To Assess the Efficacy of Esomeprazole 40 mg Once Daily in Subjects Who Still Had Heartburn After Receiving Rabeprazole: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for To Assess the Efficacy of Esomeprazole 40 mg Once Daily in Subjects Who Still Had Heartburn After Receiving Rabeprazole (NCT01249651), a na phase 4 study. The primary outcome is Change in the Frequency of Heartburn During the 7-day Period Prior to the 8 Week Visit (Visit 3) Compared to the Frequency of Heartburn During the 7-day Period Prior to Baseline (Visit 1).

2. Clinical Question

In practical statistical terms, the question is whether heartburn frequency was different at the later assessment than at baseline among participants represented in the primary analysis. A within-group change can describe what happened over time in this study group, but it cannot by itself separate a treatment effect from other influences. Those may include the natural course of symptoms, changes in reporting, expectations associated with an open-label study, or events occurring during follow-up. With no concurrent control group, the record cannot establish what would have happened to comparable participants over the same period without the study treatment.

The primary outcome is a count of days with heartburn in a 7-day reporting period, summarized as a mean and standard deviation. That makes the endpoint interpretable as average symptom frequency, while leaving important details about individual responses unrepresented by the mean alone. The registry record does not report the actual average at baseline or follow-up, the estimated mean change, or an interval describing its precision. Consequently, the clinical question can be identified, but the direction and magnitude of the observed result cannot be assessed from the registry record.

3. Trial Design

This was a phase 4, open-label, multicentre study of esomeprazole 40 mg once daily. Its official title describes an 8-week study in participants with continuing heartburn following treatment with a previous rabeprazole. The brief summary specifies prior rabeprazole 20 mg once daily for 4 to 8 weeks. The registry lists one arm and identifies the model as single group. Allocation is recorded as not applicable, consistent with the absence of a randomized arm comparison.

The study enrolled 101 participants. The primary outcome description identifies the full analysis set as 96 participants. These are different counts attached to different descriptions in the registry record; the record does not explain the reasons for the difference or describe how the analysis population was formed. The safety summary gives a risk set of 100 for the displayed adverse-event categories. These denominators should be read in the context of their stated purposes rather than treated as interchangeable.

The primary outcome covers change from baseline to the 8-week visit. At each assessment, heartburn frequency refers to the number of days with heartburn during the preceding 7-day period. The record also lists secondary outcomes concerning frequency at the 4-week visit and maximum severity at the 4-week and 8-week visits. The descriptions of the severity outcomes refer to comparison with baseline frequency, so the registry wording does not make the measurement comparison entirely clear.

The study is marked completed. Its recorded start is 2010-11 and its primary completion is 2011-06. The sponsor is AstraZeneca. The registry record does not report a concurrent placebo or active comparator, masking, or a randomized allocation scheme. It also does not report a detailed statistical analysis plan, the rationale for the enrollment target, or the procedures used to address missing observations. These omissions limit the extent to which the design and analysis can be independently evaluated beyond the basic structure described in the record.

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: Participants with a history of reflux oesophagitis and with continuing heartburn after previous treatment with rabeprazole 20 mg were included in this study.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full analysis set (96 participants)

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 Change in the Frequency of Heartburn During the 7-day Period Prior to the 8 Week Visit (Visit 3) Compared to the Frequency of Heartburn During the 7-day Period Prior to Baseline (Visit 1), measured over Baseline to 8 weeks.

The primary endpoint is change in the number of days with heartburn, measured by comparing the 7-day period before baseline with the 7-day period before the 8-week visit. The unit is number of days, and the registry describes the outcome as a mean with standard deviation. This measure focuses on how often symptoms occurred, rather than their maximum severity or another aspect of symptom experience.

A frequency measure can be useful because it gives a direct description of the number of days affected during a defined recall period. Comparing the same measure over time also makes the endpoint suitable for describing within-group change. The mean summarizes the group’s average change, while the standard deviation describes variation among the observations. Neither alone reveals the full distribution: participants may have different starting frequencies and different changes, even when their average change is similar.

