PF-06669571 In Subjects With Idiopathic Parkinson's Disease: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for PF-06669571 In Subjects With Idiopathic Parkinson's Disease (NCT02565628), a randomized phase 1 study. The primary outcome is Maximum Percent Change From Baseline in Movement Disorder Society-Sponsor Revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS) Part III at Day 7..

2. Clinical Question

This study addressed safety, tolerability, pharmacokinetics, and pharmacodynamics of multiple doses of PF-06669571. Its summary also describes an assessment of whether the drug could demonstrate superior efficacy to placebo for motor symptoms. The posted primary endpoint is a motor-symptom measure: maximum percent change from baseline in the Movement Disorder Society-Sponsor Revision of the Unified Parkinson’s Disease Rating Scale Part III at Day 7.

The registry reports a least-squares mean change of -19.24 for the PF-06669571 arm and -14.21 for placebo. Negative changes indicate improvement under the endpoint definition. The sponsor’s reported mixed-model estimate is a least-squares mean difference of -5.02, with p = 0.638 and a 90% confidence interval whose reported upper bound is 8.97; the lower bound is not reported in the registry record. The comparison’s direction convention is not reported in the registry record, so the negative estimate should not be assigned a treatment-favoring direction without that information.

The question is therefore both descriptive and comparative: what changes were recorded in the study arms, and how uncertain is the sponsor’s model-based contrast? The registry result gives arm summaries and a model-based estimate, but the incomplete confidence interval limits interpretation of the estimate’s range.

3. Trial Design

The registry identifies this as a Phase 1b, randomized, double-blind, sponsor-open, parallel-group, multiple-dose study. Its official title describes safety, tolerability, pharmacokinetics, and pharmacodynamics as study aims. The listed condition is idiopathic Parkinson’s disease, and the study status is completed.

The intervention entries are PF-06669571 and placebo. The reported PF-06669571 arm is identified as 0.5 mg, once daily for 7 days; placebo was also given once daily for 7 days. The registry records enrollment of 20. For the primary outcome, the stated population is all enrolled participants who started treatment. The arm summaries list 10 participants for PF-06669571 and 9 for placebo. These figures describe the posted outcome summaries; the registry does not explain the relationship between the enrollment figure and the arm-level outcome counts.

Randomization and double masking describe design features, but the registry record does not report the sequence-generation method, allocation concealment, or who was masked. “Sponsor open” is part of the recorded design description; further details about which study roles knew treatment assignments are not reported in the registry record.

The recorded study start date is 2015-11-16, and the primary completion date is 2016-05-13. Pfizer is listed as sponsor. The registry lists four secondary pharmacokinetic outcomes, including maximum observed plasma concentration, area under the curve, and time to maximum observed concentration, with assessments on Day 1 and Day 7 as specified for those measures. Results for those secondary outcomes are not reported in the registry record. The record also indicates 14 outcome measures and one reported analysis, but does not provide a complete statistical analysis plan.

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: A total of 20 participants were randomized, 19 participants were treated. One participant was randomized but withdrew consent before receiving any treatment. This subject was not included in any analysis set.

Overall Study

Analysis population for the primary outcome, as defined in the registry: All enrolled participants who started treatment.

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 Maximum Percent Change From Baseline in Movement Disorder Society-Sponsor Revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS) Part III at Day 7., measured over Day 7.

The primary endpoint is maximum percent change from baseline in MDS-UPDRS Part III at Day 7. Part III assesses motor signs of Parkinson’s disease. The registry explains that the broader MDS-UPDRS evaluates disease severity across behavior, daily activities, motor abilities, and other complications, with subsections addressing motor and non-motor aspects. Higher total scores indicate more severe motor signs, and negative changes from baseline indicate improvement.

The measure is made up of 33 subscores based on 18 items. Several items allow scores for the right side, left side, or other body distributions. Each question uses response categories anchored to clinical terms ranging from normal to severe. The endpoint is expressed as a percentage change, and the reported statistic is a least-squares mean with standard error as its dispersion measure.

