This page provides an independent statistical analysis and educational interpretation of publicly reported results. ClinicalTrials.gov provides the official trial registry record.
1. Trial at a Glance
MONALEESA-7 was a randomized, parallel-group, phase 3 trial with quadruple masking and a treatment purpose. The registry reports 672 enrolled participants and two treatment arms, with a primary time-to-event endpoint of investigator-assessed progression-free survival.
| Feature | MONALEESA-7 |
|---|---|
| Trial name | MONALEESA-7 |
| NCT ID | NCT02278120 |
| Phase | Phase 3 |
| Condition | Advanced Metastatic Breast Cancer |
| Population description | Premenopausal women with hormone receptor-positive, HER2-negative advanced breast cancer |
| Allocation | Randomized |
| Design model | Parallel |
| Masking | Quadruple |
| Primary purpose | Treatment |
| Enrollment | 672 |
| Primary endpoint | Progression Free Survival (PFS) by Investigator Assessment |
| Primary endpoint type | Time-to-event |
| Results posted | Yes |
| Statistical analyses posted | 4 |
| Lead sponsor | Novartis Pharmaceuticals |
| Sponsor type | Industry |
2. Clinical Question
The primary statistical question is whether the randomized ribociclib-containing regimen differs from the placebo-containing regimen with respect to investigator-assessed progression-free survival in the registered population. The registry classifies the primary hypothesis as superiority.
Population
Premenopausal women with hormone receptor-positive, HER2-negative advanced breast cancer, within the registry's condition description of advanced metastatic breast cancer.
Intervention
Ribociclib combined with NSAI or tamoxifen and goserelin.
Comparator
Placebo combined with NSAI or tamoxifen and goserelin.
Primary question
Does the ribociclib-containing regimen improve investigator-assessed progression-free survival relative to the placebo-containing regimen?
3. Trial Design
Ribociclib-containing regimen
- Ribociclib
- NSAI or tamoxifen
- Goserelin
Placebo-containing regimen
- Placebo
- NSAI or tamoxifen
- Goserelin
The registry describes the allocation as randomized, the design model as parallel, and masking as quadruple. Those design descriptors matter statistically because randomization establishes the basis for comparing treatment assignments, while masking is intended to reduce the influence of knowledge of treatment assignment on trial conduct and assessment.
4. Trial Timeline
Trial start
The registry lists November 20, 2014 as the study start date.
Primary completion
The registry lists August 21, 2017 as the primary completion date.
Completed
The ClinicalTrials.gov record classifies the study as completed and indicate that results have been posted.
5. Endpoints
| Endpoint | Registry definition / time frame | Type |
|---|---|---|
| Progression Free Survival (PFS) by Investigator Assessment | From randomization to first documented progression or death, assessed up to approximately 29 months. | Time-to-event |
The registry defines PFS as the period starting from the date of randomization to the date of the first documented progression or death caused by any reason. When patients did not experience an event, PFS was censored at the date of the last adequate tumor assessment. Clinical deterioration without objective radiological evidence was not considered documented disease progression.
The ClinicalTrials.gov record contains four posted statistical analyses: one primary endpoint analysis and three secondary endpoint analyses. The primary endpoint has a formal statistical comparison and an estimated hazard ratio with a 95% confidence interval.
6. Statistical Methodology
Primary time-to-event analysis
The registry reports the log-rank test for the primary PFS comparison. The analysis population is the Full Analysis Set (FAS), including all randomized patients. The comparison is between ribociclib + NSAI/tamoxifen + goserelin and placebo + NSAI/tamoxifen + goserelin.
The registry describes the primary analysis as a superiority comparison. The log-rank test addresses the between-group time-to-event comparison, while the hazard ratio summarizes the relative event hazard.
Cochran-Mantel-Haenszel analysis
The registry also reports the Cochran-Mantel-Haenszel test for the two binary secondary endpoints: overall response rate and clinical benefit rate. This method provides a way to compare categorical outcomes while accounting for stratification when strata are part of the analysis framework.
