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 limited to the information from the registry data for XPORT.
1. Trial at a Glance
XPORT was a randomized, double-blind, parallel phase 4 clinical trial evaluating the persistency of response with or without Xolair (omalizumab) after long-term therapy in participants with allergic asthma.
| Feature | XPORT |
|---|---|
| Trial name | XPORT |
| NCT ID | NCT01125748 |
| Brief title | A Study Evaluating the Persistency of Response With or Without Xolair (Omalizumab) After Long-term Therapy |
| Phase | Phase 4 |
| Status | COMPLETED |
| Therapeutic area | Pulmonology |
| Condition | Allergic Asthma |
| Enrollment | 176 |
| Allocation | Randomized |
| Design model | Parallel |
| Masking | Double |
| Primary purpose | Treatment |
| Lead sponsor | Genentech, Inc. |
| Sponsor type | Industry |
| Start | 2010-05 |
| Primary completion | 2013-08 |
2. Clinical Question
The central clinical-trial question was whether the persistency of response after long-term therapy differed between participants assigned to omalizumab and those assigned to placebo.
Population
Participants with allergic asthma enrolled in the XPORT randomized phase 4 study.
Intervention
Omalizumab, with asthma therapies.
Comparator
Placebo, with asthma therapies.
Primary question
Does the percentage of participants not experiencing a protocol-defined severe exacerbation differ between the omalizumab and placebo groups during the study?
3. Trial Design
Omalizumab group
- Omalizumab (drug)
- Asthma therapies (drug)
- Serious adverse events: 10/121 affected/at risk
Placebo group
- Placebo (drug)
- Asthma therapies (drug)
- Serious adverse events: 8/88 affected/at risk
4. Primary Endpoint
| Endpoint | Registry definition / time frame | Type | Formal analysis |
|---|---|---|---|
| Percentage of Participants Not Experiencing a Protocol-defined Severe Exacerbation During the Study | Baseline to the end of the study (up to 52 weeks) | Binary | Yes |
The registry defines the primary endpoint as the percentage of participants not experiencing a protocol-defined severe exacerbation during the study, assessed from baseline to the end of the study, up to 52 weeks.
5. Statistical Methodology
The posted primary analysis used the intent-to-treat population: all randomized participants. The registry reports a comparison of omalizumab versus placebo using a mean difference in final values. The hypothesis type is superiority.
| Statistical feature | Registry information |
|---|---|
| Analysis population | Intent-to-treat population: All randomized participants. |
| Groups compared | Omalizumab vs Placebo |
| Endpoint type | Binary |
| Effect measure | Mean Difference (Final Values) |
| Estimate | 19.3 |
| Confidence interval | 95% two-sided CI: 5.0 to 33.6 |
| Hypothesis type | Superiority |
| Named analysis concept | Intention-to-treat analysis |
| Method reported by registry | Not reported |
| Method category reported by registry | Not reported |
6. Primary Result
The ClinicalTrials.gov data contain one formal statistical analysis for the primary endpoint. The analysis compares omalizumab with placebo in the intent-to-treat population.
Percentage of Participants Not Experiencing a Protocol-defined Severe Exacerbation
Mean difference in final values
95% two-sided CI: 5.0–33.6
Hypothesis type: Superiority
| Primary endpoint | Analysis population | Comparison | Effect measure | Estimate | 95% CI |
|---|---|---|---|---|---|
| Percentage of Participants Not Experiencing a Protocol-defined Severe Exacerbation During the Study | Intent-to-treat population: All randomized participants. | Omalizumab vs Placebo | Mean Difference (Final Values) | 19.3 | 5.0 to 33.6 |
The reported mean difference of 19.3 describes the registry's estimated difference in final values for the percentage of participants not experiencing a protocol-defined severe exacerbation, comparing omalizumab with placebo. Because the registry labels the effect measure as a mean difference, the number should be interpreted according to that reported analysis rather than silently converted into a different effect measure.
The estimate does not mean that every individual participant experienced a 19.3-unit improvement, nor does it provide an individual-level probability of avoiding a severe exacerbation. It is a group-level treatment comparison.
The 95% two-sided confidence interval of 5.0 to 33.6 describes statistical uncertainty around the reported estimate under the analysis framework. It does not describe the range of responses that individual participants can experience.