Motor signs are relevant to the study’s stated interest in treatment of motor symptoms. A measure at Day 7 provides a defined time point for describing change during the recorded treatment period. The registry identifies the endpoint as the maximum percent change from baseline at that time point, but does not further specify how the maximum was selected or calculated. That detail, along with any clinically meaningful threshold for interpreting the score, is not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry reports arm-level least-squares means and standard errors for a continuous endpoint, then gives a mixed-model comparison expressed as a least-squares mean difference. These statistics answer related but distinct questions: the arm summaries describe estimated change within each group, while the model-based contrast estimates a difference between groups after accounting for the model structure. The registry does not report enough model detail to identify which covariates, repeated-measure terms, or covariance assumptions were used.

What does a least-squares mean represent?

General statistical explanation: a least-squares mean is a model-based estimate of a group mean. It can differ from a simple arithmetic average when a model adjusts for other terms or accommodates the structure of the observations. The reported endpoint specifies least-squares means, but the registry record does not describe any adjustment variables or the model specification. The posted values are -19.24 for PF-06669571 and -14.21 for placebo.

How should the standard errors be read?

General statistical explanation: a standard error describes the precision of an estimated quantity under a statistical model. A smaller standard error generally corresponds to a more precise estimate, all else equal. It is not the same as the standard deviation of individual measurements and should not be interpreted as describing the range of participant outcomes. The reported standard errors are 7.21 and 7.6 for the two arms. The registry does not state how those standard errors were calculated beyond identifying the dispersion measure as standard error.

What does the mixed-model result add?

A mixed model can represent more than one source of variation or dependence in data, depending on its specification. General statistical explanation: such models are often used when observations have a structured relationship, but the record does not state the structure used in this analysis. The registry names the method as “Mixed Models Analysis” and reports a least-squares mean difference of -5.02. The particular model terms, estimation method, handling of repeated measurements, and assumptions are not reported in the registry record. It is therefore not possible to independently assess whether the model was appropriate or reproduce its estimate from the summary.

What does the confidence interval communicate?

General statistical explanation: a confidence interval expresses the range of values compatible with an estimate under a specified method and confidence level. It is not a range containing a fixed percentage of individual responses, nor is it the probability that the true effect lies inside the particular interval. The sponsor’s analysis is reported with a 90% confidence interval and an upper bound of 8.97. Its lower bound is not reported in the registry record. This prevents assessment of the full interval’s width and limits conclusions about the range of model-compatible effects.

What does the p-value communicate?

General statistical explanation: a p-value is calculated under a null hypothesis and model assumptions; it measures how unusual the data, or data more extreme, would be under that setup. It does not quantify clinical importance, establish causation, or tell readers the chance that a hypothesis is true. The reported p-value is 0.638. The registry does not identify the exact null hypothesis or all elements of the test, although the reported analysis compares the two groups.

Why can over-dispersion matter?

General statistical explanation: over-dispersion occurs when observed variability exceeds what a model assumes. If not accommodated, standard errors and inferential summaries may be misleading. This concept is especially relevant to some count-data models; the primary endpoint in this study is continuous, and the record does not report an over-dispersion assessment. There is no basis in the registry record to say whether over-dispersion was evaluated or relevant to the reported analysis.

The study also lists sample-size planning assumptions for illustrations based on an observed effect, including a two-sided significance level of 0.05, equal allocation, and a normal approximation. These assumptions are planning illustrations, not evidence of the trial’s original design rationale and not observed power. The registry does not report the trial’s own sample-size justification. It also does not provide enough information to use the planning assumptions as a substitute for the actual analysis plan.

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("PF-06669571 0.5 mg", "Placebo")
n   <- c(10, 9)
m   <- c(-19.24, -14.21)
sp  <- c(7.21, 7.6)
sd  <- sp * sqrt(n)      # standard errors converted to SDs
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  PF-06669571 0.5 mg  10  -19.240  22.800  -35.550  -2.930
CARM  Placebo  9  -14.210  22.800  -31.736  3.316

11. Analyses Reported by the Sponsor

The sponsor’s reported analysis is a mixed-model analysis of the primary endpoint, with a least-squares mean difference of -5.02, p = 0.638, and a 90% confidence interval with an upper bound of 8.97. The lower bound is not reported in the registry record. This is the sponsor’s posted model-based comparison, distinct from the arm-level least-squares mean changes of -19.24 and -14.21.

