Randomized Clinical Trial Of Bococizumab (PF-04950615; RN316) In Subjects With Hyperlipidemia Or Mixed Dyslipidemia At Risk Of Cardiovascular Events: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Randomized Clinical Trial Of Bococizumab (PF-04950615; RN316) In Subjects With Hyperlipidemia Or Mixed Dyslipidemia At Risk Of Cardiovascular Events (NCT01968954), a randomized phase 3 study. The primary outcome is Percent Change From Baseline in Low Density Lipoprotein-Cholesterol (LDL-C) at Week 12.

2. Clinical Question

This is a question about a measured laboratory outcome at a specified time point, not a direct comparison of cardiovascular events. Although participants were described as being at risk of cardiovascular events, the primary outcome was LDL-C change from baseline. The registry lists other lipid measures and time points as secondary outcomes, but the central statistical comparison is the Week 12 LDL-C endpoint.

3. Trial Design

The registry describes a Phase 3, randomized, quadruple-masked, parallel-group study comparing PF-04950615 with placebo. Its official title identifies the study as double-blind, while the registry’s masking field specifies quadruple masking. The record describes the purpose as assessing efficacy, safety, and tolerability in people with primary hyperlipidemia or mixed dyslipidemia who were at risk of cardiovascular events. The brief summary says participants had high cholesterol and were receiving highly effective statins.

The recorded enrollment was 711. The study began in 2013-10, had a primary completion date of 2016-04, and is listed as completed. The sponsor is Pfizer. For the primary outcome, the posted results include 329 evaluable participants in the placebo group and 336 in the PF-04950615 150 mg group. Those outcome-specific counts are not the same as a statement that every enrolled participant contributed an evaluable Week 12 measurement. The registry defines the full analysis set as all randomized participants and says that the number analyzed for this outcome refers to participants evaluable for it.

The registry lists placebo and PF-04950615 150 mg in the primary results. The arm descriptions themselves are blank, so additional details about dose schedule or administration are not reported in the registry record. The record also does not report the original design assumptions behind the enrollment target, such as the effect size used for planning or the planned power. The separate sample-size illustrations on this page are based on the observed results and should not be read as the trial’s design justification.

The reported primary comparison uses a mixed model for repeated measures. The registry does not give enough detail to reconstruct the model specification, including its covariance structure or handling of missing repeated measurements. The posted analysis and the simple unadjusted comparison answer related but not identical questions, so their estimates are presented separately.

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: FAS included all participants who were randomized. Here, "number of participants analyzed" signifies those participants who were evaluable for this outcome measure.

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: Full analysis set (FAS) included all participants who were randomized.

6. Primary Endpoint

The registry lists the primary outcome as Percent Change From Baseline in Low Density Lipoprotein-Cholesterol (LDL-C) at Week 12, measured over Baseline, Week 12.

The primary endpoint is the percent change from baseline in low-density lipoprotein cholesterol (LDL-C) at Week 12. It summarizes the change in a blood lipid measurement relative to each participant’s baseline level, with the group results expressed as means. A negative percentage change indicates a decrease relative to baseline; a positive change indicates an increase. The primary results report a mean change for each group and the between-group difference.

LDL-C is the particular lipid measure selected for the primary outcome. Measuring change from baseline provides a way to compare how the groups’ LDL-C values changed during the period leading to Week 12, rather than comparing only their end-of-period levels. The record also lists other lipid measures, including total cholesterol, non-HDL-C, apolipoprotein B, lipoprotein(a), and HDL-C, as secondary outcomes. Those do not replace the prespecified primary endpoint in interpreting the central result.

The endpoint is a laboratory measure, not a count of cardiovascular events. The study population is described as being at risk of cardiovascular events, but the primary result does not establish a difference in those events. Nor does a group mean describe every participant’s individual change. The reported standard deviations show that individual measurements varied around each group mean, while the comparison and its confidence interval describe the estimated average contrast between groups.

The registry identifies the timeframe as baseline to Week 12 and states that the primary analysis population included randomized participants, with the analyzed number referring to those evaluable for the outcome. The record does not report further details about how individual baseline values were incorporated into the analysis beyond describing the outcome as percent change from baseline.

7. Results Posted in the Registry

• PF-04950615 150 mg: mean -55.60 versus 1.00 on control; difference -56.60 (95% CI -60.45 to -52.75), standardized effect d = -2.23; z-test p = <0.001.