A confidence interval and a p-value answer different questions. The ClinicalTrials.gov record provides the confidence interval but does not provide a numerical p-value. A p-value, when reported, would quantify evidence against the null hypothesis under a specified testing framework; it would not measure the size or clinical importance of the effect.
Because the registry does not report the statistical method, stratification, missing-data handling, or a formal testing procedure beyond identifying the analysis as superiority, those features should not be inferred from the estimate alone.
7. How to Interpret the Confidence Interval
The confidence interval is particularly important because the point estimate alone does not communicate the precision of the comparison.
The interval gives a range of values compatible with the estimated treatment contrast under the statistical framework used to generate it. Its width reflects uncertainty in the estimate.
What the point estimate says
The registry's estimated mean difference in final values was 19.3 for omalizumab versus placebo.
What the interval says
The registry-reported 95% two-sided confidence interval extends from 5.0 to 33.6, showing the statistical uncertainty around the estimate.
What it does not say
It does not describe the response range for individual participants or guarantee that a future study will produce an estimate inside the same interval.
Why method matters
The registry does not identify the formal calculation method, so interpretation should remain tied to the reported mean-difference analysis rather than a reconstructed method.
8. Intention-to-Treat Analysis
The posted primary analysis used the intent-to-treat population: all randomized participants. This is a central design principle in randomized clinical trials because participants remain associated with the treatment group to which they were randomized for the efficacy comparison.
The purpose is to preserve the comparison created by randomization rather than redefining treatment groups according to what participants subsequently received.
For XPORT, the registry explicitly identifies ITT as the analysis population for the posted primary endpoint. That is stronger evidence than attempting to infer the analysis population from the treatment arms or enrollment figure.
Why ITT matters for this endpoint
The primary endpoint is binary: whether a participant did or did not experience a protocol-defined severe exacerbation during the study period. Using all randomized participants as specified maintains the randomized comparison and avoids selectively excluding participants based on subsequent events or treatment exposure.
9. Randomization and Blinding
XPORT was registered as a randomized, double-blind, parallel trial. These design features are directly relevant to the statistical interpretation of the treatment comparison.
Randomization
Randomized allocation is intended to create comparable groups at baseline in expectation and provides the foundation for interpreting between-group differences as treatment effects within the trial.
Double blinding
Double blinding can reduce the influence of knowledge of treatment assignment on participant behavior, investigator decisions, assessment, and other aspects of trial conduct.
Parallel design
Participants were assigned to one of two parallel study arms rather than being described in the registry as crossing between treatment sequences.
Statistical implication
The posted primary analysis compares the randomized treatment groups using the ITT population, aligning the analysis with the randomized design.
10. Results Reported Beyond the Primary Analysis
The ClinicalTrials.gov record states that 2 outcome measures were posted and that 1 statistical analysis was posted. Only one formal statistical analysis is included in the ClinicalTrials.gov record, and it corresponds to the primary endpoint.
| Results component | Information available in the ClinicalTrials.gov record |
|---|---|
| Outcome measures posted | 2 |
| Statistical analyses posted | 1 |
| Primary-endpoint analyses | 1 |
| Primary analyses with estimate + CI | 1 |
| Primary formal analysis | Percentage of Participants Not Experiencing a Protocol-defined Severe Exacerbation During the Study |
| Additional formal statistical results | Not contained in the ClinicalTrials.gov record |
11. Safety Results
The ClinicalTrials.gov record provides serious adverse events by treatment arm as affected participants over those at risk. These counts should be reported separately from the primary efficacy analysis because safety and efficacy address different dimensions of the trial.
| Safety measure | Omalizumab | Placebo |
|---|---|---|
| Serious adverse events, affected / at risk | 10/121 | 8/88 |
Omalizumab
Serious adverse events affected 10 participants among 121 at risk, according to the ClinicalTrials.gov record.
Placebo
Serious adverse events affected 8 participants among 88 at risk, according to the ClinicalTrials.gov record.
12. Statistical Methods Explained
Why was an intention-to-treat analysis used?
The registry identifies the primary analysis population as all randomized participants. An ITT analysis keeps participants associated with their randomized treatment assignment, preserving the principal comparison generated by randomization. This is especially important when treatment exposure or follow-up differs after randomization.
What does a mean difference of 19.3 mean?