Analysis population
The primary PFS analysis uses the FAS, explicitly described in the registry as including all randomized patients. This is closely aligned with the intention-to-treat principle: treatment comparisons remain anchored to randomized assignment rather than being restricted to participants who completed treatment.
Effect measure
The primary analysis reports a hazard ratio. A hazard ratio is a relative measure of the instantaneous event rate under a time-to-event model. It is not a probability, a median, or a percentage of patients who benefit.
7. Primary Result: Progression-Free Survival
The registry reports a formal superiority analysis of investigator-assessed PFS using a log-rank test in the Full Analysis Set. The reported effect measure is a hazard ratio.
Hazard ratio for progression or death
95% CI: 0.441–0.694 · P < 0.0000001
Two-sided 95% confidence interval · Full Analysis Set · Log-rank test
| Primary endpoint | Ribociclib regimen vs placebo regimen |
|---|---|
| Endpoint | Progression Free Survival (PFS) by Investigator Assessment |
| Time frame | From randomization to first documented progression or death, assessed up to approximately 29 months |
| Analysis population | Full Analysis Set including all randomized patients |
| Method | Log-rank test |
| Effect measure | Hazard ratio |
| Estimate | 0.553 |
| 95% CI | 0.441–0.694 |
| P-value | <0.0000001 |
| Hypothesis | Superiority |
The estimated hazard ratio of 0.553 means that the estimated instantaneous rate of progression or death was 0.553 times that of the comparator group under the reported time-to-event analysis. Expressed as a simple relative-hazard transformation, this corresponds to an estimated 44.7% lower hazard for progression or death because \(1-0.553=0.447\). This is a relative hazard interpretation, not a statement that 44.7% of participants avoided progression or death.
The estimate does not tell us the probability that a particular patient will remain progression-free, nor does it tell us the median PFS. Those quantities require different information. The ClinicalTrials.gov record does not provide median PFS or time-specific PFS probabilities, so they are not presented here.
The 95% confidence interval of 0.441–0.694 describes statistical uncertainty around the estimated hazard ratio under the reported analysis framework. It is not a range containing the outcomes that individual patients might experience.
The very small p-value, <0.0000001, addresses evidence against the null hypothesis specified for the statistical comparison. It does not measure the magnitude of the treatment effect. Effect size is communicated by the hazard ratio, while precision is communicated by the confidence interval.
As with other hazard-ratio analyses, interpretation should not be expanded into an assumption that the relative hazard is identical at every time point unless the underlying proportional-hazards assumption is appropriate. The ClinicalTrials.gov record does not report a formal assessment of proportional hazards.
8. Secondary Result: Overall Survival
Overall survival was analyzed as a secondary time-to-event endpoint. The registry defines the time frame as from randomization to death, assessed up to approximately 45 months. The analysis population was the Full Analysis Set including all randomized participants.
Hazard ratio for overall survival
95% CI: 0.535–0.948 · P = 0.00973
Two-sided 95% confidence interval · Log-rank test
| Secondary endpoint | Reported analysis |
|---|---|
| Endpoint | Overall Survival (OS) |
| Time frame | From randomization to death, assessed up to approximately 45 months |
| Analysis population | FAS including all randomized participants |
| Groups compared | Ribociclib + NSAI/Tamoxifen + Goserelin vs Placebo + NSAI/Tamoxifen + Goserelin |
| Method | Log-rank test |
| Effect measure | Hazard ratio; reported as Cox Proportional Hazard |
| Estimate | 0.712 |
| 95% CI | 0.535–0.948 |
| P-value | 0.00973 |
| Hypothesis | Superiority |
The reported OS hazard ratio of 0.712 corresponds to an estimated instantaneous rate of death of 0.712 times that in the comparator group under the reported model. As a direct mathematical interpretation of the estimate, this is approximately a 28.8% lower estimated hazard of death.
