A Randomized Placebo-Controlled Study of Lovastatin in Children With Neurofibromatosis Type 1: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Randomized Placebo-Controlled Study of Lovastatin in Children With Neurofibromatosis Type 1 (NCT00853580), a randomized phase 2 study. The primary outcome is Paired Associate Learning (Cambridge Neuropsychological Test Automated Battery)..

2. Clinical Question

The study’s stated aim was to assess whether lovastatin improved visuospatial learning and/or sustained attention in children with NF1. Its secondary aims covered a broader set of cognitive and behavioral domains and the treatment’s toxicity and tolerability. Those aims describe questions the trial was designed to investigate; they do not establish what the results were.

The primary measure was Paired Associate Learning from the Cambridge Neuropsychological Test Automated Battery. The registry describes performance in terms of total errors: a higher number indicates poorer performance. The assessment was scheduled at baseline and after treatment. However, a numerical comparison of performance between the randomized groups, including an estimate of the difference and its precision, is not reported in the registry record. The clinical question can therefore be identified, but the posted record does not allow the reader to determine the observed primary-outcome effect.

3. Trial Design

The registry describes a randomized, placebo-controlled, parallel-group Phase 2 study sponsored by the University of Alabama at Birmingham. It lists quadruple masking, meaning the masking designation was recorded at that level in the registry; further details about which individuals were masked or how masking was maintained are not reported in the registry record. The trial status is completed. Enrollment was 146.

The intended population was children with NF1 aged 8 to less than 16 years. The study’s stated focus was children with NF1 and cognitive deficits. The intervention groups were lovastatin and placebo. The treatment period relevant to the primary outcome is described as 16 weeks, with Paired Associate Learning assessed at baseline and post-treatment. The registry record lists a start date of 2009-07 and primary completion date of 2014-05. These dates describe the trial record and do not, by themselves, explain the duration of any individual participant’s treatment or follow-up.

The primary outcome was a continuous measure, reported as mean PAL Total Errors with standard error as the dispersion measure. The record describes an intention-to-treat analysis using a modified intention-to-treat population, defined as subjects with baseline data. Missing post-treatment values were imputed using linear regression with age, sex, and baseline values as predictors, using 20 imputations.

Several details needed to reconstruct or assess the full design are not reported in the registry record. These include the planned allocation ratio, the treatment dose and schedule, the full eligibility criteria, the precise randomization procedure, and operational details of masking. The sample-size justification and any interim-analysis plan are also not reported. The record gives a planning-illustration description, but does not report a trial-specific sample-size justification.

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: After obtaining consent, participants were screened for study inclusion. If entry criteria were passed, they were randomized to study. All randomized participants were included in the primary efficacy analysis (baseline-to-post treatment) if they completed the baseline assessments.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Intention to treat using the modified intention-to-treat population (defined as all subjects that had baseline data). Missing post-treatment values were imputed using linear regression with age, sex and baseline values used as predictors (20 imputations).

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: Primary analyses of efficacy and safety were performed on the baseline to post-treatment data using the modified intention-to-treat population (defined as all subjects that had baseline data). Two participants from the placebo condition were excluded due to failure to complete baseline assessment.

6. Primary Endpoint

The registry lists the primary outcome as Paired Associate Learning (Cambridge Neuropsychological Test Automated Battery)., measured over Baseline and Post-treatment (16 weeks).

Paired Associate Learning (PAL), from the Cambridge Neuropsychological Test Automated Battery, was the primary outcome. The registry describes it as a computerized test of visuospatial learning. Participants were shown patterns associated with locations on a screen and, during the test phase, were asked to select the location associated with each presented pattern. The task begins simply and becomes more difficult.

The recorded unit was PAL Total Errors. More errors indicate poorer performance, according to the registry description. The scale has no stated maximum range. The outcome was assessed at baseline and post-treatment, with the post-treatment assessment scheduled at 16 weeks. The registry lists the measure as a mean with standard error as its dispersion statistic.

This kind of task provides a structured way to quantify performance in a cognitive domain relevant to the study’s stated question about visuospatial learning. It is an outcome measure, not a direct measurement of everyday functioning. The registry also identifies attention as a central study aim, but the primary endpoint named in the record is PAL Total Errors rather than an attention measure.