8. Secondary Efficacy Endpoints

The registry also posts results for secondary outcomes. For each outcome below, the endpoint type, the test applied to the posted summary statistics, the result and its interpretation are given in turn. Secondary endpoints are usually not adjusted for multiple testing, so they support rather than confirm the primary finding.

Percent Change From Baseline in Fasting Low-Density Lipoprotein-Cholesterol (LDL-C) at Week 12 in Participants With Primary Hyperlipidemia

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • PF-04950615 150 mg: mean -56.80 versus 1.50 on control; difference -58.30 (95% CI -62.49 to -54.11), standardized effect d = -2.37; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for PF-04950615 150 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Percent Change From Baseline in Fasting Low-Density Lipoprotein-Cholesterol (LDL-C) at Week 12 in Participants With Mixed Dyslipidemia

• Endpoint type: Continuous: a mean value per participant, compared as a difference in means.
• Test: Unadjusted two-sample z-test for the difference in means, using the posted standard deviations.
• Result:
  • PF-04950615 150 mg: mean -50.90 versus -1.00 on control; difference -49.90 (95% CI -59.27 to -40.53), standardized effect d = -1.77; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically lower for PF-04950615 150 mg than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The secondary outcomes broaden the description of lipid changes beyond the primary LDL-C endpoint. The registry lists measures of total cholesterol, non-HDL-C, apolipoprotein B, lipoprotein(a), and HDL-C, along with additional LDL-C assessments at later time points and within the primary hyperlipidemia and mixed dyslipidemia groups. The posted secondary results include the Week 12 LDL-C subgroup analyses for both named dyslipidemia categories. Across the posted Week 12 LDL-C subgroup comparisons, the estimated changes favor a more negative mean percentage change in the PF-04950615 group than in placebo, consistent in direction with the primary comparison.

This broad pattern is relevant as a description of consistency across related measures and participant categories. It does not make the secondary outcomes equivalent to the primary endpoint. Subgroup estimates can be less precise because they involve fewer participants, and the number of outcomes and analyses creates multiple opportunities for apparently notable findings. The registry lists 31 outcome measures and 56 analyses, with 27 secondary results posted.

In general, when many outcomes or subgroup comparisons are examined, unadjusted p-values provide less protection against chance findings across the full set of analyses. The multiplicity approach is not reported in the registry record. Accordingly, secondary findings are best read as supportive descriptive information rather than as a set of independent confirmatory tests. This discussion does not repeat the individual estimates shown in the results tables.

The secondary outcomes also do not change what the primary result measures. They are lipid measures and time points, not evidence of a difference in cardiovascular events. The registry record does not give a multiplicity-adjusted interpretation of the secondary findings, so the overall pattern can be described without treating every result as separately established.

Secondary outcomes registered for this trial, for reference (only those above were recalculated):

• Percent Change From Baseline in Total Cholesterol (TC) at Week 12, 24 and 52
• Percent Change From Baseline in Non- High Density Lipoprotein-Cholesterol (Non HDL-C) at Week 12, 24 and 52
• Percent Change From Baseline in Apolipoprotein B (ApoB) at Week 12, 24 and 52
• Percent Change From Baseline in Lipoprotein(a) at Week 12, 24 and 52
• Percent Change From Baseline in High Density Lipoprotein-Cholesterol (HDL-C) at Week 12, 24 and 52
• Percent Change From Baseline in Fasting Low-Density Lipoprotein-Cholesterol (LDL-C) at Week 12 in Participants With Primary Hyperlipidemia
• Percent Change From Baseline in Fasting Low-Density Lipoprotein-Cholesterol (LDL-C) at Week 12 in Participants With Mixed Dyslipidemia
• Percent Change From Baseline in Fasting Low Density Lipoprotein-Cholesterol (LDL-C) at Week 24 and 52

9. Statistical Interpretation

10. Statistical Methods Explained

The primary measure is continuous: each participant’s outcome is a percentage change, and the registry reports group means with standard deviations. For continuous outcomes, a mean describes the average observed value in a group. A standard deviation describes the spread of participant values around that mean. It is not the same as a confidence interval, which expresses uncertainty about an estimated quantity such as a group mean or between-group difference.

The simple comparison is an unadjusted recalculation from the posted group summaries. It compares the placebo mean with the PF-04950615 150 mg mean and reports their difference, together with a confidence interval and an unadjusted p-value. It is useful as a transparent summary derived from the published numbers, but it is not a substitute for the trial’s own statistical analysis. It does not incorporate repeated measurements or any model adjustments that may have been used by the sponsor.