That does not mean that 28.8% fewer participants died, nor does it imply a 28.8% increase in survival time. A hazard ratio is a relative time-to-event measure and should not be translated directly into an absolute survival probability.
The 95% confidence interval, 0.535–0.948, indicates uncertainty around the estimate. Its width is important: the data are compatible with a range of relative hazard reductions rather than with one exact effect size.
The p-value of 0.00973 describes the strength of evidence against the null comparison under the reported statistical framework. It is not a measure of clinical importance and should not be read as a 0.973% probability that the observed treatment effect occurred by chance.
Because OS is a time-to-event endpoint, censoring and the assumptions underlying the hazard-ratio model remain relevant. The ClinicalTrials.gov record does not provide a separate formal proportional-hazards assessment, so no stronger conclusion about the shape of the hazard functions is made here.
9. Secondary Result: Overall Response Rate
Overall Response Rate (ORR) by Investigator Assessment was reported as a secondary binary endpoint. The time frame was up to approximately 29 months. The analysis population was the Full Analysis Set including all randomized participants.
Cochran-Mantel-Haenszel test
Superiority comparison · FAS including all randomized participants
| Secondary endpoint | Reported analysis |
|---|---|
| Endpoint | Overall Response Rate (ORR) by Investigator Assessment |
| Time frame | Up to approximately 29 months |
| Outcome unit | Percentage of participants |
| Endpoint type | Binary |
| Analysis population | FAS including all randomized participants |
| Method | Cochran-Mantel-Haenszel test |
| P-value | 0.000980 |
| Hypothesis | Superiority |
The registry supplies a formal p-value for the ORR comparison but does not supply an ORR estimate or confidence interval in the ClinicalTrials.gov record. Accordingly, this page does not reconstruct or infer response percentages.
The Cochran-Mantel-Haenszel test addresses the categorical comparison represented by ORR. The reported P = 0.000980 provides evidence against the null comparison under the stated analysis framework, but the p-value alone does not communicate the size of the difference between treatment groups.
To describe the magnitude of an ORR difference, one would normally want the response proportion in each arm together with an effect measure such as a risk difference, risk ratio, or odds ratio and an associated confidence interval. Those numerical quantities are not included in the ClinicalTrials.gov record, so they are not added here.
10. Secondary Result: Clinical Benefit Rate
Clinical Benefit Rate (CBR) by Investigator Assessment was another secondary binary endpoint. The registry gives a time frame of up to approximately 29 months and analyzes the Full Analysis Set including all randomized participants.
Cochran-Mantel-Haenszel test
Superiority comparison · FAS including all randomized participants
| Secondary endpoint | Reported analysis |
|---|---|
| Endpoint | Clinical Benefit Rate (CBR) by Investigator Assessment |
| Time frame | Up to approximately 29 months |
| Outcome unit | Percentage of participants |
| Endpoint type | Binary |
| Analysis population | FAS including all randomized participants |
| Method | Cochran-Mantel-Haenszel test |
| P-value | 0.002 |
| Hypothesis | Superiority |
As with ORR, the ClinicalTrials.gov record reports the formal statistical comparison but does not provide the underlying CBR percentages or a confidence interval for the treatment effect. The p-value should therefore be interpreted as evidence from the categorical hypothesis test rather than as an effect-size estimate.
11. Serious Adverse Events
The ClinicalTrials.gov record includes serious adverse-event counts expressed as affected participants over participants at risk by arm. The labels below are reproduced from the ClinicalTrials.gov record rather than expanded beyond what the registry record provides.
| Registry arm label | Affected / at risk |
|---|---|
| Ribociclib + NSAI/Tamoxifen + Goserelin | 81/335 |
| Placebo + NSAI/Tamoxifen + Goserelin | 49/337 |
| Placebo Crossover to Ribociclib | 1/17 |
These values should be kept distinct from the efficacy analysis. The primary PFS comparison was based on randomized participants in the Full Analysis Set, whereas safety events are naturally related to treatment exposure and the registry reports them using affected/at-risk counts.