The registry record does not include a separate recalculated two-arm estimate for this continuous endpoint; it indicates that values were missing or not estimable for such a comparison. A numerical comparison between the sponsor’s model and a recalculation therefore cannot be made from the posted information. The record also does not explain the contrast’s sign convention or provide the model details needed to reproduce the estimate.

The sponsor result should consequently be described as reported, not treated as independently verified by a calculation from the arm summaries. The arm summaries and the model-based comparison are not interchangeable: a model can use information or assumptions not represented in a simple comparison of group summaries. The missing confidence-interval bound further limits assessment of the precision and direction of the full contrast.

12. Multiplicity, Missing Data and Analysis Populations

The registry lists 14 outcome measures and one reported analysis. It names four secondary outcomes, all pharmacokinetic measures: maximum observed plasma concentration, area under the curve from time zero to 12 hours, time to reach maximum observed plasma concentration, and area under the curve from time zero to 24 hours. The listed Day 1 and Day 7 assessments apply as specified in the individual outcome descriptions. Results for these secondary measures are not reported in the registry record.

Multiplicity arises when several outcomes or comparisons are tested, because interpreting each test separately can increase the chance of at least one apparently unusual result. General statistical explanation: a prespecified strategy may control or otherwise address that issue. The registry record does not report whether any multiplicity adjustment was planned or applied, how the primary and secondary outcomes were prioritized, or whether the primary analysis was prespecified. The number of outcome measures and the single reported analysis do not, on their own, establish the complete testing strategy.

The primary endpoint population is described as all enrolled participants who started treatment. The arm summaries report 10 participants for PF-06669571 and 9 for placebo. The registry does not state how missing endpoint observations were handled, whether all participants in those summaries had evaluable measurements, or whether any observations were excluded. Reasons for missing data and any sensitivity analyses are not reported in the registry record.

The analysis population is therefore only partly described. The record does not report an intention-to-treat definition, a per-protocol definition, or rules for treatment discontinuation and inclusion in the primary analysis. It also does not explain how the stated enrollment of 20 relates to the arm-level endpoint counts. These gaps prevent assessment of whether the analysis preserved the randomized comparison or how sensitive the result might be to missingness and analysis-population choices.

13. 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 5% reporting threshold.

Most frequent non-serious adverse event terms

The posted serious adverse event figures report 0 affected participants among 10 at risk in the PF-06669571 0.5 mg group, and 0 among 9 at risk in the placebo group. These are counts in the registry record; they do not establish that no serious events occurred outside the recorded observation or reporting framework. The record does not provide the serious-event terms, and the serious-event term list is empty.

The death counts are not reported in the registry record. A missing death figure should not be interpreted as zero. The registry also lists other adverse events affecting 6 participants in the PF-06669571 group and 5 in the placebo group. Those figures are separate from the serious adverse event counts and should not be conflated with them.

General statistical explanation: adverse-event counts are descriptive and depend on the population observed, event definitions, monitoring, and reporting. The registry does not provide additional detail about event definitions, severity grading, exposure-adjusted rates, or follow-up for safety. These figures therefore describe the posted counts but do not, on their own, establish comparative safety or rule out risks.

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

The primary result describes maximum percent change from baseline in a motor-sign measure at Day 7. The arm summaries are negative, and the registry defines negative change as improvement. The sponsor’s mixed-model comparison reports a least-squares mean difference of -5.02 and p = 0.638. Its 90% confidence interval has an upper bound of 8.97, while the lower bound is not reported.

These findings do not establish the size of a precisely estimated treatment contrast: the interval is incomplete, the analysis details are limited, and the sign convention for the difference is not stated. The reported p-value is a feature of the specified analysis, not a probability that the treatment effect is absent or present. It does not indicate clinical importance. The record does not identify a threshold for a clinically meaningful change.

The study’s stated aims included safety, tolerability, pharmacokinetics, and pharmacodynamics. However, the primary outcome result alone cannot answer all those questions. Four secondary pharmacokinetic outcomes are listed, but their results are not reported in the registry record. Serious adverse events are recorded as 0 in each arm’s at-risk group; death counts are not reported. The other adverse-event counts provide additional descriptive information but do not determine comparative safety.