The sponsor’s primary analysis is identified as a mixed model for repeated measures, or MMRM. In general, repeated-measures models are used when outcomes are measured at multiple time points for participants. They can account for the fact that measurements from the same participant are related, rather than treating every measurement as independent. MMRM can estimate group differences over time while using the available repeated outcome information under the model’s assumptions. The registry reports a least-squares mean difference from this analysis. A least-squares mean is a model-based estimate, not simply the arithmetic mean displayed in the arm summaries.

The name MMRM does not, by itself, tell us all the analytical choices. The covariance structure, fixed effects, adjustment variables, treatment of intercurrent events, and exact assumptions about missing observations are not reported in the registry record. It would be inappropriate to infer those details from the method label. In general, the validity of model-based estimates depends on the specification and assumptions used, along with the quality and completeness of the data.

The reported contrast is a mean difference. For this outcome, its sign follows the ordering of the groups used in the comparison: a negative value means the estimated change was more negative in the PF-04950615 group than in the placebo group. The estimate is presented with a 95% confidence interval. In general, a confidence interval gives a range of values compatible with the data and analysis at the stated confidence level. It conveys uncertainty about the estimated contrast; it is not a range expected to contain the outcomes of most individual participants.

The p-value is reported as <0.001 for both the recalculated unadjusted comparison and the MMRM result. In general, a p-value describes how unusual data at least as incompatible with a null hypothesis would be if that null hypothesis and the analysis assumptions held. It is not the probability that the null hypothesis is true, and it does not measure clinical importance. The registry does not report the full hypothesis-testing plan here, so the displayed p-values should be understood as the results attached to their respective analyses.

The outcome-specific analysis population deserves attention. The registry describes the full analysis set as including all participants who were randomized, but it defines the number analyzed for the primary outcome as those evaluable for that outcome. The posted primary group counts are therefore the evaluable counts, not a claim that all randomized participants had a usable Week 12 measurement. In general, missing observations can affect precision and can bias results if the reasons for missingness relate to outcomes in ways not handled by the analysis. The precise missing-data assumptions and procedures are not reported in the registry record.

Over-dispersion is a general concern mainly in count models when observed variability exceeds what a simple model assumes. It is not the central issue for this continuous mean comparison. Here, the reported standard deviations show the observed spread of a continuous measure, and the MMRM accounts for repeated observations according to its model. No claim about over-dispersion in this trial is warranted from the posted results.

The recalculated standardized effect shown with the comparison is based on a pooled standard deviation. In general, standardization expresses a mean difference in standard-deviation units, which can help describe relative scale but can be less intuitive than the original percentage-change units. The clinical meaning of the endpoint is best read in its original units. The standardized value is not needed to understand the direction of the primary result, and it should not be interpreted as a patient-level effect.

Finally, the registry includes a set of planning illustrations derived from the observed effect. Those illustrations are not the trial’s original design calculation and are not retrospective evidence of the probability that this completed trial detected an effect. The original sample-size justification and any interim-analysis plan are not reported in the registry record. Statistical interpretation should therefore prioritize the posted estimate, its interval, the analysis method, and the limits of the information available.

11. Confidence Intervals and Precision

The registry’s primary MMRM result is a least-squares mean difference of -57.0, with a 95% confidence interval from -61.0 to -53.1. The interval lies below zero, indicating that the model-based estimate is compatible with a more negative mean percentage change in the PF-04950615 group than in the placebo group under the analysis. The simple unadjusted recalculation gives -56.6, with a 95% confidence interval from -60.45 to -52.75. The close direction and scale of the two estimates are reassuring as a comparison of summaries, but the model-based and unadjusted calculations are not interchangeable.

In general, a confidence interval describes uncertainty in an estimated contrast, conditional on the analysis and its assumptions. It does not show the range of changes experienced by most participants, and it is not a guarantee that the true value lies inside the particular interval. A narrower interval generally indicates greater precision for the estimated contrast; precision depends on factors including the amount of information and outcome variability.

The arm-level standard deviations are 20.89 for placebo and 29.17 for PF-04950615 150 mg. They describe spread in participant percentage changes, not uncertainty in the estimated difference. The endpoint analysis includes 329 and 336 evaluable participants, respectively. These counts and the observed variability help contextualize the precision of the estimates, but no additional uncertainty calculation is needed to interpret the intervals already posted.