12. Why the Full Analysis Set Matters
The primary and secondary analyses posted on ClinicalTrials.gov for MONALEESA-7 use the Full Analysis Set, explicitly described as including all randomized patients or all randomized participants. This is an important feature of randomized-trial inference.
Randomization anchor
Analyzing participants according to their randomized assignment preserves the connection between the treatment comparison and the randomization process.
Avoiding treatment-completion selection
Restricting efficacy analyses only to patients who completed treatment can introduce selection because treatment completion may itself be related to prognosis or tolerability.
Primary PFS analysis
The registry explicitly identifies the Full Analysis Set including all randomized patients for the primary PFS analysis.
Secondary efficacy analyses
The OS, ORR, and CBR analyses reported in the registry also use the Full Analysis Set including all randomized participants.
13. Time-to-Event Endpoints: What Is Actually Being Compared?
PFS and OS are not ordinary binary outcomes. For each participant, the analysis considers both whether an event occurred and when it occurred. Participants who have not experienced the event by the end of their available follow-up can contribute information through censoring.
For MONALEESA-7, the PFS time origin is randomization and the event is first documented progression or death. The registry specifies censoring at the date of the last adequate tumor assessment for participants without an event.
This structure explains why a simple comparison of the number of progressions or deaths is not enough. A participant followed for a short period without an event contributes different information from a participant followed for a much longer period without an event.
14. Statistical Methods Explained
Why was a log-rank test used for PFS and OS?
The registry identifies both PFS and OS as time-to-event endpoints and reports the log-rank test for their comparisons. The log-rank framework uses the timing of events and the risk sets over follow-up rather than reducing each participant to a simple event/no-event indicator. It is therefore suited to randomized comparisons in which follow-up times and censoring vary across participants.
What does a hazard ratio of 0.553 mean?
A hazard ratio of 0.553 means that the estimated instantaneous rate of the event in the ribociclib-containing group was 0.553 times the estimated rate in the comparator group under the reported analysis. The complementary quantity, \(1-0.553=0.447\), is a 44.7% relative reduction in estimated hazard. It does not mean that 44.7% of patients avoided progression or death.
Why does the confidence interval matter?
The estimate 0.553 is only one point estimate. The 95% confidence interval of 0.441–0.694 communicates the uncertainty associated with that estimate under the statistical framework. A narrower interval would indicate greater precision; a wider interval would indicate less precision. The interval is about the estimated treatment effect, not about individual patient outcomes.
Why does the p-value not measure effect size?
The primary PFS p-value is reported as <0.0000001. A p-value addresses the compatibility of the observed data with the null hypothesis under the specified testing framework. It does not quantify how large the treatment effect is. Two studies can have the same p-value while having different effect estimates, particularly when sample size and event information differ.
Why was the Cochran-Mantel-Haenszel test used for ORR and CBR?
ORR and CBR are binary outcomes, unlike PFS and OS. The registry reports the Cochran-Mantel-Haenszel test for these endpoints. This method is designed for categorical comparisons and can account for stratified data structures rather than treating all observations as though they necessarily came from one unstructured two-by-two table.
What does quadruple masking tell us?
The registry classifies MONALEESA-7 as quadruple masked. This is a design feature intended to reduce the influence of treatment knowledge. The ClinicalTrials.gov record does not identify which four parties were masked, so the statistical interpretation should stop at the registry's masking designation rather than assigning roles not present in the data.
Why is randomization important to the statistical comparison?
Randomization creates the design basis for comparing outcomes between treatment assignments. Because the primary PFS analysis uses the Full Analysis Set including all randomized patients, the reported comparison remains linked to that randomized allocation rather than being redefined around who received or completed treatment.
