An Open-label Study of NRP104 in Adults With Attention Deficit Hyperactivity Disorder (ADHD): Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for An Open-label Study of NRP104 in Adults With Attention Deficit Hyperactivity Disorder (ADHD) (NCT00337285), a non-randomized phase 3 study. The primary outcome is Change in ADHD-RS-IV Total Score From Baseline at Up to One Year.

2. Clinical Question

The study is framed as a long-term assessment of safety and efficacy in adults with ADHD. Its primary measure is a symptom-rating score, while the listed secondary outcomes concern improvement on the CGI-I and change in PSQI total score from baseline. Those outcomes indicate the breadth of the study’s planned assessments, but their results are not reported in the registry record.

Because there is no control group, the study’s primary question is about change over time among treated participants, not about a treatment-versus-control contrast. A change observed during treatment would describe the measured participants’ scores; without a concurrent comparator, it would not by itself separate treatment-associated change from other influences on scores over time.

3. Trial Design

This is a Phase 3, completed, open-label, non-randomized, single-group study sponsored by New River Pharmaceuticals. The registry lists enrollment of 349 and identifies the intervention as Vyvanse (lisdexamfetamine dimesylate), also called NRP104. The official title describes a long-term study of 30 mg, 50 mg, or 70 mg per day in adults with ADHD.

The study began in 2006-07, and primary completion is listed as 2007-11. The status is completed. These dates and status describe the trial record; they do not establish when each participant started or finished treatment. Participant-level treatment duration and the way doses were assigned or changed are not reported in the registry record.

Open-label means the study is not described as masking treatment assignment. A single-group design means that the record does not list a separate control group. The allocation is explicitly non-randomized. Consequently, the study does not make a randomized comparison between treatment and control, and the listed doses should not be treated as independent randomized arms. The record does not describe the assignment process across doses.

The primary efficacy population is defined as treated participants with a baseline and at least one post-baseline primary efficacy measurement. This is a measurement-based eligibility definition for the primary analysis population, not necessarily the full enrolled group. The registry record does not report the number included in this population or the number contributing measurements at each follow-up time.

The brief summary states that the purpose was to assess long-term safety and efficacy at the listed doses. However, the registry information available for this analysis does not include the primary outcome estimate or a detailed statistical analysis plan. The design can therefore be described, but a treatment effect or its uncertainty cannot be reconstructed from the information reported.

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: Subjects received a 30, 50, or 70 mg once daily dose of Vyvanse for up to 1 year.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Intent-to-treat (ITT). Defined as all subjects who were treated and had both the baseline and at least one post-baseline primary efficacy measurement (i.e., ADHD-RS-IV total score)

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 Change in ADHD-RS-IV Total Score From Baseline at Up to One Year, measured over up to one year.

The primary endpoint is change from baseline in the ADHD-RS-IV total score, measured for up to one year. The scale is the Attention Deficit Hyperactivity Disorder Rating Scale-fourth edition. It contains 18 items, each scored on a 4-point scale from 0, no symptoms, to 3, severe symptoms; the total score ranges from 0 to 54.

This measure turns ratings across ADHD symptoms into a total score that can be followed over time. A baseline score gives a reference for assessing subsequent scores, and change from baseline describes how the measured score differs from that reference. Because the items are symptom ratings, the total score represents symptom burden on the scale rather than a direct measure of every aspect of functioning or quality of life.

The registry identifies the endpoint as a mean change and lists standard deviation as the dispersion measure. A mean summarizes the average score change in the analysis population, while a standard deviation describes variability among individual measurements around that average. Neither statistic alone indicates how precise the estimated mean is; that requires information such as a confidence interval or another measure of uncertainty.

The registry record does not report the mean change, its standard deviation, a confidence interval, or the exact assessment schedule. It also does not specify the sign convention used for change. Accordingly, the endpoint’s definition can be explained, but the magnitude, direction, and precision of the observed result cannot be interpreted from the record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The record describes a continuous primary outcome: change in ADHD-RS-IV total score from baseline. For a continuous measure, an analysis may summarize the observed changes with a mean and a measure of variability. The registry lists the mean as the summary parameter and standard deviation as the dispersion measure. These describe the central tendency and spread of the measurements, but the registry record does not provide their values.

What does the mean describe?

A mean change is an average across the observations included in an analysis. It can give a concise description of the group’s measured change, but it does not show whether participants had similar changes or widely varying ones. The standard deviation helps describe that variation. It is not the same as the uncertainty around the estimated mean: a confidence interval is used to communicate uncertainty in an estimate, and its width depends on the data and analysis. No confidence interval is reported in the registry record.