The registry reports a mean difference in final values of 19.3 for omalizumab versus placebo. Because the underlying endpoint is a percentage of participants and the registry labels the effect measure as a mean difference, the safest interpretation is the reported group-level contrast. The ClinicalTrials.gov record does not provide the arm-specific final percentages, so those values are not reconstructed here.
What does the 95% confidence interval of 5.0 to 33.6 tell us?
It expresses uncertainty around the estimated mean difference. The interval is two-sided and has a 95% confidence level. It should not be interpreted as containing 95% of individual participant outcomes.
Why not report a hazard ratio?
The primary endpoint is binary and is evaluated over baseline to the end of the study, up to 52 weeks. The registry reports a mean difference rather than a hazard ratio. A hazard ratio would require a time-to-event analysis and is not an effect measure reported for the posted primary analysis.
Why not replace the mean difference with a risk ratio or odds ratio?
Different measures of binary treatment effect answer different questions and can have materially different numerical interpretations. The ClinicalTrials.gov record explicitly identify the effect measure as mean difference, so replacing it with a different measure would constitute an analysis not contained in the ClinicalTrials.gov record.
Why does the p-value matter, and why is it absent here?
A p-value would describe the evidence against a specified null hypothesis under a defined testing procedure. However, the ClinicalTrials.gov record contains no numerical p-value.
Why is the analysis population important?
The posted analysis uses all randomized participants. This connects the statistical analysis directly to the randomized design and helps preserve the comparability created by random allocation. The ClinicalTrials.gov record does not describe separate per-protocol or as-treated efficacy analyses.
13. What the Primary Estimate Does — and Does Not — Mean
The reported mean difference of 19.3 is the estimated final-value contrast between omalizumab and placebo for the primary binary endpoint, using the intent-to-treat population.
It does not mean that every participant experienced a 19.3-unit change, nor does it establish the magnitude of benefit for any individual participant.
The 95% two-sided CI of 5.0 to 33.6 describes uncertainty around the reported treatment contrast. A narrower interval would indicate greater statistical precision, while a wider interval would indicate more uncertainty.
The ClinicalTrials.gov record does not report a numerical p-value.
The endpoint is binary, but the posted effect measure is a mean difference in final values. The registry does not provide enough methodological detail in the ClinicalTrials.gov record to determine whether the analysis used a particular regression model, covariance adjustment, or transformation.
14. Missing Data and Analysis Details
The registry data posted on ClinicalTrials.gov for XPORT identify the analysis population and effect measure but do not report several methodological details that can materially affect a binary-endpoint analysis.
| Methodological topic | What the ClinicalTrials.gov record reports |
|---|---|
| Missing-data / imputation method | Not reported |
| Statistical method | Not reported |
| Stratification factors | Not reported |
| Interim analysis | Not reported |
| Multiplicity adjustment | Not reported |
| Non-inferiority margin | Not applicable to the reported superiority hypothesis; no margin is reported |
| Crossover | Not reported |
| Bayesian methods | Not reported |
These omissions are important because a point estimate cannot reveal how missing observations were handled, whether covariates were adjusted for, or whether any multiplicity or interim-monitoring procedure affected the inferential framework.
15. Superiority Hypothesis
The registry identifies the hypothesis type for the posted primary analysis as superiority. This means the statistical question is framed around whether the treatment groups differ in the specified direction under a superiority-testing framework, rather than whether one treatment is merely not unacceptably worse than another.
Superiority
The goal is to evaluate whether the randomized groups differ in the endpoint under the prespecified superiority framework.
Non-inferiority
No non-inferiority margin is reported in the ClinicalTrials.gov record, and the posted analysis is explicitly identified as superiority.
The distinction matters because confidence intervals are interpreted differently depending on the hypothesis being tested. A superiority analysis asks whether the treatment contrast is compatible with a meaningful difference under the specified null hypothesis; a non-inferiority analysis instead requires the confidence interval to be evaluated against a prespecified clinically acceptable margin.
16. Trial Timeline
Trial start
The XPORT study began in May 2010 according to the ClinicalTrials.gov record.
Primary endpoint assessment period
The primary endpoint was assessed from baseline to the end of the study, up to 52 weeks.
Primary completion
The ClinicalTrials.gov record lists August 2013 as the primary completion date.
Trial status
The registry identifies the overall study status as completed.