The registry record does not report the group means, a between-group estimate, a confidence interval, or a p-value for the primary outcome. It also indicates that the primary outcome has several categories or time points and was not reduced to one comparison. Consequently, the endpoint’s purpose and direction can be explained, but the magnitude and precision of an observed treatment contrast cannot be assessed from the posted primary-outcome information.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry describes the study as randomized, placebo-controlled, quadruple-masked, and parallel-group. Randomization is intended to create groups that are comparable on average at the start of a trial, although chance imbalances can remain. A placebo comparator gives the treatment group a concurrent reference group. Masking is intended to limit the influence of knowledge about assigned treatment on participants’ experiences, assessment, or interpretation. These are general purposes of the design features; the operational details of randomization and masking are not reported in the registry record.

What does a mean with standard error describe?

The primary outcome was reported in the registry as a mean of PAL Total Errors, with standard error as the dispersion measure. A mean describes the average measured performance in a group. Standard error describes the statistical uncertainty around an estimated mean under the analysis assumptions; it is not a description of the spread of individual participants’ scores. General statistical interpretation typically benefits from a between-group estimate and a confidence interval, because these show both the estimated contrast and its uncertainty. Those primary-outcome statistics are not reported in the registry record.

The outcome is continuous, so a treatment comparison would generally concern a difference in the scale’s measured values rather than a count of participants reaching a binary state. That is a general explanation, not a claim about the specific model used in this trial. The exact test or model for the primary comparison is not reported in the registry record. Nor is the exact contrast used to summarize baseline and post-treatment measurements reported.

How should the modified intention-to-treat population be understood?

The registry defines the modified intention-to-treat population as all subjects who had baseline data. This definition retains participants on the basis of baseline availability, but it is not identical to an analysis that includes every randomized participant regardless of available data. The record does not report the number randomized to each group, the number included in this population, or the number contributing observed post-treatment measurements. Therefore, the extent to which the analysis population differed from the enrolled population cannot be assessed.

The registry states that missing post-treatment values were imputed using linear regression, with age, sex, and baseline values as predictors, using 20 imputations. In general, multiple imputation creates several completed analysis datasets by replacing missing values with plausible values drawn under a specified model, analyzes each dataset, and combines the resulting estimates to reflect imputation uncertainty. The method relies on assumptions about the missing-data process and the imputation model. The registry’s brief description does not report those assumptions, model diagnostics, imputation results, or sensitivity analyses. It is therefore not possible to evaluate how well the imputation model represented the observed data or how robust the result was to other assumptions.

What can be inferred from the planning description?

The registry describes a sample-size planning illustration based on the observed effect, with a two-sided significance level of 0.05, equal allocation, and a normal approximation. It also says the effect to detect is expressed as a stated fraction of the observed effect. Such an illustration is a planning calculation: it asks how many participants per arm might be needed under specified assumptions. It is not observed power, does not show the probability that the completed trial detected an effect, and does not establish that the trial was designed using those assumptions. The trial’s own sample-size justification is not reported in the registry record.

The registry’s planning description distinguishes total events for time-to-event outcomes from participants per arm for other outcomes. The primary measure in this study is continuous, and the applicable planning figures are not reported in the registry entries for this analysis. No sample-size value should therefore be inferred from the planning description alone.

Why do confidence intervals and multiplicity matter?

In general, a confidence interval presents a range of values compatible with an estimate under a statistical procedure and its assumptions. Its width conveys precision: a wider interval indicates greater uncertainty than a narrower interval. Statistical significance alone would not describe the size or practical relevance of an effect. In this case, no primary-outcome confidence interval or effect estimate is reported in the registry record, so neither precision nor magnitude can be assessed.