15. Hazard Ratios and Their Limits
The two reported time-to-event hazard ratios are useful because they compress the relative separation between the treatment groups into a single measure. But a hazard ratio is not interchangeable with other effect measures.
| Measure | What it communicates | What it does not communicate by itself |
|---|---|---|
| Hazard ratio | Relative event hazard under the reported time-to-event model | Absolute survival probability, median survival, or individual patient benefit |
| 95% confidence interval | Statistical uncertainty around the estimated effect | The probability that an individual patient's outcome lies inside the interval |
| P-value | Evidence against a specified null hypothesis under the testing framework | Effect size or clinical importance |
| ORR / CBR p-value | Evidence from a categorical comparison | The response rate difference itself when the underlying percentages are not reported |
For MONALEESA-7, this distinction is especially important because the ClinicalTrials.gov record gives complete effect estimates for the two reported time-to-event analyses but only p-values for the two categorical secondary analyses. A statistically disciplined summary should preserve that asymmetry rather than filling the missing effect estimates from outside sources.
16. Confidence Intervals in MONALEESA-7
The primary PFS estimate is 0.553 with a 95% confidence interval of 0.441–0.694. The secondary OS estimate is 0.712 with a 95% confidence interval of 0.535–0.948.
PFS precision
The interval from 0.441 to 0.694 gives a quantitative description of uncertainty around the PFS hazard-ratio estimate of 0.553.
OS precision
The interval from 0.535 to 0.948 gives a quantitative description of uncertainty around the OS hazard-ratio estimate of 0.712.
Point estimate versus interval
The point estimate is the central reported estimate; the confidence interval shows that the data do not identify a single treatment-effect value with certainty.
Not individual prognosis
Neither interval should be interpreted as the range of survival outcomes that individual participants should expect.
17. Multiplicity and the Secondary Endpoints
The ClinicalTrials.gov record identifies one registered primary endpoint and three posted secondary statistical analyses. The primary endpoint is PFS, while OS, ORR, and CBR are secondary endpoints.
| Endpoint | Role | Statistical method | Reported result |
|---|---|---|---|
| Progression Free Survival (PFS) by Investigator Assessment | Primary | Log-rank test | HR 0.553; 95% CI 0.441–0.694; P < 0.0000001 |
| Overall Survival (OS) | Secondary | Log-rank test | HR 0.712; 95% CI 0.535–0.948; P = 0.00973 |
| Overall Response Rate (ORR) by Investigator Assessment | Secondary | Cochran-Mantel-Haenszel test | P = 0.000980 |
| Clinical Benefit Rate (CBR) by Investigator Assessment | Secondary | Cochran-Mantel-Haenszel test | P = 0.002 |
Multiple endpoints raise a statistical issue that cannot be resolved simply by looking at which p-values are small. A complete multiplicity interpretation requires the prespecified testing hierarchy, alpha allocation, or other error-control strategy. Those details are not included in the ClinicalTrials.gov record, so this page does not infer them.
18. Interim Analysis, Non-Inferiority, Crossover, and Bayesian Methods
Several common trial-design topics are not supported by the registry-reported MONALEESA-7 data. They are therefore deliberately not reconstructed.
| Topic | What the ClinicalTrials.gov record establishes |
|---|---|
| Non-inferiority margin | Not reported in the ClinicalTrials.gov record. The registered hypothesis type is superiority. |
| Crossover | The ClinicalTrials.gov record contains a safety category labelled “Placebo Crossover to Ribociclib” with 1/17 serious adverse events, but do not provide a general crossover analysis or crossover rate. |
| Factorial design | Not reported. The design model is parallel with 2 arms. |
| Interim analysis | Not reported in the ClinicalTrials.gov record. |
| Missing-data imputation | Not reported in the ClinicalTrials.gov record. |
| Bayesian methods | Not reported. The registry-reported methods are log-rank and Cochran-Mantel-Haenszel tests. |
| Multiplicity procedure | Not reported in the ClinicalTrials.gov record. |
| Stratification variables | Not specified in the ClinicalTrials.gov record. |
This distinction is important. A statistical analysis page should explain the methods actually documented for the trial rather than importing the design features of another oncology study simply because they are common in the field.
