretation depends on the prespecified questions, methods, and multiplicity approach. Those details are not reported in the registry record.

What can the sample-size information establish?

The record describes planning illustrations based on an observed effect, a two-sided significance level of 0.05, equal allocation between groups, and a normal approximation. Such illustrations are conditional calculations: they indicate a hypothetical number of participants per arm for a chosen detectable effect under stated assumptions. They are not observed power, and they do not show that the original trial was designed or powered using those assumptions. The trial’s own sample-size justification and planning assumptions are not reported in the registry record. Because the primary outcome was not reduced to one comparison, no single effect comparison is available to interpret as the observed result.

Over-dispersion is a general issue when observed variability exceeds what a chosen statistical model expects. If present and ignored, uncertainty estimates can be too small. The registry record does not report a model or diagnostic information for this outcome, so there is no basis to say whether over-dispersion was assessed or relevant to the analysis. More broadly, no reported model, inferential result, or follow-up summary supports a precise estimate of the primary treatment contrast.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists one primary outcome and two secondary outcomes: changes in Cow Milk-IgE and Cow Milk Immunoglobulin G4 (IgG4). It also records three outcome measures overall, but does not provide a full description of each measure or the relationship between the listed outcomes and that count. The statistical plan for handling multiple outcomes or comparisons is not reported in the registry record.

As a general concept, testing several outcomes can increase the chance of a nominally unusual result arising by chance when each is assessed separately. Methods for addressing multiplicity depend on which comparisons were prespecified and the intended interpretation. No adjustment method, testing hierarchy, or distinction between confirmatory and exploratory analyses is reported. The registry provides no analysis results for the listed secondary outcomes.

The registry reports that one participant in the active-treatment arm did not complete the study because of persistent eczema during dose escalation. It does not report the number of missing outcome values at each time point, reasons for any other missingness, or the method used to handle missing data. The analysis population is not reported in the registry record: it is not stated whether results were intended for all randomized participants, participants who completed treatment, or another group. The number of participants contributing to the baseline and 23-week summaries is also not reported.

These omissions limit interpretation of both the primary and secondary outcomes. They prevent readers from determining how incomplete follow-up was addressed, whether all randomized participants were included in an analysis, and how multiple outcome tests were interpreted.

11. 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.

Most frequent non-serious adverse event terms

The adverse-event record lists 0 serious events and 0 deaths for both Active Treatment and Placebo. It also records serious-event at-risk values of 2437 for Active Treatment and 1193 for Placebo, and other-event at-risk values of 2437 and 1193, respectively. For other events, the recorded affected counts are 1107 for Active Treatment and 134 for Placebo.

These entries require caution. The at-risk and affected figures are not reconciled with the registry’s enrollment of 20, and the units or counting basis for these values are not reported in the registry record. They should therefore be read as recorded figures, not assumed to be participant counts or converted into rates. The registry lists no top serious-event terms, but does not provide further detail about the collection, definitions, or reporting of adverse events.

The recorded zero serious events and zero deaths do not, by themselves, establish that there were no other safety events or quantify safety risk. The non-serious figures cannot be interpreted as proportions of participants from the information reported. The study’s small listed enrollment and the unresolved units further limit safety interpretation.

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

The record describes a randomized, parallel-group comparison of oral cow’s milk powder with placebo in children with cow’s milk allergy. It identifies a primary endpoint based on the milk threshold dose inducing a reaction, assessed at baseline and 23 weeks. At baseline, both groups are reported to have a median threshold of 40 and a full range of 40-1340.

Those baseline descriptions do not show whether the threshold changed during the study or whether change differed between groups. The 23-week outcome values, an effect estimate, and measures of statistical uncertainty are not reported in the registry record. The posted results therefore do not establish the direction or magnitude of a treatment-group difference, and they do not support a claim about the precision of such a difference.

The registry reports that one participant in the active-treatment arm did not complete the study because of persistent eczema during dose escalation. It does not explain how missing outcomes were handled or identify the analysis population. The safety entries record no serious events and no deaths in either group, but other event counts and at-risk values are not reconciled with enrollment, and their units are not reported. These data do not provide a complete, interpretable estimate of safety outcomes.

More generally, a study’s stated purpose and randomized design are not substitutes for reported comparative results. The available registry information can describe the intended question, design, baseline threshold summaries, one reported non-completion, and the recorded adverse-event entries. It cannot establish efficacy, safety, or the statistical certainty of a treatment effect from the primary outcome.

13. Why This Trial Matters Statistically

This record illustrates why the endpoint definition, the assessment schedule, and the actual reported results all matter. A threshold dose may be intended to represent sensitivity on a dose scale, but a baseline summary alone cannot answer whether the endpoint changed over time or whether the groups differed at follow-up. The stated 23-week timeframe does not replace the missing follow-up values.

The equal baseline medians and ranges are descriptive, not a treatment comparison. A valid interpretation of change would require the relevant follow-up information and a clearly specified contrast. Without reported estimates and uncertainty, readers cannot distinguish a small imprecisely estimated difference from a larger, more precisely estimated one. The registry does not report the inferential analysis needed to make that distinction.

The record also shows the importance of documenting analysis populations and missing-data handling. One active-treatment participant is reported not to have completed the study, but the number included in each analysis and the treatment of missing measurements are not reported. These details affect how outcome summaries relate to the randomized groups.

Finally, registry adverse-event entries need interpretable units and definitions. Here, the recorded at-risk and affected values do not reconcile with the enrollment count, and the counting basis is not reported. Reporting values without enough context can make even simple safety summaries difficult to interpret. These limitations are statistical and reporting concerns; they do not determine what the unreported study results would have shown.

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 registry record does not provide the 23-week primary-outcome values, a between-group estimate, or an inferential analysis. Although the primary endpoint is described at baseline and 23 weeks, only the baseline median and full range are included in the posted primary-outcome description. No confidence interval or p-value is reported.

The record lists an enrollment of 20 and notes that one participant in the active-treatment arm did not complete the study because of persistent eczema during dose escalation. It does not report the group-specific numbers analyzed, the completion status of all participants, the amount of missing outcome data, or the approach used to handle missingness. The analysis population is not reported in the registry record.

Important design and analysis details are also absent. The record does not report the randomization method, allocation concealment, the roles covered by masking, the dose schedule, the placebo contents, the statistical analysis plan, or a sample-size justification. The registry’s masking classification is quadruple, while the title calls the study double-blind; the difference in terminology is not explained.

The secondary outcomes are named but their results and methods are not reported. The registry does not describe how multiplicity was addressed. Adverse-event at-risk and affected values are difficult to interpret because their units and counting basis are not stated and the values do not reconcile with the listed enrollment. These reporting gaps limit assessment of comparative outcomes and safety.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: A Randomized, Double-Blind, Placebo-Controlled Study of Oral Milk Immunotherapy for Cow's Milk Allergy — NCT00465569.
• Registry record last updated 2017-04-20; status last verified 2017-04.
• Results first posted 2017-04-20.
• 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 describes a completed Phase 1 and Phase 2 randomized, parallel-group, placebo-controlled study of oral milk immunotherapy for cow’s milk allergy. Enrollment was 20. The active intervention was pre-measured dry, nonfat powdered milk; placebo details are not reported. The primary endpoint was the median milk threshold dose inducing a reaction at baseline and 23 weeks. The posted baseline median was 40 in both groups, with a full range of 40-1340. Follow-up results and a comparative analysis are not reported in the registry record. One active-treatment participant did not complete the study because of persistent eczema during dose escalation. Changes in Cow Milk-IgE and IgG4 are listed as secondary outcomes, but their results are not reported.