Tipifarnib in Treating Patients With Relapsed or Refractory Lymphoma: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Tipifarnib in Treating Patients With Relapsed or Refractory Lymphoma (NCT00082888), a na phase 2 study. The primary outcome is Proportion of Participants With Confirmed Response (Complete Response, Unconfirmed Complete Response, or Partial Response) During the First 6 Courses of Treatment.

2. Clinical Question

3. Trial Design

This was a phase II, single-group study of tipifarnib in relapsed or refractory lymphoma. The registry lists planned enrollment of 93 and gives the study status as completed. Its recorded start date is 2004-03-24, and its primary completion date is 2009-05-20. Those dates describe the registry record; they do not establish when individual participants began or completed treatment.

The treatment description specifies oral tipifarnib twice daily on days 1–21, with courses repeating every 28 days if disease had not progressed and toxicity was not unacceptable. The primary endpoint was assessed during the first 6 courses. The registry also lists laboratory biomarker analysis and secondary outcomes of overall survival, time to progression, duration of response, and the number of patients who experienced grade 3 or 4 toxicities.

Allocation is recorded as not applicable, masking as none, and the model as single-group. Consequently, there is no randomized comparison or concurrent control arm described. The trial can describe outcomes observed among participants receiving the study regimen, but this design does not separate treatment effects from other influences on those outcomes. The registry record does not report a detailed protocol, the rationale for the planned enrollment, interim analyses, or a statistical analysis plan.

The listed conditions span multiple lymphoma categories rather than a single narrowly defined subtype. The record does not explain how eligibility, stratification, or subgroup analyses were handled across these categories. It also does not report the number who started treatment, completed the first 6 courses, or were included in each secondary-outcome analysis. Those details should not be inferred from planned enrollment alone.

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: All participants are included in this analysis.

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.

Population: All participants are included in this baseline analysis.

6. Primary Endpoint

The registry lists the primary outcome as Proportion of Participants With Confirmed Response (Complete Response, Unconfirmed Complete Response, or Partial Response) During the First 6 Courses of Treatment, measured over During the first 6 cycles of treatment.

The primary endpoint is a proportion: the number of participants meeting the registry’s response definition relative to the analysis population. It combines complete response, unconfirmed complete response, and partial response, and limits the assessment to the first 6 courses of treatment. The registry describes the endpoint as the proportion of participants and states that all participants are included in the analysis.

The response definition is based on tumor measurements and disease status. It requires at least a 50% decrease in the sum of the products of the greatest diameters of the six largest dominant nodes or nodal masses, no increase in other nodes, liver, or spleen, regression of splenic and hepatic nodules by at least 50% in that measure, and no new sites of disease. The endpoint therefore combines measured shrinkage with conditions that guard against counting a response when other specified disease features worsen or new disease appears.

General statistical context: a binary response endpoint reduces each participant’s assessment to whether the prespecified response criteria were met. The resulting proportion is readily interpretable as the share classified as responders, but it does not convey the size or durability of each individual response. The registry lists duration of response separately as a secondary outcome. The primary response count and proportion are not reported in the registry record, so the endpoint’s observed value and its precision cannot be described.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

What does a single-group design estimate?

General statistical context: a single-group study estimates outcomes among participants who receive the study regimen. For a binary endpoint such as response, the basic descriptive quantity is the proportion meeting the response criteria within the defined analysis population and assessment window. That estimate answers a descriptive question about the enrolled study group. In the absence of a concurrent control group, it does not directly estimate the difference that would have occurred under an alternative treatment.

This trial is recorded as single-group, with allocation not applicable and masking none. There is therefore no randomized treatment contrast to analyze. Randomization is one method used to make comparison groups comparable on average; without it, observed outcomes cannot be attributed to treatment alone through a between-group comparison. General considerations such as participant selection, disease course, supportive care, and assessment practices may matter, but the registry record does not provide details with which to evaluate their influence in this study.

How should a response proportion be read?

General statistical context: a proportion is a count of participants meeting a criterion divided by the relevant analysis population. It gives an intuitive summary, but its interpretation depends on a clearly specified numerator, denominator, and assessment rule. Here, the registry defines the response categories and the first 6-course assessment window, and states that all participants are included in the endpoint analysis. It does not post the numerator, denominator, or numerical estimate. Planned enrollment of 93 cannot substitute for the actual endpoint denominator.

A confidence interval, when reported, describes statistical uncertainty around an estimate under the assumptions of the method used. It is not a guarantee that the true value falls within a particular range, and it does not address biases arising from study design or measurement. No confidence interval is reported for the primary endpoint in the registry record. No recalculated estimate is possible from the posted endpoint details because the response count and analysis denominator are absent.

What does the response definition contribute?

