Dacomitinib (PF-00299804) As A Single Oral Agent In Selected Patients With Adenocarcinoma Of The Lung: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Dacomitinib (PF-00299804) As A Single Oral Agent In Selected Patients With Adenocarcinoma Of The Lung (NCT00818441), a non-randomized phase 2 study. The primary outcome is Progression-Free Survival (PFS) at Month 4: Cohort A.

2. Clinical Question

The study was intended to explore safety and efficacy in selected patients with adenocarcinoma of the lung. Cohort A included people with EGFR-mutated non-small-cell lung cancer or clinical characteristics intended to enrich for EGFR-mutated disease. Cohort B included people with HER2-mutated or HER2-amplified non-small-cell lung cancer. These eligibility differences matter when reading the results: cohort membership reflects patient characteristics, rather than random allocation to distinct interventions.

The primary question is restricted to Cohort A and the status of participants at Month 4. It is not a question about a comparative treatment effect against a control. Other outcomes listed in the record include progression-free survival, best overall response, duration of response, overall survival, quality-of-life scores, and dacomitinib trough plasma concentrations. Their listed presence does not establish that results for them are reported.

3. Trial Design

This was a phase 2, open-label, non-randomized trial of dacomitinib (PF-00299804), a single oral agent, in selected patients with advanced adenocarcinoma of the lung. The registry lists Pfizer as the sponsor and records the study as completed. The recorded start date is 2009-03-11, and the primary completion date is 2012-04-27. Enrollment was 119.

The registry describes two cohorts. Cohort A received dacomitinib and included patients with EGFR-mutated non-small-cell lung cancer or specified clinical characteristics intended to enrich for EGFR-mutated disease. Cohort B received dacomitinib and included patients with HER2-mutated or HER2-amplified non-small-cell lung cancer. The primary endpoint applies to Cohort A; a secondary outcome lists progression-free survival at Month 4 for Cohort B.

Because allocation was non-randomized and there was no masking, the design does not provide a randomized, blinded comparison. The two cohorts are defined by different disease-related characteristics, so comparing their outcomes directly would not isolate a treatment effect. No separate control treatment is listed. Details such as the planned cohort enrollment targets, dose schedule, treatment duration, follow-up schedule beyond endpoint descriptions, and eligibility criteria beyond those summarized in the record are not reported in the registry record.

The record lists nine outcome measures, including the primary four-month progression-free survival outcome for Cohort A and secondary measures covering progression-free survival, response, survival, quality of life, and drug concentration. It lists zero analyses. Consequently, the registry record establishes the broad design and endpoint definitions but does not provide the primary endpoint estimate or a statistical analysis report from which its calculation can be checked.

4. Participant Flow and Accounting

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

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: As-enrolled population included all participants who were enrolled in the study.

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 Progression-Free Survival (PFS) at Month 4: Cohort A, measured over Baseline up to Month 4.

The primary endpoint is the percentage of Cohort A participants who were alive and event free at Month 4, measured from the first dose of study treatment. An event is progressive disease or death from any cause, whichever occurs first. The endpoint therefore combines disease progression and death into a single status at a defined follow-up point: a participant counts as event free only if neither event has occurred by that time.

Progression was defined using RECIST version 1.0. The registry describes progression as a sufficiently large increase in the sum of the longest dimensions of target lesions relative to the smallest sum recorded since treatment began, appearance of one or more new lesions, or unequivocal progression in non-target lesions. The stated increase criterion is at least 20 percent.

A fixed-time progression-free survival percentage can describe the proportion meeting the event-free definition at a clinically specified time. It is different from reporting the time to progression or death for each participant, and it does not by itself show how outcomes changed over the entire follow-up period. The registry record does not report the observed Cohort A percentage or its 95% confidence interval. It also does not report details of censoring or the method used to estimate the fixed-time percentage.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary endpoint is a binary status evaluated at a specified time: each participant is classified as alive and event free at Month 4 or as having experienced an event by then. The reported percentage would summarize the share in the event-free category within Cohort A. A percentage at a fixed time is easy to interpret as a group-level summary, but it does not show the timing of events across follow-up or describe the course of an individual participant.