The interval’s interpretation is limited by the analysis details available in the registry record. The sponsor used MMRM, but the summarized record does not specify the full model or missing-data procedures. Confidence intervals quantify sampling uncertainty under an analysis; they do not include every possible source of uncertainty, such as model misspecification or bias from missing observations.

12. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The sample-size table and curve are planning illustrations based on the observed effect, not the trial’s original design calculation. For these continuous outcomes, the table gives participants per arm, not a total across both arms and not total events. The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each row considers an effect set to the stated fraction of the observed effect.

The column for 80% power gives the illustrative number of participants per arm for a design with an 80% chance of detecting the assumed effect under those planning assumptions, if that effect and the assumptions were correct. The 90% power column gives the corresponding illustrative number per arm for a design with a 90% chance. These are forward-looking design quantities, not descriptions of the completed trial’s observed performance. This is not observed power.

The rows reduce the assumed effect from the full observed effect to 75% and 50% of that effect. Smaller effects are harder to distinguish from random variation, so they require more participants per arm to reach the same target power under the illustration’s assumptions. The values should be read as examples of how sample-size needs change when the target effect changes, rather than as recommendations for a future study.

The registry record does not report the trial’s own sample-size assumptions or justification. Thus these figures cannot establish whether the original enrollment target was chosen using the same significance level, allocation, effect size, or approximation. The curve visualizes the same planning relationship; it does not represent observed enrollment, participant follow-up, or a recalculated probability that the completed trial detected an effect.

13. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = -56.600; pooled standard deviation σ = 25.413.
2. n = 2 × (1.96 + 0.842)² × 25.413² / -56.600² = 3.2, rounded up to 4 participants per arm for 80% power.

The smaller-effect rows in the table above repeat the same calculation with the effect multiplied by 0.75 and 0.5 (for ratios, applied to the logarithm of the ratio).

R code

alpha <- 0.05
z_a   <- qnorm(1 - alpha / 2)          # two-sided
delta <- -56.6                      # observed difference in means
sigma <- 25.4131588549402                     # pooled standard deviation
n_per_arm <- function(power, frac = 1) {
  ceiling(round(2 * (z_a + qnorm(power))^2 * sigma^2 / (delta * frac)^2, 6))
}
for (f in c(1, 0.75, 0.5))
  cat(sprintf("%3.0f%% of observed effect: n per arm = %s (80%% power), %s (90%% power)\n", 100 * f,
              format(n_per_arm(0.80, f), big.mark = ","), format(n_per_arm(0.90, f), big.mark = ",")))

# Check against R's built-in function (t-based, so very slightly larger)
cat("power.t.test:", round(power.t.test(delta = delta, sd = sigma, power = 0.80)$n, 1), "\n")

# Simulation: exact two-sample t-test using simulated means and variances
set.seed(1968954)
n    <- n_per_arm(0.80)
reps <- 20000
m_diff <- rnorm(reps, delta, sigma * sqrt(2 / n))             # difference in sample means
s2     <- sigma^2 * rchisq(reps, 2 * (n - 1)) / (2 * (n - 1))   # pooled sample variance
tstat  <- m_diff / sqrt(s2 * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(tstat) > qt(0.975, 2 * (n - 1))), reps))

Output from running the code

100% of observed effect: n per arm = 4 (80% power), 5 (90% power)
 75% of observed effect: n per arm = 6 (80% power), 8 (90% power)
 50% of observed effect: n per arm = 13 (80% power), 17 (90% power)
power.t.test: 4.4 
Simulated power at n = 4 per arm: 0.744 (20000 replicates)

The simulation draws many sets of group means and variances at the planned sample size and counts how often the two-sample t-test rejects the null. It should land close to the target power; at very small required sample sizes it can fall below it, because the normal approximation is rough there.

14. Analyses Reported by the Sponsor

The sponsor’s reported primary analysis is the MMRM result: a least-squares mean difference of -57.0, with a 95% confidence interval from -61.0 to -53.1 and p < 0.001. The simple recalculation from the posted arm summaries gives a mean difference of -56.6, with a 95% confidence interval from -60.45 to -52.75 and an unadjusted p-value of <0.001. Both summaries point in the same direction and are similar in scale.