Change-from-baseline analyses use a starting measurement as the reference and evaluate subsequent measurements relative to it. This can make the endpoint directly relevant to the study’s stated question about score change over time. Interpretation still depends on the assessment timing, analysis population, handling of incomplete observations, and statistical model. Those details are not reported in the registry record, and the sign convention for the change is not stated.

Why does the design affect interpretation?

In a randomized controlled study, random assignment can support comparison of outcomes between groups, subject to the design and analysis assumptions. This record instead describes non-randomized allocation and a single group. The primary comparison is therefore not between a treatment group and a concurrent control group. A within-group change can describe scores over time, but it cannot by itself establish what would have happened over the same period in the absence of treatment.

The study is open-label, with no masking listed. In general, knowledge of treatment can influence expectations, reporting, assessment, or decisions made during a study. That is a general design consideration, not a claim that any particular influence occurred in this trial. The record does not describe assessor procedures or additional steps taken to limit such influences.

What can a confidence interval add?

In general, a confidence interval presents a range of values compatible with the data and the statistical method used. It helps readers assess the precision of an estimate, while a p-value addresses compatibility with a specified null hypothesis under the model. Neither measure replaces judgment about study design or clinical relevance. The registry record does not report a confidence interval or primary-outcome p-value, so these aspects of the result cannot be assessed.

The analysis population is described as intent-to-treat, with a specific definition: all subjects who were treated and had both baseline and at least one post-baseline primary efficacy measurement. This differs from assuming that every enrolled participant contributed to the primary analysis. The record does not provide the analyzed population size, reasons for missing measurements, or whether participants without the required measurements were included in any other analysis.

How should planning calculations be understood?

The planning assumptions describe an illustration based on an observed effect, with a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The illustrated effect is a stated fraction of the observed effect. These assumptions do not describe the actual design of this single-group trial, which has no like-for-like control comparison. A planning sample size calculated under such assumptions would be an illustration for a hypothetical two-arm design, not an observed property of this study and not evidence of observed power.

The record does not include the actual planning outputs or the observed primary effect needed to interpret those outputs. It also does not report the trial’s own sample-size justification. Thus, the stated assumptions can be distinguished from the study design, but no sample-size adequacy conclusion can be made from them.

Why does over-dispersion matter in general?

Over-dispersion refers generally to observed variability that exceeds what a statistical model expects. When it is present, a model that assumes less variability can understate uncertainty and make estimates appear more precise than warranted. The primary endpoint is continuous and is described using a mean and standard deviation; no over-dispersion assessment or corresponding model is reported. It would therefore be inappropriate to claim that over-dispersion was present or that a particular adjustment was used.

In short, the registry record identifies the endpoint type and summary approach but does not report the numerical outcome or enough analysis detail to reproduce or fully evaluate it. The study design also limits interpretation to description of change in a single group rather than a controlled treatment contrast.

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("Vyvanse")
n   <- c(345)
m   <- c(-24.8)
sp  <- c(11.7)
sd  <- sp      # posted standard deviations
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  Vyvanse  345  -24.800  11.700  -26.039  -23.561

11. Multiplicity, Missing Data and Analysis Populations

The registry lists a primary endpoint and secondary outcomes concerning CGI-I improvement and change in PSQI total score from baseline. It does not report how hypothesis testing across these outcomes was handled. In general, when several outcomes or analyses are tested, the chance of at least one apparently notable result can increase unless the analysis plan addresses multiplicity. This is a general statistical consideration; the registry record does not say whether an adjustment, hierarchy, or other strategy was used.

The record does not report interim analyses, rules for stopping, or a detailed prespecified statistical analysis plan. These items should not be inferred from the completed status or from the presence of outcome listings. The number of analyses recorded does not establish what hypotheses were tested or how results were selected for reporting.

The primary population is defined as treated participants with baseline and at least one post-baseline ADHD-RS-IV measurement. This makes eligibility for the described analysis dependent on observed measurements. The record does not report the number meeting that definition, reasons for missing data, how missing values were handled, or whether sensitivity analyses assessed the impact of missingness. It also does not specify whether all scheduled measurements or a particular follow-up measurement contributed to the estimate.

These omissions matter because missing-data methods and multiplicity procedures can affect both the estimated result and its uncertainty. Without the relevant details, readers cannot determine whether the reported analysis, if available, followed a prespecified strategy or how robust it is to alternative assumptions. In this record, the primary outcome result itself is not reported, further limiting assessment.