What would the confidence interval describe?

A confidence interval communicates uncertainty in an estimated population quantity, given the observed data and the statistical method used. A narrower interval generally indicates greater precision under that method; a wider interval indicates more uncertainty. The registry specifies a 95% confidence interval as the endpoint’s dispersion measure, but does not report the interval or the method used to calculate it. Without those results, its width and the precision of the endpoint estimate cannot be assessed.

How is progression defined?

The endpoint counts progression or death from any cause, whichever occurs first. Progression is based on RECIST version 1.0 criteria, including an increase of at least 20 percent in the sum of the longest dimensions of target lesions relative to the smallest sum recorded since treatment started, a new lesion, or unequivocal progression in non-target lesions. Combining progression and death means either can determine event status. The registry record does not provide participant-level event dates or explain how assessments between scheduled visits were handled.

What can the cohort structure tell us?

The trial is non-randomized and open-label. Cohort A and Cohort B reflect distinct eligibility characteristics, and both received dacomitinib. Cohort membership therefore is not a randomized contrast. A difference in outcomes between cohorts could arise from differences in their underlying characteristics and cannot, by itself, be read as the effect of one treatment versus another. The registry does not report an analysis adjusting for differences between cohorts.

What does the record say about analysis?

The registry lists zero analyses and does not report an analysis plan for the primary endpoint. It does not state whether the percentage was to be calculated using a simple observed proportion, a time-to-event estimator, or another method. Nor does it describe any adjustment, stratification, interim analysis, or sample-size justification. These details should not be inferred from the endpoint definition or the study phase.

In general, a time-to-event analysis can account for the timing of events and censoring, whereas a simple fixed-time proportion depends on how participants with unavailable status at the chosen time are handled. The registry record does not report the approach to censoring, missing Month 4 assessments, or participants who discontinued follow-up before that time. Therefore, the exact statistical interpretation of the intended estimate cannot be verified from the record.

Why does over-dispersion matter in general?

For binary data, a simple model may assume that observations vary according to a specified probability structure. Over-dispersion means the observed variation is greater than that structure would anticipate; if ignored, uncertainty estimates can be too small. This is a general statistical consideration, not a reported feature or analysis of this trial. The registry record does not identify an over-dispersion assessment or a model for the primary endpoint.

The posted safety counts are also descriptive summaries. Counts of participants with serious adverse events do not, on their own, account for differing time at risk, event recurrence, or differences in participant characteristics. The record does not describe an inferential safety comparison. More generally, percentages and confidence intervals need to be interpreted alongside the population, event definition, follow-up, and missing-data approach. For this trial, some of those definitions are stated, but the primary result and several analysis details are not reported in the registry record.

10. Exact Estimates for Each Arm

No two-arm comparison is shown for this trial, but each arm's result can still be summarized with exact interval estimates computed from the posted counts. The Clopper-Pearson interval is exact and conservative; the Wilson interval is a common closer-to-nominal alternative; the Bayesian credible interval uses a uniform Beta(1, 1) prior. For small groups the three can differ noticeably.

R code and output

arm    <- c("Dacomitinib: Cohort A")
n      <- c(89)
events <- c(68)
for (i in seq_along(n)) {
  ci <- binom.test(events[i], n[i])$conf.int          # Clopper-Pearson exact interval
  cr <- qbeta(c(0.025, 0.975), 1 + events[i], 1 + n[i] - events[i])   # Bayesian, uniform Beta(1,1) prior
  wi <- (function(x, n) { p <- x / n; z <- qnorm(0.975); d <- 1 + z^2 / n
    c((p + z^2 / (2 * n) - z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d, (p + z^2 / (2 * n) + z * sqrt(p * (1 - p) / n + z^2 / (4 * n^2))) / d) })(events[i], n[i])
  cat(sprintf("ARM|%s|%d|%d|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f|%.1f\n", arm[i], n[i], events[i], 100 * events[i] / n[i],
              100 * ci[1], 100 * ci[2], 100 * wi[1], 100 * wi[2], 100 * cr[1], 100 * cr[2]))
}