17. Statistical Interpretation of the Trial Design
The XPORT design provides a useful example of how several core clinical-trial concepts fit together without requiring a complex time-to-event model. The study is randomized, double-blind, parallel, and superiority-focused. Its primary endpoint is binary, while the posted effect measure is a mean difference in final values.
| Concept | How it appears in XPORT |
|---|---|
| Randomization | Participants were randomized to two parallel treatment groups. |
| Blinding | The registry identifies the study as double-blind. |
| ITT analysis | The primary analysis population was all randomized participants. |
| Binary endpoint | The primary endpoint is whether participants did not experience a protocol-defined severe exacerbation. |
| Mean difference | The posted effect measure was Mean Difference (Final Values). |
| Confidence interval | The reported estimate has a 95% two-sided CI of 5.0 to 33.6. |
| Superiority | The posted hypothesis type was superiority. |
| Registry transparency | The ClinicalTrials.gov record does not identify the formal statistical method used to produce the estimate. |
18. Limitations
- Limited statistical-method detail: The ClinicalTrials.gov record does not identify the statistical method or method category used for the primary analysis.
- No numerical p-value: The primary statistical-analysis record provides an estimate and confidence interval but no numerical p-value.
- No arm-specific endpoint percentages: The ClinicalTrials.gov record does not give the final percentage of participants not experiencing a severe exacerbation in each arm.
- Missing-data handling not reported: The ClinicalTrials.gov record does not describe imputation, missingness assumptions, or treatment of participants without an evaluable endpoint.
- No reported stratification: The ClinicalTrials.gov record does not identify stratification variables.
- No reported interim-analysis framework: No interim-analysis or alpha-spending strategy is contained in the ClinicalTrials.gov record.
- Safety denominator differences: Serious adverse events are reported using arm-specific affected/at-risk counts of 10/121 and 8/88, which should not be replaced with the overall enrollment of 176.
- Limited secondary-results information: Two outcome measures were posted, but the ClinicalTrials.gov record contains only one formal analysis.
- No subgroup analysis data: No subgroup estimates, confidence intervals, or interaction analyses are included in the ClinicalTrials.gov record.
19. Why This Trial Matters Statistically
XPORT is useful as a teaching case because it demonstrates how a randomized clinical trial can produce a treatment comparison for a binary clinical endpoint while leaving important methodological questions visible in the registry record.
| Concept | What XPORT illustrates |
|---|---|
| Randomization | Two parallel groups were created through randomized allocation. |
| Blinding | The trial was double-blind. |
| ITT principle | The posted primary analysis included all randomized participants. |
| Binary outcome | The primary endpoint classifies participants according to whether they experienced the specified event. |
| Mean difference | The registry reports a mean difference in final values as the treatment effect measure. |
| Confidence intervals | The 95% two-sided interval communicates uncertainty around the point estimate. |
| Superiority testing | The formal hypothesis type is identified as superiority. |
| Statistical transparency | The registry supplies the analysis population and estimate but does not identify the statistical method. |
| Safety analysis | Serious adverse events are reported separately by treatment arm using affected/at-risk counts. |
20. Related Tutorials
Learn more about the methods used in this trial:
21. Related Calculators
22. Sources
- ClinicalTrials.gov: XPORT, NCT01125748.
Continue through Clinical Biostats
Explore statistical tutorials, clinical-trial methods, and practical calculators for understanding randomized-study evidence.
23. Record Summary
XPORT is a completed phase 4, randomized, double-blind, parallel clinical trial in allergic asthma. The ClinicalTrials.gov record reports a primary binary endpoint measuring the percentage of participants not experiencing a protocol-defined severe exacerbation during the study, from baseline to the end of the study, up to 52 weeks. The primary formal analysis used the intent-to-treat population and compared omalizumab with placebo using a reported mean difference in final values of 19.3, with a 95% two-sided confidence interval of 5.0 to 33.6.
The statistical record is notable not only for the reported treatment contrast but also for what the registry does and does not specify. The analysis method and method category are not reported in the ClinicalTrials.gov record, and no numerical p-value is provided. Consequently, the appropriate interpretation is to preserve the reported effect measure and confidence interval rather than reconstructing an unreported model. The ClinicalTrials.gov record separately report serious adverse events of 10/121 for omalizumab and 8/88 for placebo.