The response criteria use measurements of dominant nodes or nodal masses and also specify conditions for other nodes, the liver and spleen, splenic and hepatic nodules, and new disease sites. Such criteria aim to make classification depend on stated disease changes rather than an informal judgment alone. The registry’s definition includes a threshold of at least a 50% decrease in the sum of products of greatest diameters, as well as requirements concerning lack of worsening in specified sites and absence of new sites. The registry does not report further information about assessment schedules, independent review, or adjudication procedures.

General statistical context: endpoint definitions can improve consistency, but they do not by themselves reveal how consistently the assessments were performed. Masking status is recorded as none. The record does not describe who assessed response or whether any review process was used, so the potential role of assessment knowledge cannot be evaluated from this information.

What can be learned from the safety summaries?

The registry lists serious-event and other-event counts for the Aggressive B-cell NHL Group, Indolent B-cell NHL Group, and HL/T-cell Lymphoma Group. It also lists selected serious adverse-event terms with percentages. These are descriptive safety summaries. General statistical context: counts of affected participants and percentages can help characterize reported event experience, but their interpretation depends on definitions, observation time, denominators, and event attribution. The registry entries do not give all of those details for the selected terms, and the event summaries do not provide a control-group comparison.

The death counts are also listed by group. A death count alone does not indicate cause, timing, or whether the death was considered related to treatment. Those details are not reported in the registry record described for this trial. The group-specific counts should therefore be read as recorded outcomes, not as comparative estimates of treatment risk.

What is not reported about the analysis?

The registry entries list five outcome measures and no statistical analyses. They do not specify the statistical methods for the primary endpoint, the confidence level for any interval, or procedures for handling missing response assessments. They also do not report an interim-analysis plan, a sample-size justification, or a plan for multiplicity across outcomes or lymphoma groups. These omissions mean that the analysis choices and their effect on uncertainty cannot be assessed from the record. General statistical principles can explain why those choices matter, but they cannot fill in the unreported trial methods.

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("Aggressive B-cell NHL Group", "Indolent B-cell NHL Group", "HL/T-cell Lymphoma Group")
n      <- c(42, 15, 36)
events <- c(0, 0, 0)
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  Aggressive B-cell NHL Group  42  0  0.0  0.0  8.4  -0.0  8.4  0.1  8.2
ARM  Indolent B-cell NHL Group  15  0  0.0  0.0  21.8  0.0  20.4  0.2  20.6
ARM  HL/T-cell Lymphoma Group  36  0  0.0  0.0  9.7  -0.0  9.6  0.1  9.5

11. Multiplicity, Missing Data and Analysis Populations

The registry lists a primary response endpoint and secondary outcomes of overall survival, time to progression, duration of response, and grade 3 or 4 toxicities. It does not report whether the trial used a formal multiplicity procedure, such as adjusting interpretation when several outcomes or subgroup comparisons are examined. When multiple outcomes are tested, the chance of at least one apparently notable finding can increase; adjustment or a clear hierarchy can help define how evidence should be interpreted. This is general statistical context, not a description of a method used in this trial.

Missing-data handling for the primary endpoint is not reported in the registry record. The endpoint description states that all participants are included in the analysis, but it does not say how participants without an assessment during the first 6 courses were classified, whether any assessments were unevaluable, or how incomplete follow-up was handled. The record also does not provide the actual endpoint denominator. These details matter because the estimated response proportion can depend on who is included and how missing outcomes are treated.

The record does not report analysis populations for the secondary outcomes, analysis methods, or details of censoring for time-to-event outcomes. It does not describe interim analyses or identify a prespecified statistical analysis plan. Without those details, the registry cannot establish how the listed outcomes were analyzed or whether analyses followed a prespecified hierarchy. No conclusions about missingness, multiplicity adjustment, or analysis populations beyond the primary endpoint description should be inferred.

12. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: neutrophil count decreased (36.6%), platelet count decreased (26.7%), leukocyte count decreased (19.5%), fatigue (17.1%), dyspnea (11.1%).

The registry reports serious and other adverse-event counts across three groups. In the Aggressive B-cell NHL Group, 27 of 41 participants were recorded as affected by serious adverse events and 38 of 41 by other adverse events; 34 deaths are listed. In the Indolent B-cell NHL Group, the corresponding counts are 4 of 15 and 15 of 15, with 9 deaths listed. In the HL/T-cell Lymphoma Group, the counts are 20 of 36 and 36 of 36, with 27 deaths listed. These are registry counts, not comparisons against a control group.

Selected serious-event terms are reported with percentages: neutrophil count decreased, 36.6%; platelet count decreased, 26.7%; leukocyte count decreased, 19.5%; fatigue, 17.1%; dyspnea, 11.1%; and hypotension, 9.8%. The registry entries do not specify the denominators or additional calculation details for these percentages. They also do not establish whether an event was attributed to treatment, when it occurred, or whether a participant could contribute to more than one term. The death counts do not identify cause or treatment relationship. These summaries describe recorded safety events and should not be read as causal or comparative estimates.