ARM  Dacomitinib: Cohort A  89  68  76.4  66.2  84.8  66.6  84.0  66.6  84.0

11. Multiplicity, Missing Data and Analysis Populations

The registry lists a primary endpoint for Cohort A and nine outcome measures in total. The listed secondary outcomes include progression-free survival at Month 4 for Cohort B, progression-free survival, best overall response, duration of response, overall survival, quality-of-life scores, and trough plasma concentrations of dacomitinib. Listing several outcomes raises a general multiplicity consideration: when many outcomes are examined, the chance of at least one apparently notable result can increase. The registry record does not report a multiplicity adjustment, a hierarchy for testing outcomes, or an analysis plan specifying which results were confirmatory.

The record identifies the primary population as the as-enrolled population, defined as all participants enrolled in the study. It does not report how many participants in Cohort A contributed to the primary endpoint calculation, or how participants with missing Month 4 status were handled. The approach to missing assessments, early withdrawal, censoring, and incomplete follow-up is not reported in the registry record. These omissions matter because the denominator and handling of unavailable outcomes affect the interpretation of a fixed-time percentage.

The registry lists zero analyses and does not provide a statistical analysis plan, interim-analysis details, or a sample-size justification. It is therefore not possible to determine from the registry record whether the listed outcome analyses were planned as primary, secondary, exploratory, or adjusted in any particular way. No assumptions about these methods should be inferred from the endpoint descriptions alone.

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 0% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: diarrhoea (10.0%), nausea (6.7%), vomiting (6.7%), pleural effusion (6.7%), asthenia (3.4%).

The serious adverse event figures are presented separately for the two dacomitinib cohorts. Cohort A lists 29 affected participants among 89 at risk, and Cohort B lists 9 affected participants among 30 at risk. These counts describe the registry’s recorded serious adverse event information; they do not establish that dacomitinib caused the events. The groups were not randomized comparisons and differed in eligibility characteristics.

The registry also lists serious-event terms with percentages: diarrhoea, 10.0%; nausea, 6.7%; vomiting, 6.7%; pleural effusion, 6.7%; asthenia, 3.4%; and disease progression, 3.3%. The record does not specify cohort attribution for this list, so those percentages should not be assigned to either cohort. Nor does the listing establish whether a participant could contribute to more than one term.

Counts and percentages alone do not describe event timing, duration, recurrence, exposure time, or causal attribution. The number of deaths is not reported in the registry record. These figures therefore provide a limited descriptive account of serious adverse events, not a comparative estimate of safety.

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

The record establishes that this phase 2 study examined dacomitinib in selected patients with advanced lung adenocarcinoma and defined a four-month progression-free survival endpoint for Cohort A. The endpoint counts participants who are alive and have had neither documented progression nor death by Month 4. The record also provides cohort descriptions and some serious adverse event counts.

It does not report the observed primary endpoint percentage or its confidence interval. The magnitude and precision of the Cohort A outcome therefore cannot be evaluated from the registry record. The absence of a reported endpoint value is not evidence that the endpoint was or was not reached; it means the result is unavailable in this record.

The trial’s non-randomized design does not support a causal comparison between Cohort A and Cohort B. Both cohorts received dacomitinib, and they were formed around different patient characteristics. The registry does not provide a randomized comparator group, so it cannot establish how outcomes would have differed under another treatment or no treatment.

The safety counts are descriptive, and they do not show whether events were caused by treatment or how risk varied over time. The registry does not report the deaths count or a detailed safety analysis. Similarly, the listed secondary outcomes do not establish that results for those outcomes are available.