19. Kaplan-Meier Estimation and the Registry Result
Kaplan-Meier estimation is a standard descriptive framework for time-to-event data because it accommodates right censoring and estimates the event-free probability over time. It is particularly useful for displaying PFS and OS as survival curves.
However, the registry-reported MONALEESA-7 statistical-analysis record explicitly identifies the inferential method as the log-rank test and the effect measure as a hazard ratio. It does not explicitly state in the ClinicalTrials.gov record that a Kaplan-Meier estimator was used for the posted analysis. Therefore, Kaplan-Meier estimation is best understood here as the natural educational framework for understanding the reported time-to-event endpoint, not as an additional trial-specific method claimed from the registry record.
Here, \(d_i\) represents events at a particular event time and \(n_i\) represents the number at risk immediately before that time. The formula illustrates why time and censoring information matter in survival analysis.
20. Investigator Assessment and Endpoint Interpretation
The primary endpoint is explicitly named Progression Free Survival (PFS) by Investigator Assessment. The registry definition is therefore important: progression is based on documented progression, and clinical deterioration without objective radiological evidence was not considered documented disease progression.
Event definition
The PFS event is first documented progression or death caused by any reason.
Censoring
Participants without an event are censored at the date of the last adequate tumor assessment.
Clinical deterioration
Clinical deterioration without objective radiological evidence is not considered documented progression under the registry definition.
Time origin
PFS begins at randomization, consistent with the registered endpoint definition.
These details show why endpoint definitions matter statistically. A hazard ratio is only interpretable relative to the event definition, time origin, censoring rules, and analysis population that generated it.
21. Secondary Endpoints: Why ORR and CBR Are Different From PFS
ORR and CBR are binary endpoints in the ClinicalTrials.gov record. That makes their statistical structure fundamentally different from PFS and OS.
| Feature | PFS | ORR / CBR |
|---|---|---|
| Endpoint type | Time-to-event | Binary |
| Time component | Yes | No, although the registry supplies an assessment time frame |
| Reported method | Log-rank test | Cochran-Mantel-Haenszel test |
| Reported effect measure | Hazard ratio | Not reported in the posted analysis data |
| Reported p-value | <0.0000001 | ORR: 0.000980; CBR: 0.002 |
The distinction prevents a common statistical mistake: a p-value from a categorical endpoint should not be interpreted as though it were a hazard ratio, and a hazard ratio should not be interpreted as though it were a response percentage.
22. Statistical Interpretation of the Complete Reported Evidence
Within the ClinicalTrials.gov record, MONALEESA-7 reports a statistically significant superiority comparison for the primary PFS endpoint, with a hazard ratio of 0.553, a 95% confidence interval of 0.441–0.694, and a p-value of <0.0000001.
The secondary OS analysis reports a hazard ratio of 0.712 with a 95% confidence interval of 0.535–0.948 and a p-value of 0.00973. The secondary ORR and CBR analyses report p-values of 0.000980 and 0.002, respectively, using the Cochran-Mantel-Haenszel test.
Taken together, these are different pieces of statistical evidence. PFS and OS quantify relative time-to-event effects, while ORR and CBR are categorical outcomes. The reported p-values provide hypothesis-testing information, whereas the reported hazard ratios and confidence intervals provide information about the magnitude and precision of the time-to-event effects.
The most defensible numerical statement from the ClinicalTrials.gov record is that the randomized comparison produced a reported PFS hazard ratio of 0.553 (95% CI 0.441–0.694; P < 0.0000001) in the Full Analysis Set. The corresponding interpretation is a lower estimated hazard of progression or death in the ribociclib-containing group under the reported analysis.
It would go beyond the registry-reported evidence to attach an unreported median PFS, a specific absolute PFS probability, a number-needed-to-treat, or a reconstructed Kaplan-Meier curve. Those quantities require additional data that are not present in the ClinicalTrials.gov record.
23. Limitations
- Registry-only numerical scope: this analysis intentionally uses only the ClinicalTrials.gov record for trial-specific numbers. Additional numerical results from publications or other sources are not substituted for missing registry values.