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

The trial record describes an investigation of tipifarnib in participants with relapsed or refractory lymphoma and defines a primary response endpoint during the first 6 courses. It also describes the dosing schedule, the single-group design, and selected adverse-event summaries. However, the primary response result is not reported in the registry record. There is consequently no posted response proportion to interpret, and no reported confidence interval with which to characterize its statistical precision.

Even if a response proportion were available, the design would shape what it could mean. A single-group study can describe the observed outcome among participants receiving the regimen, but it cannot make a randomized comparison with another treatment. The observed response rate alone would not identify the treatment’s causal effect. The registry also lists a broad set of lymphoma categories; it does not report subgroup response results or explain how outcome patterns may vary among those categories.

The endpoint has a specified measurement-based definition, which helps clarify what counted as response. It does not by itself establish how assessments were performed, how missing assessments were handled, or how durable responses were. Duration of response is listed as a secondary outcome, but its numerical result is not reported in the record details. Likewise, the listed survival and progression outcomes have no posted estimates in this record.

The safety counts show adverse events and deaths recorded by lymphoma group, while selected serious-event terms are given with percentages. These counts do not establish causation, comparative risk, timing, or attribution. The registry record does not provide a control arm against which to compare them. Thus, the available information supports understanding what the study set out to measure and what safety summaries were recorded, but does not support a quantitative conclusion about response or a causal conclusion about benefit or harm.

14. Why This Trial Matters Statistically

This trial illustrates why an endpoint definition and an endpoint result are different kinds of information. The record carefully describes a confirmed-response criterion and an assessment window during the first 6 courses, but does not report the response count or proportion. Without those outcome data, readers cannot assess the observed response frequency or its precision. A protocol-level description can clarify what was intended to be measured without answering what the study observed.

The design also highlights the distinction between a descriptive estimate and a comparative treatment effect. In a single-group phase II study, the observed outcomes can characterize participants receiving the regimen, but there is no concurrent randomized group to support a direct comparison. This matters when readers encounter claims about treatment effects: the design and analysis determine what conclusions the data can support, independently of the clinical importance of the question.

The record’s combination of multiple lymphoma categories adds another statistical consideration. Outcomes for the overall study group may not represent every category equally, and subgroup interpretation requires suitable data and methods. The record does not report subgroup endpoint results or analysis details, so it cannot answer whether response or safety patterns differed across the listed groups.

Finally, the safety summaries demonstrate why counts need context. Group sizes and affected-participant counts are reported, along with selected event percentages and deaths, but the registry entries do not provide all details needed to interpret attribution, timing, or comparative risk. Reading the record statistically means distinguishing observed counts from causal evidence, and distinguishing planned enrollment from the actual denominator for an endpoint. These distinctions remain important even when no primary result is posted.

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 principal limitation for interpreting efficacy is that the registry record does not report the primary response count or proportion. It also does not provide a confidence interval, an actual analysis denominator, or the number of participants with evaluable assessments. The statement that all participants are included in the endpoint analysis does not resolve how missing or unevaluable assessments were handled.

The single-group design has no randomized comparator, and masking is recorded as none. Any observed outcome would therefore be descriptive rather than a direct estimate of comparative treatment effect. The registry does not report who assessed response, whether independent review was used, or how assessments were adjudicated.

The study includes a range of lymphoma categories, but the registry entries do not describe subgroup analysis methods or provide subgroup response results. The record also does not report a statistical analysis plan, sample-size justification, interim-analysis plan, or multiplicity approach. The secondary outcomes are named without numerical results or analysis details in the registry record for this record.

For safety, group-specific affected-participant counts and death counts are listed, as are selected serious-event terms with percentages. The registry entries do not provide complete denominator and attribution details for those percentages, or information sufficient to interpret timing and causes of deaths. These limitations restrict causal and comparative interpretation of the safety summaries.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Tipifarnib in Treating Patients With Relapsed or Refractory Lymphoma — NCT00082888.
• Registry record last updated 2020-04-13; status last verified 2020-04.
• Results first posted 2011-12-07.
• 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

NCT00082888 is a completed phase II, single-group study sponsored by the National Cancer Institute. It evaluated tipifarnib in participants with relapsed or refractory lymphoma, with planned enrollment of 93. Participants were scheduled to take tipifarnib by mouth twice daily on days 1–21, with courses repeating every 28 days in the absence of progression or unacceptable toxicity.

The primary endpoint was the proportion with a confirmed complete response, unconfirmed complete response, or partial response during the first 6 courses. Overall survival, time to progression, duration of response, and grade 3 or 4 toxicities are listed as secondary outcomes. The registry record does not report the numerical primary endpoint result or statistical analyses for it. It includes group-specific safety counts and selected serious-event terms, but does not provide a randomized comparison. The record does not report missing-data procedures, multiplicity methods, or a detailed statistical analysis plan.