The study lists multiple outcome measures and analyses. When many outcomes or contrasts are examined, the chance of at least one apparently unusual result can increase if each is assessed without accounting for the family of comparisons. Methods such as adjustment or a prespecified hierarchy can address that concern, depending on the analysis plan. The multiplicity strategy is not reported in the registry record. The number of listed outcomes and analyses alone does not reveal whether adjustment was used or how the primary and secondary questions were prioritized.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists 20 outcome measures and 20 analyses, while the primary endpoint is described as having several categories or time points and is not reduced to one comparison. This means the posted record does not identify a single numerical primary contrast that can be interpreted as the definitive result. The statistical plan for selecting among outcome categories or time points is not reported in the registry record.

When a study examines multiple outcomes, time points, or contrasts, interpreting isolated findings requires attention to multiplicity. In general, the more comparisons considered, the greater the chance that at least one may appear noteworthy by chance if no strategy accounts for the family of tests. Adjustment procedures or prespecified testing hierarchies can help manage this issue. Whether any such method was used, and what the prespecified hierarchy was, are not reported in the registry record. The number of outcomes alone is not evidence that a particular adjustment was or was not performed.

For missing data, the registry defines its modified intention-to-treat population as subjects with baseline data. It states that missing post-treatment values were imputed by linear regression using age, sex, and baseline values as predictors, with 20 imputations. The number of participants with missing post-treatment measurements, the distribution of missingness across groups, and the imputed outcome results are not reported in the registry record. Sensitivity analyses assessing alternative missing-data assumptions are also not reported.

These omissions limit assessment of both multiplicity and missing-data robustness. They do not demonstrate that the analysis was invalid, but they prevent a reader from checking the relevant assumptions or tracing how the reported analysis population and imputation affected an effect estimate. No primary-outcome effect estimate is reported in the registry record, so the consequences of these analytic choices cannot be quantified from the posted information.

11. 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: serious adverse event (2.7%).

The registry reports serious adverse-event counts for the lovastatin and placebo groups. The serious adverse-event categories list 74 participants at risk and 6 affected in the lovastatin group, and 70 at risk and 1 affected in the placebo group. Deaths are reported as 0 in each group. The record also lists a top serious-event term, “Serious Adverse Event,” with 2.7%.

These are descriptive safety figures. “At risk” gives the group count recorded for the category, while “affected” gives the number recorded as experiencing a serious adverse event. The figures do not by themselves establish causation, describe event severity in detail, or show the timing or duration of events. The registry entries do not provide enough detail to reconcile the listed term percentage with the affected counts, so the percentage should be read as reported rather than recalculated or interpreted using an assumed denominator.

The registry also reports other adverse events affecting 65 participants in the lovastatin group and 59 in the placebo group, with 74 and 70 at risk, respectively. These are separate “other adverse” counts and should not be conflated with the serious adverse-event counts. Definitions, event-level detail, exposure time, and statistical comparisons are not reported in the registry record. The counts describe what was recorded, but are not by themselves a comparative safety analysis.

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

The registry record establishes that a randomized, placebo-controlled Phase 2 study evaluated lovastatin in children with NF1, with a primary focus on Paired Associate Learning and additional cognitive, behavioral, quality-of-life, and safety aims. It describes the primary measure and the intended assessment period, and it gives a brief account of the analysis population and missing-value procedure. Those details help explain what the study asked and how some data were handled.

However, the primary-outcome result is not reported in the registry record. There is no reported group comparison, effect estimate, confidence interval, or p-value in the information available for interpretation. It is therefore not possible to say whether the observed primary measure favored one group, how large any difference was, or how precisely it was estimated. An absent result is not evidence that the groups were the same, and it is not evidence that the treatment had no effect.

The record’s aims and hypotheses are not results. The stated expectation that lovastatin might improve aspects of cognition, and the stated expectation about safety and tolerability, describe the rationale for conducting the study. They do not show whether the hypotheses were supported. Similarly, the list of secondary outcomes does not establish findings on attention, executive function, behavior, or quality of life.

Safety counts are available for serious and other adverse events, as well as deaths. These figures can be described as recorded counts, but detailed event descriptions, exposure-adjusted comparisons, and a causal assessment are not reported in the registry record. The safety information should not be interpreted as proving either the presence or absence of a treatment-related risk.