- Incomplete effect measures for binary endpoints: ORR and CBR have reported p-values, but the statistical analyses posted on ClinicalTrials.gov do not provide the corresponding treatment-group percentages or confidence intervals.
- Limited design detail: stratification variables, interim-analysis rules, multiplicity procedures, missing-data methods, and other protocol-level details are not included in the ClinicalTrials.gov record.
- Hazard-ratio assumptions: a hazard ratio is a model-based relative time-to-event measure. The ClinicalTrials.gov record does not provide a formal assessment of proportional hazards.
- Endpoint-specific interpretation: PFS, OS, ORR, and CBR answer different questions and should not be collapsed into a single generic measure of treatment effect.
- Safety-data scope: the registry-reported serious-adverse-event field provides affected/at-risk counts but not a complete safety profile, exposure-adjusted rates, event grades, or formal safety comparisons.
- Masking detail: quadruple masking is documented, but the ClinicalTrials.gov record does not identify which parties were masked.
- No unreported reconstruction: median survival, time-specific survival probabilities, subgroup estimates, and other commonly reported trial quantities are not included because they are absent from the ClinicalTrials.gov record.
24. Why This Trial Matters Statistically
MONALEESA-7 is a useful teaching case because its registry record connects a randomized parallel-group design with two distinct classes of statistical endpoints: time-to-event outcomes and binary outcomes. That allows several core clinical-trial concepts to be examined without treating all endpoints as though they had the same statistical structure.
| Concept | How it appears in MONALEESA-7 |
|---|---|
| Randomization | The registry identifies the allocation as randomized. |
| Parallel design | The design model is parallel with two arms. |
| Blinding | The registry identifies quadruple masking. |
| Full Analysis Set | The primary PFS and secondary efficacy analyses include all randomized participants. |
| Time-to-event endpoint | Investigator-assessed PFS is the registered primary endpoint. |
| Log-rank test | Used for the reported PFS and OS analyses. |
| Hazard ratio | Reported for PFS and OS. |
| Confidence interval | 95% two-sided intervals are reported for both PFS and OS hazard ratios. |
| P-values | Reported for all four posted statistical analyses. |
| Categorical analysis | ORR and CBR use the Cochran-Mantel-Haenszel test. |
| Superiority testing | The posted analyses are classified as superiority hypotheses. |
| Safety by arm | Serious adverse events are reported as affected/at-risk counts for the registry-reported arm labels. |
25. Related Tutorials
Learn more about the methods used in this trial:
26. Related Calculators
27. Sources
- ClinicalTrials.gov: NCT02278120.
- Linked publication: PubMed PMID 42334791.
- Linked publication: PubMed PMID 39826197.
- Linked publication: PubMed PMID 37673211.
- Linked publication: PubMed PMID 36800111.
- Linked publication: PubMed PMID 34965945.
Continue exploring clinical-trial statistics
Connect the endpoints and methods in MONALEESA-7 with deeper biostatistics tutorials and statistical calculation tools.
28. Record Summary
MONALEESA-7 provides a compact example of how randomized clinical-trial evidence can combine different statistical endpoint types. The primary investigator-assessed PFS endpoint is a time-to-event outcome analyzed with a log-rank test and reported with a hazard ratio of 0.553 (95% CI 0.441–0.694; P < 0.0000001). Secondary OS uses the same broad time-to-event framework and reports a hazard ratio of 0.712 (95% CI 0.535–0.948; P = 0.00973), while ORR and CBR are binary outcomes analyzed with the Cochran-Mantel-Haenszel test.
The statistical lesson is not simply that the reported p-values are small. The more useful interpretation is that each endpoint requires its own effect measure and inferential framework. Hazard ratios describe relative event hazards, confidence intervals describe uncertainty around those estimates, and p-values address specified null hypotheses. The Full Analysis Set keeps the efficacy analyses connected to randomized assignment, while the registry's incomplete reporting of some design and effect-size details places limits on how far the analysis can be extended.