In general, a study endpoint is interpreted in light of its definition, the population analyzed, the analysis method, uncertainty, and missing data. Several of these details are not reported in the registry record. The appropriate reading is therefore limited: the record describes the intended primary question and selected safety information, but does not supply the primary efficacy estimate needed to characterize the observed four-month outcome.

14. Why This Trial Matters Statistically

This study illustrates why an endpoint definition and an endpoint result are different kinds of information. The registry specifies a clinically interpretable status at Month 4 for Cohort A, including the events that count as failure to remain progression free. However, without the observed percentage and confidence interval, readers cannot assess either the outcome’s magnitude or its precision.

The cohort structure also matters statistically. Cohort A and Cohort B were defined by distinct clinical and molecular eligibility characteristics, not randomized assignment. Treating them as interchangeable arms would obscure the difference between a descriptive cohort contrast and a treatment comparison. A non-randomized study can describe outcomes in selected groups, but the design does not itself remove differences between those groups.

The record further highlights the importance of analysis transparency. It lists multiple outcomes but no analyses, and does not report the methods for missing data, censoring, multiplicity, or the confidence interval. These details help determine what a reported estimate means and how much uncertainty surrounds it. Their absence limits independent statistical interpretation, even when the endpoint wording is specific.

Finally, safety counts need context. Counts of participants with serious adverse events can be informative descriptively, but they do not establish causation or provide a fair comparison across non-randomized groups. Reading the study statistically therefore requires attention both to what is defined and what is not reported.

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 main limitation for interpreting efficacy is that the registry record does not report the primary Cohort A four-month progression-free survival percentage or its 95% confidence interval. The record therefore does not permit assessment of the observed result or its precision. Although it defines progression using RECIST version 1.0, it does not report participant-level assessments, event timing, or the method used to estimate status at Month 4.

The study is open-label and non-randomized, with cohorts defined by different eligibility characteristics. There is no like-for-like randomized control comparison. The registry does not report whether analyses adjusted for cohort or participant characteristics, and no such adjustment should be assumed. The overall enrollment is 119, but the record does not provide the number analyzed for the primary endpoint or explain how enrollment was distributed beyond the cohort at-risk counts in the safety information.

Important analysis details are also absent: missing-data handling, censoring methods, the statistical method for the confidence interval, multiplicity control, interim analyses, and sample-size justification are not reported in the registry record. The record lists zero analyses, which further limits assessment of the statistical results. The listed secondary outcomes do not come with reported estimates in the information.

Safety interpretation is limited by the descriptive nature of the counts, the lack of reported exposure-time details, and the absence of a death count. The serious-event term percentages are not attributed to a cohort in the registry record. Taken together, the available record supports a description of design and selected safety counts, but not a full evaluation of efficacy, comparative effects, or the precision of the primary outcome.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Dacomitinib (PF-00299804) As A Single Oral Agent In Selected Patients With Adenocarcinoma Of The Lung — NCT00818441.
• Registry record last updated 2019-01-08; status last verified 2018-12.
• Results first posted 2016-06-01.
• 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

The registry describes a completed phase 2, open-label, non-randomized study of dacomitinib (PF-00299804) in selected patients with advanced adenocarcinoma of the lung. Enrollment was 119. Cohort A included patients with EGFR-mutated disease or specified clinical characteristics; Cohort B included patients with HER2 mutation or amplification. Both cohorts received dacomitinib.

The primary endpoint was the percentage of Cohort A participants alive and event free at Month 4 after first dose, with progression or death counted as an event. The registry record does not report the primary endpoint estimate or its 95% confidence interval. It lists nine outcome measures and zero analyses. Serious adverse event counts are listed as 29 of 89 in Cohort A and 9 of 30 in Cohort B. The record does not establish causality or provide a randomized comparison.