The most defensible reading is consequently limited: the record documents a completed randomized study and its stated measurement and analysis approach, but does not provide enough outcome results to judge the primary clinical question. Any conclusion about efficacy, lack of efficacy, equivalence, or overall benefit and harm would go beyond the results reported in the registry record.

13. Why This Trial Matters Statistically

This trial illustrates why the design description and the outcome results must be read separately. Randomization, placebo control, masking, and a defined cognitive measure describe ways the study sought to make a treatment comparison interpretable. They do not substitute for an estimated treatment effect or its uncertainty. A registry can identify the question and measurement strategy while still leaving the central statistical result unavailable.

The primary outcome is a continuous error score with a clear direction: higher scores indicate poorer performance. That allows the measure to be understood in principle, but interpretation of a trial still requires the observed values and a suitable group contrast. Without that contrast, readers cannot assess the magnitude or precision of the result, or distinguish a small, uncertain estimate from a larger, more precise one.

The record also highlights common analysis issues in clinical trials. A modified intention-to-treat population may differ from the full randomized population, and missing-data imputation relies on assumptions. Multiple outcomes and time points can create multiplicity concerns. Here, the registry gives some details about population definition and imputation, but does not report participant-level missingness, sensitivity analyses, or the multiplicity strategy. Those limits matter because they restrict the reader’s ability to audit the robustness of an analysis.

Finally, the serious adverse-event counts show why safety reporting needs context as well as numbers. Counts by group are useful descriptive information, but event definitions, timing, exposure, and comparative methods affect what conclusions are justified. This trial is statistically informative as an example of the distinction between a documented study design and a fully interpretable set of posted results.

14. 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.

A central limitation for interpreting this trial from the registry record is the absence of a reported primary-outcome comparison. Group means, an effect estimate, a confidence interval, and a p-value are not reported in the registry record. The registry also notes that the primary outcome has several categories or time points and was not reduced to one comparison. This prevents a reader from identifying and evaluating a single quantitative primary result.

The record describes the primary analysis population as subjects with baseline data and states that missing post-treatment values were imputed using linear regression with age, sex, and baseline values as predictors, using 20 imputations. It does not report the number of missing observations, the analysis-population size by group, the amount of observed post-treatment data, or sensitivity analyses. The impact of missingness and imputation therefore cannot be judged.

Multiplicity is another unresolved issue. The registry lists 20 outcome measures and 20 analyses, but the statistical approach for handling multiple outcomes, categories, or time points is not reported in the registry record. The record also does not report the precise primary contrast or enough detail about the statistical model to reproduce the analysis. The trial’s sample-size justification and any interim-analysis plan are not reported.

Details of the treatment regimen, allocation procedure, masking operations, and full eligibility criteria are also not reported in the registry record. Although the study is described as completed and randomized, these omissions limit assessment of implementation and generalizability. The safety information is presented as group counts and a listed serious-event term, without event-level descriptions or exposure-based analysis. These limitations concern what can be evaluated from the registry record; they do not establish that the underlying trial lacked these methods or data.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: A Randomized Placebo-Controlled Study of Lovastatin in Children With Neurofibromatosis Type 1 — NCT00853580.
• Registry record last updated 2018-03-12; status last verified 2018-03.
• Results first posted 2018-03-12.
• 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.

18. Record Summary

NCT00853580 is a completed randomized, placebo-controlled Phase 2 study of lovastatin in children with NF1, sponsored by the University of Alabama at Birmingham. The registry lists quadruple masking, a parallel-group model, and enrollment of 146. The recorded start date is 2009-07, and the primary completion date is 2014-05.

The primary outcome was Paired Associate Learning Total Errors, a computerized visuospatial-learning measure assessed at baseline and post-treatment at 16 weeks. Higher error counts indicate poorer performance. The analysis population was defined as subjects with baseline data; missing post-treatment values were imputed using linear regression with age, sex, and baseline values as predictors, using 20 imputations.

The registry record does not report the primary-outcome comparison or its effect estimate and precision. It lists multiple outcome measures and analyses, without reporting the multiplicity strategy. Serious adverse-event counts and deaths are listed by group, but the posted information does not include enough detail for a full comparative safety assessment.