As a general statistical point, an endpoint is most informative when its definition, analysis population, and time window are clear. Here, the registry identifies the time windows and primary population, but does not report the numerical baseline or follow-up means, the mean change, its confidence interval, or a test result. It therefore does not establish how large or precise the observed change was. A before-and-after endpoint can describe change over time, but without a concurrent comparison group it cannot isolate the effect attributable to treatment.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous in the sense that it is analyzed as a numerical measure and summarized by a mean. Its underlying value is the number of days with heartburn in the 7-day period before a visit. The primary comparison is between the value before baseline and the value before the 8-week visit. The record describes the analysis as a difference in the number of heartburn days from baseline to 8 weeks, but does not provide the estimated difference or identify the exact statistical test used.

What does a mean change describe?

In general, a mean change is an average of participants’ within-person changes between two assessments. This can be more informative than comparing group averages without regard to pairing, because each participant’s follow-up measurement is linked to that participant’s baseline measurement. A mean change is still a summary: it does not show whether most participants changed by a similar amount, whether some changed in opposite directions, or whether a small number of observations strongly influenced the average. The registry record does not report individual-level results or other distributional summaries for the primary endpoint.

The standard deviation is listed as the dispersion measure. In general, a standard deviation describes how spread out observations are around their mean. It is not the same as a confidence interval: the standard deviation describes variability in the data, whereas a confidence interval describes uncertainty about an estimated quantity. Because the registry record does not report the primary result’s standard deviation or confidence interval, neither the spread of observed changes nor the precision of the mean change can be assessed from this entry.

How should a confidence interval be read?

As a general statistical explanation, a confidence interval gives a range of values compatible with an estimate under the assumptions of the analysis. A narrower interval indicates greater precision than a wider interval, while the interval’s position helps show which effect sizes remain plausible. An interval around a mean change could help readers distinguish a precisely estimated small change from an imprecisely estimated change. No such interval is reported for the primary outcome in the registry record, so its uncertainty cannot be described numerically.

What would a significance test establish?

In general, a significance test evaluates how compatible the observed data are with a specified null hypothesis, under the statistical model and its assumptions. A small p-value would not measure the size or importance of a change, and it would not show that the treatment caused the change. The registry record does not report a p-value or identify the primary test. The brief summary’s stated expectation of a statistically significant improvement is not a test result and should not be interpreted as one.

The study has a single group and no randomized comparator. In general, a within-group analysis can estimate change over time among those analyzed, but the absence of a control group prevents direct estimation of the change that would have occurred under a different treatment or without the study intervention. Open-label conduct can also affect symptom reporting or other aspects of study participation. These are design considerations, not proof that any particular bias occurred.

What do the planning assumptions mean?

The record describes sample-size planning illustrations based on an observed effect. The stated assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation; the effect to detect is described as a stated fraction of the observed effect. For non-time-to-event outcomes, the illustrations are defined as participants per arm for the stated power. These are planning calculations, not observed power and not the number of participants analyzed in this single-group study. The record does not report numerical planning outputs in the information, and it does not describe those illustrations as the trial’s own design rationale. Their two-arm assumptions do not match the recorded single-group design.

In general, a planning calculation asks how much information a proposed design might need to detect a prespecified effect under specified assumptions. It does not establish that the effect is real, that the study achieved that power, or that the observed data support the effect. Planning based on an observed effect can also be sensitive to the estimate chosen. Since the registry record does not report the numerical observed effect or a detailed sample-size justification, the planning assumptions should be understood only as a general illustration rather than as evidence about the study’s achieved precision.

The registry also lists outcome and analysis counts, but does not provide a full statistical plan describing model choice, handling of repeated measurements, covariate adjustment, or sensitivity analyses. In general, these choices can affect estimates and uncertainty. Without the detailed plan and numerical results, readers cannot determine whether the analysis followed a prespecified approach or assess the robustness of the primary result. This uncertainty is distinct from the lack of a comparator: even a fully specified within-group analysis would not resolve the study’s limits for causal interpretation.