General statistical explanation: a randomized comparison can support a treatment contrast when its design, conduct, analysis, and reporting are adequately described. Randomization and double masking are recorded design features, but details about allocation procedures, masking roles, missing data, and the model are unavailable. The result should therefore be understood as the registry’s reported summaries and sponsor analysis, with incomplete information about precision and analysis choices.

The trial record does not establish that PF-06669571 works or does not work. It records a short treatment schedule and an endpoint at Day 7 in a Phase 1b study. The posted result is limited to that measure, time point, and reported analysis; it should not be extended to longer-term outcomes or other populations.

15. Why This Trial Matters Statistically

This trial is statistically informative because its record places arm-level summaries beside a model-based comparison for a continuous motor endpoint. The distinction matters: estimated changes within each group describe what was recorded in each arm, whereas the comparison is intended to summarize the difference between groups under the sponsor’s model. Treating the arm summaries as if they were the treatment contrast would obscure that distinction.

The record also illustrates why uncertainty should be read alongside an estimate. The sponsor reports a p-value and a confidence interval level, but the interval has only an upper bound in the registry record. Without the lower bound, readers cannot assess the full range or width of the interval. The model name alone is likewise insufficient to reproduce or fully evaluate the analysis.

Reporting the endpoint population and arm counts is useful, but the relationship between enrollment and the outcome counts is not explained. Nor are missing-data methods, multiplicity procedures, or key model specifications reported. Those omissions are statistically relevant because they affect how readers judge precision, bias, and the scope of the reported inference.

Finally, the record identifies several pharmacokinetic outcomes in addition to the primary motor measure, yet their results are not reported in the record. This separates the study’s broad aims from the results available for interpretation. The case underscores that a completed registry entry can give meaningful design and outcome information while still leaving material uncertainty about the analysis and the full set of results.

16. 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 statistical interpretation is incomplete reporting of the sponsor’s confidence interval. The 90% interval has an upper bound of 8.97, but its lower bound is not reported in the registry record. The direction convention for the least-squares mean difference is also not stated, making it inappropriate to assign the negative estimate to a treatment-favoring direction.

The registry names a mixed-model analysis without describing its specification. Covariates, repeated-measure structure, covariance assumptions, estimation details, and the exact testing procedure are not reported. The posted arm-level standard errors do not replace those details, and no arm-level confidence limits are reported.

The primary population is described as all enrolled participants who started treatment. The arm summaries list 10 and 9 participants, while enrollment is recorded as 20. The registry does not explain this relationship, report reasons for any unavailable measurements, or describe missing-data handling. It also does not define other analysis populations or report sensitivity analyses.

Four secondary pharmacokinetic outcomes are listed, but their results are not reported in the registry record. The record does not say whether multiplicity was addressed or how the outcomes were prioritized. The trial’s own sample-size justification, interim analyses, and detailed statistical plan are not reported in the registry record. Planning illustrations based on the observed effect do not fill those gaps.

Safety interpretation is also bounded by reporting detail: serious-event counts are posted, but serious-event terms are absent and death counts are not reported. The record does not describe follow-up duration for safety beyond the stated treatment schedule. These limitations do not erase the posted findings, but they constrain how far the estimates can be interpreted.

17. Related Tutorials

18. Related Statistical Calculators

19. Sources

• ClinicalTrials.gov: PF-06669571 In Subjects With Idiopathic Parkinson's Disease — NCT02565628.
• Registry record last updated 2023-07-24; status last verified 2017-04.
• Results first posted 2017-08-07.
• 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.

20. Record Summary

The registry identifies NCT02565628 as a completed Phase 1b randomized, double-blind, sponsor-open, parallel-group study of PF-06669571 in idiopathic Parkinson’s disease. The recorded enrollment is 20. The PF-06669571 0.5 mg and placebo arms were each scheduled once daily for 7 days.

The primary endpoint was maximum percent change from baseline in MDS-UPDRS Part III at Day 7. The posted arm-level least-squares mean changes were -19.24 for PF-06669571 and -14.21 for placebo. The sponsor’s mixed-model analysis reported a least-squares mean difference of -5.02, p = 0.638, and a 90% confidence interval with upper bound 8.97; the lower bound is not reported.

Several analysis details remain unavailable, including the full confidence interval, model specification, missing-data approach, and multiplicity strategy. Secondary pharmacokinetic results and death counts are not reported in the registry record.