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

The study record describes an evaluation of NRP104 in adults with ADHD, using change in ADHD-RS-IV total score as its primary endpoint. It also lists safety assessments and secondary outcomes. The primary outcome estimate and the secondary outcome results are not reported in the registry record. Therefore, the record does not establish the observed direction or magnitude of symptom-score change, its statistical precision, or whether a reported test met a specified threshold.

Even if a within-group score change were available, its meaning would need to be kept distinct from a treatment-versus-control effect. This trial is open-label, non-randomized, and single-group, with no separate comparator. A change from baseline describes what happened to measured scores over time in the analyzed participants. It does not, on its own, tell readers what would have happened in a comparable group without treatment.

The endpoint is a symptom-rating total, not a complete measure of each participant’s experience or every outcome relevant to ADHD. The registry’s secondary measures broaden the stated assessment scope, but their results are absent from the record. Likewise, the safety entries identify reported events but lack the at-risk denominators needed to interpret them as rates in the available information.

These limits do not erase the descriptive purpose of the trial. The record documents a long-term, open-label study structure and identifies the outcome measures used to frame its questions. It does mean that claims about the magnitude, precision, causality, or comparative safety of treatment cannot be supported by the information reported. A missing result is not evidence of no change or no effect; it means the registry record does not provide the result needed to judge it.

13. Why This Trial Matters Statistically

This trial illustrates why design and reporting have to be considered alongside an endpoint definition. The registry identifies a standardized symptom scale, a mean change-from-baseline outcome, and a long-term assessment purpose. Those features tell readers what was intended to be measured. They do not, without the estimate and its uncertainty, show what the study observed.

The single-group, open-label structure is central to the statistical interpretation. It can describe change among participants who contribute measurements, but it lacks the concurrent comparison needed to distinguish that change from other influences over time. Recognizing this distinction prevents a within-group result from being read as though it were a randomized treatment contrast.

The record also demonstrates the importance of transparent reporting for analysis populations, missing observations, multiplicity, and uncertainty. The primary population definition is available, but the number analyzed and the handling of missing data are not reported. The outcome estimates, confidence interval, and testing details are also absent. Without them, readers cannot judge precision or reconstruct the analysis.

Finally, sample-size planning assumptions should not be confused with a trial’s actual design or with observed power. The planning assumptions describe a hypothetical two-arm illustration, whereas this study is single-group. Keeping those concepts separate is important when interpreting statistical planning material associated with a trial record.

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.

The most important limitation for interpreting results is that the registry record does not report the primary endpoint estimate. It also omits the reported standard deviation and confidence interval, so neither the size nor precision of the mean change can be evaluated. The direction convention for change is not stated.

The study has no separate control group and is described as open-label and non-randomized. This limits interpretation of any within-group change as a treatment effect. The registry record does not describe how the listed daily doses were assigned, whether doses changed over time, or the treatment duration for individual participants.

For the primary analysis, the record defines an intent-to-treat population using treatment and availability of baseline and post-baseline measurements. It does not report how many participants met that definition, the amount or reasons for missing data, or the method used to address missingness. Assessment timing within the period of up to one year is also not specified.

The analysis plan is not reported in enough detail to assess multiplicity, interim analyses, model assumptions, or sensitivity analyses. The sample-size assumptions are planning illustrations rather than a description of the trial’s own design, and the actual planning outputs and sample-size justification are not reported.

The adverse-event entries include counts but no at-risk denominators in the available record. As a result, those counts cannot be interpreted as comparative risks. The registry record does not provide enough information to assess the completeness of safety reporting or relate individual events causally to treatment.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: An Open-label Study of NRP104 in Adults With Attention Deficit Hyperactivity Disorder (ADHD) — NCT00337285.
• Registry record last updated 2012-08-20; status last verified 2012-08.
• Results first posted 2009-07-17.
• 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.

18. Record Summary

NCT00337285 is a completed Phase 3, open-label, non-randomized, single-group study sponsored by New River Pharmaceuticals. It enrolled adults with ADHD and evaluated NRP104, identified as Vyvanse (lisdexamfetamine dimesylate), at 30 mg, 50 mg, or 70 mg per day. The record lists enrollment of 349, a start date of 2006-07, and primary completion in 2007-11.

The primary endpoint was mean change from baseline in ADHD-RS-IV total score for up to one year. The primary analysis population is defined as treated participants with baseline and at least one post-baseline primary efficacy measurement. Secondary outcomes listed are CGI-I improvement and change in PSQI total score from baseline.

The registry record does not report the primary outcome estimate, its uncertainty, detailed missing-data methods, multiplicity procedures, or a full analysis plan. The single-group design does not provide a concurrent control comparison. Safety entries list 8 participants with serious adverse events and 306 with other adverse events, without reported at-risk denominators.