The recalculation is an unadjusted comparison of group summary statistics. The sponsor’s estimate comes from a repeated-measures model and is reported as a least-squares mean difference. Differences between the estimates and intervals are therefore possible even when both use the same trial. The registry record does not give the model specification needed to reproduce the sponsor’s estimate from participant-level data.

The record indicates no discrepancy between the sponsor’s result and the recalculation. The sponsor’s own analysis remains the trial’s reported analysis; the recalculation is a supplementary check based on posted summaries, not a replacement for the sponsor’s model. Its p-value is explicitly unadjusted and should not be treated as accounting for the many outcomes and analyses in the record. Neither result should be extended beyond the Week 12 LDL-C comparison they address.

15. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when a study evaluates several outcomes, time points, groups, or statistical comparisons. In general, the more tests that are considered, the greater the opportunity for at least one result to appear statistically notable by chance if each is judged separately. The registry lists 31 outcome measures and 56 analyses, and 27 secondary results are posted. The multiplicity strategy, including whether any formal adjustment or hierarchy was used, is not reported in the registry record.

The primary Week 12 LDL-C endpoint provides the clearest single focus for interpreting the study’s main reported comparison. The secondary endpoints include other lipid measures, later assessments, and LDL-C results in two participant categories. Their unadjusted results should not be treated as if each were an isolated confirmatory test. The posted primary and secondary p-values do not, on their own, establish how the full family of comparisons was handled.

The record defines the primary full analysis set as all randomized participants, and clarifies that the outcome-specific analyzed count refers to those evaluable for that measure. It reports 329 evaluable participants in placebo and 336 in PF-04950615 150 mg for the primary endpoint. This definition distinguishes the intended analysis population from the set with an evaluable outcome, but does not explain how missing Week 12 observations were handled.

In general, missing outcome data can reduce precision and may affect validity, particularly when the chance of a measurement being missing is related to the outcome or treatment experience. MMRM is the reported method, but its missing-data assumptions and implementation details are not reported. The registry record also does not report an interim-analysis plan, rules for stopping early, or the original sample-size justification. These gaps limit reconstruction of the complete statistical plan; they should not be filled by assumptions based solely on the method name or the posted results.

16. 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 1% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: myocardial infarction (1.4%), chest pain (1.1%), non-cardiac chest pain (0.8%), angina unstable (0.8%), angina pectoris (0.6%).

The registry lists serious adverse events among 40 of 353 participants at risk in the placebo group and 45 of 356 at risk in the PF-04950615 150 mg group. For other adverse events, the listed counts are 185 of 353 and 205 of 356, respectively. These are descriptive counts from the record. They should not be converted into an overall treatment-safety conclusion from the summaries alone, and no comparative statistical analysis of these counts is posted.

The registry also lists serious-event terms and percentages, including myocardial infarction at 1.4%, chest pain at 1.1%, non-cardiac chest pain at 0.8%, unstable angina at 0.8%, angina pectoris at 0.6%, and congestive cardiac failure at 0.6%. The summarized record does not assign these listed terms to a particular arm, so they should not be interpreted as arm-specific rates.

Deaths are not reported in the registry record. Serious adverse events and other adverse events are distinct categories in the displayed data; the counts should be read according to those categories rather than added together. The figures provide a summary of reported events, not a complete account of event timing, duration, severity, or causal assessment.

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

The posted results show that, at Week 12, the mean percentage change in LDL-C was more negative in the PF-04950615 150 mg group than in the placebo group. The registry’s MMRM analysis estimates a between-group difference of -57.0, and its 95% confidence interval is below zero. The unadjusted recalculation from arm summaries gives a similar direction and scale. These findings describe the trial’s reported laboratory endpoint and the precision of its estimated group contrast.

The result does not mean that every participant experienced the group average change. Individual values varied, as reflected in the reported standard deviations. Nor does it establish what happened to outcomes beyond the endpoint and time point being analyzed. In particular, LDL-C change is not itself a cardiovascular event outcome. The fact that participants were described as being at risk of cardiovascular events does not make the primary result a test of event reduction.

The result also does not resolve the interpretation of all secondary analyses. Many measures, time points, and analyses are listed, while the multiplicity approach is not reported. The secondary pattern can offer context, but it does not convert the primary laboratory finding into a result about other outcomes. Likewise, the statistical significance of a comparison does not by itself describe clinical importance, long-term durability, or the balance of benefits and harms.