10. Confidence Intervals for Each Arm

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

R code and output

arm <- c("Arm 1 - Esomeprazole 40 mg")
n   <- c(96)
m   <- c(-3.3)
sp  <- c(2.36)
sd  <- sp      # posted standard deviations
for (i in seq_along(n)) {
  se <- sd[i] / sqrt(n[i]); h <- qt(0.975, n[i] - 1) * se
  cat(sprintf("CARM|%s|%d|%.3f|%.3f|%.3f|%.3f\n", arm[i], n[i], m[i], sd[i], m[i] - h, m[i] + h))
}

CARM  Arm 1 - Esomeprazole 40 mg  96  -3.300  2.360  -3.778  -2.822

11. Multiplicity, Missing Data and Analysis Populations

The registry lists 4 outcome measures and 1 analysis. The primary outcome is change in heartburn frequency from baseline to the 8-week visit. Secondary outcomes include frequency at the 4-week visit and maximum severity at the 4-week and 8-week visits. Testing several outcomes or time points can increase the chance of obtaining at least one apparently positive result by chance if each is interpreted independently. As a general statistical point, multiplicity is often addressed through a prespecified hierarchy, adjustment, or a clearly stated distinction between confirmatory and exploratory analyses.

The registry record does not report a multiplicity strategy, a hierarchy for interpreting outcomes, or which outcomes were intended as confirmatory. It also does not report the numerical results or tests for the listed secondary outcomes. Therefore, the extent to which multiple testing was considered, and how it would affect interpretation, is not reported in the registry record. The listed outcome count alone does not establish that every outcome was tested or that any particular correction was appropriate.

The primary population is identified as the full analysis set (96 participants), but the record does not describe missing-data handling, withdrawals, the amount of missing outcome information, or the analysis rules used to define that set. In general, missing observations can affect an estimate if the participants with recorded outcomes differ systematically from those without them. Different assumptions about missingness can lead to different analyses, so transparent reporting of the approach is important. No such details are reported in the registry record.

Enrollment is listed as 101, the primary analysis population as 96 participants, and the safety risk set as 100. The registry record does not explain why these counts differ or how each population was constructed. It is not possible to infer the reasons from the counts alone. These reporting gaps limit assessment of selection into the primary analysis and the completeness of follow-up.

12. 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.

Most frequent non-serious adverse event terms

The safety summary lists esomeprazole 40 mg, with 100 participants at risk in each displayed category. It reports 0 serious adverse events and 2 other adverse events. The record does not list serious adverse-event terms among the top serious terms. Deaths are recorded as null, which means a death count is not reported in that field; it should not be read as a reported count of zero.

These figures are descriptive counts in the registry record. They do not, on their own, establish whether an event was caused by treatment, how events were defined or collected, or how long participants were observed for safety. The record does not provide event narratives, timing, severity grades, exposure-adjusted rates, or a comparison group. In a single-group study, there is no concurrent treatment group against which to compare these counts.

The primary analysis population is described separately as the full analysis set (96 participants), while the safety summary gives a risk set of 100. The record does not explain the relationship between these populations. Safety counts and efficacy results also address different questions: the former describe reported adverse-event categories, while the primary endpoint concerns change in heartburn frequency. The registry record’s limited safety summary should therefore be read narrowly, without inferring a broader safety profile or a causal attribution.

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

The registry record establishes that the study evaluated an 8-week course of esomeprazole 40 mg once daily in participants with continuing heartburn after rabeprazole. It identifies heartburn frequency as the primary outcome and specifies a comparison of the 7-day period before baseline with the 7-day period before the 8-week visit. It also identifies the primary analysis population as the full analysis set (96 participants). These details clarify what the study was designed to assess.

The record does not report the numerical primary outcome, its uncertainty, or a statistical test. As a result, it does not show whether the mean number of heartburn days increased, decreased, or remained similar, nor how precise any change was. The study’s brief summary describes a hoped-for improvement, but an anticipated result is not an observed result. The absence of a numerical estimate should not be interpreted as evidence either for or against change.

Even a reported within-group improvement would not, by itself, establish that esomeprazole caused the change. This was an open-label, single-group study without a concurrent comparator. Natural symptom variation, expectations, changes in reporting, or other events over time could contribute to a before-and-after difference. A controlled comparison would address a different question by estimating how outcomes differed between groups treated under distinct conditions; this record does not provide such a comparison.