Safety summaries need separate consideration. The record lists serious and other adverse-event counts, but the brief data do not provide a complete comparative analysis or enough detail to characterize every event. Deaths are not reported in the registry record. Consequently, the primary endpoint result should not be used alone to draw conclusions about overall safety or clinical outcomes.

Finally, interpretation depends on the analysis and available data. The sponsor used MMRM, but important model and missing-data details are not reported in this summary. The reported estimate and interval are informative within that context, while uncertainty about unreported methods and outcomes remains.

18. Why This Trial Matters Statistically

This trial illustrates why a clinical result should be read at the level of the endpoint actually analyzed. The participants were at risk of cardiovascular events, but the primary statistical comparison concerns a continuous lipid measure at Week 12. Keeping that distinction clear prevents an estimate for a laboratory outcome from being mistaken for evidence about clinical events.

It also shows the value of presenting both arm summaries and a between-group estimate. The means describe what was observed in each group, while the difference and its confidence interval directly address the comparative question. The standard deviations describe the spread of participant outcomes; they do not replace the interval around the group contrast. Readers can therefore distinguish the variation among participants from uncertainty in the estimated average difference.

The comparison between the simple recalculation and the sponsor’s MMRM result demonstrates that an unadjusted summary and a model-based analysis can be similar without being identical. The MMRM is the reported analysis, while the recalculation is a transparent supplementary comparison. Seeing both can help readers understand what the posted arm-level values imply without confusing a reconstruction from summaries with the trial’s own model.

Finally, the record highlights the importance of statistical-plan details. The number of listed outcomes and analyses makes multiplicity relevant, while missing-data procedures, the original sample-size justification, and interim-analysis details are not reported in the registry record. Reporting these elements helps readers understand how robustly a trial’s estimates can be interpreted. The posted results are informative, but they do not answer every question about analysis choices, safety, or clinical outcomes.

19. 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 registry record does not report the full MMRM specification. Details such as the covariance structure, model terms, and handling of missing repeated measurements are unavailable, limiting independent reconstruction of the sponsor’s estimate. The outcome-specific counts also indicate that the primary result is based on participants evaluable for that measure, while the record does not explain the pattern or reasons for any unavailable Week 12 measurements.

The analysis concerns percent change in LDL-C at Week 12. It does not provide a primary comparison of cardiovascular events or establish the longer-term course of the endpoint. Although the registry lists later LDL-C time points and other lipid outcomes, those results do not substitute for outcomes not reported. The record’s summary of serious-event terms does not identify their treatment-arm distribution, and deaths are not reported in the registry record.

Multiplicity is another limitation for interpreting the broader collection of results. The registry includes numerous outcome measures and analyses, but the adjustment strategy or testing hierarchy is not reported. Secondary findings therefore need to be considered in the context of multiple comparisons rather than treated as independent confirmations.

The registry does not report the original sample-size assumptions, the design’s sample-size justification, or an interim-analysis plan. The planning illustrations are based on the observed effect and cannot fill those gaps. Finally, the posted group summaries and statistical results do not provide participant-level information, so they cannot support additional analyses of distributions, subgroups, or missingness beyond those explicitly reported.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Randomized Clinical Trial Of Bococizumab (PF-04950615; RN316) In Subjects With Hyperlipidemia Or Mixed Dyslipidemia At Risk Of Cardiovascular Events — NCT01968954.
• Registry record last updated 2017-05-17; status last verified 2017-03.
• Results first posted 2017-05-17.
• 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.

23. Record Summary

This completed Phase 3 study was randomized, quadruple-masked, and parallel-group, comparing PF-04950615 150 mg with placebo in participants with primary hyperlipidemia or mixed dyslipidemia at risk of cardiovascular events. The recorded enrollment was 711. The primary endpoint was percent change from baseline in LDL-C at Week 12.

The posted arm means were 1.0 for placebo and -55.6 for PF-04950615 150 mg. The sponsor’s MMRM analysis reported a least-squares mean difference of -57.0, with a 95% confidence interval from -61.0 to -53.1 and p < 0.001. The unadjusted recalculation was similar in direction and scale. These results concern LDL-C change, not cardiovascular events.

The record lists additional lipid outcomes and adverse-event summaries, but does not report the multiplicity approach, detailed missing-data procedures, original sample-size justification, or interim-analysis plan. The displayed planning figures are illustrations based on the observed effect, not the trial’s original design assumptions.