The record also does not provide enough detail to evaluate the completeness of outcome data, the handling of missing measurements, the statistical test, or the multiplicity approach. These omissions affect how fully the analysis can be appraised. The appropriate conclusion from this registry record is therefore limited: it describes the study question, design, measurement schedule, analysis population, and a small safety summary, but does not report the primary numerical result needed to assess the observed change or its precision.

14. Why This Trial Matters Statistically

This trial is statistically notable because its primary question is expressed as a within-person change in a symptom-frequency measure, while its design has only one treatment group. That distinction matters. A before-and-after estimate can summarize how the measured outcome changed during follow-up, but causal attribution requires a comparison that represents what might have happened over the same period under another condition. The registry record has no concurrent control group, so its design cannot directly provide that counterfactual comparison.

The endpoint is a count of heartburn days within a defined 7-day recall period. This makes the outcome relatively straightforward to describe, but the average alone may conceal substantial variation in individual experiences. A complete statistical interpretation would ordinarily consider both the estimated mean change and its uncertainty, as well as the distribution of individual changes and the completeness of follow-up. The registry record does not report the numerical primary result or those additional details.

The record also illustrates why denominators need context. Enrollment is listed as 101, the full analysis set as 96 participants, and the safety risk set as 100. These figures refer to different descriptions in the record, and the reasons for their relationship are not explained. It would be inappropriate to treat them as interchangeable or infer why the counts differ.

Finally, planning illustrations based on an observed effect are not the same as a prospective design justification or a measure of achieved power. The stated two-arm planning assumptions do not match the recorded single-group structure. Together, these features make the registry useful for understanding the question and basic design, while leaving the outcome’s size, precision, and statistical evidence unreported.

15. 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 outcome is that the registry record does not report the numerical primary result. There is no reported mean change in heartburn days, baseline or follow-up mean, confidence interval, or p-value. Thus, the observed direction, magnitude, and precision cannot be judged from this record. The stated expectation in the brief summary should not be substituted for a result.

The single-group, open-label design limits causal conclusions. There is no concurrent comparison group, and masking was not used. Changes over time could reflect influences other than the intervention, while participants’ knowledge of treatment could affect symptom reporting. These are potential design limitations; the record does not establish that they altered the results.

The registry does not explain why enrollment is 101 while the primary analysis population is the full analysis set (96 participants), or why the safety risk set is 100. It does not report the number or reasons for missing measurements, withdrawals, adherence, or the methods used to handle missing data. These details are necessary for evaluating whether the analyzed observations could be affected by incomplete follow-up.

The statistical methods are also incompletely described. The record does not identify the primary test or model, a multiplicity strategy, or any sensitivity analyses. The secondary-outcome descriptions include maximum-severity outcomes compared with baseline frequency, wording that leaves the intended measurement contrast unclear. In addition, the planning assumptions describe equal allocation between two arms, unlike the single-group design recorded for the study. These limitations leave both the outcome analysis and its relation to the study design only partly documented.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: To Assess the Efficacy of Esomeprazole 40 mg Once Daily in Subjects Who Still Had Heartburn After Receiving Rabeprazole — NCT01249651.
• Registry record last updated 2012-10-31; status last verified 2012-06.
• Results first posted 2012-10-31.
• 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.

19. Record Summary

This completed phase 4 study evaluated esomeprazole 40 mg once daily in participants with continuing heartburn after rabeprazole 20 mg once daily for 4 to 8 weeks. It was open label, multicentre, and single group, with 101 participants enrolled. The primary outcome was change in the number of heartburn days in the 7-day period before baseline compared with the 7-day period before the 8-week visit; the full analysis set is listed as 96 participants.

The registry record does not report the primary outcome estimate, its precision, or a test result. It also does not report detailed missing-data or multiplicity methods. The safety summary lists 0 serious adverse events and 2 other adverse events among a risk set of 100; deaths are not reported in the corresponding field. The record supports description of the study design and outcome definitions, but not assessment of the numerical efficacy result or a causal treatment effect.