Stimulant Versus Nonstimulant Medication for Attention Deficit Hyperactivity Disorder in Children: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Stimulant Versus Nonstimulant Medication for Attention Deficit Hyperactivity Disorder in Children (NCT00183391), a randomized phase 4 study. The primary outcome is ADHD-RS Total Score.

2. Clinical Question

In statistical terms, the clinical question concerns how the recorded symptom score compares under the two treatments in the enrolled population. Because this is a crossover design, treatment periods and their order can matter when interpreting a comparison. Randomization and masking are recorded, but the registry information available does not establish the sequence structure, handling of period effects, or whether the primary analysis used within-participant comparisons. Those details are important for understanding exactly what treatment effect the analysis was intended to estimate.

3. Trial Design

This was a phase 4, randomized, double-masked crossover trial sponsored by Icahn School of Medicine at Mount Sinai. The registry lists 232 participants as enrolled. The study began in 2005-07, reached primary completion in 2011-06, and is recorded as completed. Its registered purpose was to determine the effectiveness of stimulant and nonstimulant medication for ADHD symptoms in children and adolescents.

The two drug interventions were atomoxetine and methylphenidate. The registry describes atomoxetine as a non-stimulant and methylphenidate as a stimulant. A crossover design means that treatment comparisons are organized around participants receiving treatments in different periods or blocks, rather than relying only on separate groups that remain on a single assigned treatment. This design can support comparisons within participants, but the registry record does not report the treatment sequence, period lengths, washout details, or analysis method. Those details should not be inferred from the design label alone.

The primary outcome was ADHD-RS Total Score, with a timeframe of up to 14 weeks. The registry also lists secondary outcomes concerning treatment preference, ADHD hyperactivity/impulsivity and inattention, clinical global severity, social skills, child conflict, continuous performance, and sleep. There are 26 outcome measures recorded, but their individual timing and analysis details are not reported in the registry record.

The record identifies randomized allocation and double masking, but does not describe how randomization was generated, how treatment allocation was concealed, or how masking was implemented. It also does not report the protocol’s sample-size justification, a prespecified statistical analysis plan, or whether interim analyses were planned. The registered design gives useful context, while leaving these operational and analytic details unresolved.

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.

Block 1 - 5 Weeks

Reasons for not completing this period:

Crossover Placebo - 2 Weeks

Block 2 - 5 Weeks

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: see participant flow section for participants that did not complete blocks

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 ADHD-RS Total Score, measured over up to 14 weeks.

The primary endpoint was ADHD-RS Total Score, a measure based on the Attention Deficit Hyperactivity Disorder Rating Scale. The registry describes an 18-item measure in which each item is scored on a 4-point scale, from 0 (no symptoms) to 3 (severe symptoms). The possible total score is 0-54, with higher scores indicating a higher probability of diagnosis. The registry lists the outcome as a mean of a continuous measure, with standard deviation as the dispersion measure and a timeframe of up to 14 weeks.

A total score turns responses across the scale’s items into a summary measure that can be compared between treatment conditions. In general, a mean describes the average score in a group or treatment period, while a standard deviation describes how dispersed individual scores are around that mean. The mean is useful for expressing a group-level symptom measure; the spread helps show whether participants’ scores were relatively similar or varied substantially. Neither statistic alone conveys all individual experiences.

The registry does not report the primary outcome values, treatment difference, standard deviations, confidence interval, or p value. It also notes that the primary outcome has several categories or time points and was not reduced to one comparison. As a result, the endpoint’s measurement properties and intended timeframe can be described, but the size and precision of any treatment contrast cannot be established from the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The registry identifies the trial as randomized, double-masked, and crossover. These labels describe important features of the design, but do not by themselves specify the statistical analysis. The registry records no analyses and does not report a primary treatment-effect estimate, its uncertainty, or a prespecified analysis plan. Statistical concepts can clarify what would ordinarily need to be understood, but they cannot fill in those missing trial-specific details.

What does randomization contribute?

In general, randomization assigns treatment in a way intended to limit systematic differences associated with treatment choice. It supports a fair comparison when allocation is implemented as planned and when analysis respects the design. The record says allocation was randomized, but does not describe the randomization sequence, concealment, or how assignment to crossover sequences was performed. Those implementation details are not reported in the registry record.

What does crossover mean for analysis?

In general, a crossover study compares treatment periods, and may use information from the same participant under different treatments. This can account for stable differences between participants, but it also makes period, sequence, and carryover considerations relevant. A period effect is a change associated with when treatment is received; a sequence effect concerns the order of treatments; carryover refers to effects that persist into a later period. The registry does not report the treatment sequence, washout arrangements, or whether these effects were evaluated. It also does not report whether the primary analysis was within-participant or used another approach.

How should a continuous endpoint be understood?

The primary endpoint is a continuous total score, and the registry identifies the mean and standard deviation as its summary measures. In general, the mean gives the average score in the analyzed observations. The standard deviation describes the spread of scores around that average. A treatment comparison could be expressed as a difference in means, but the registry supplies no such estimate. The record also does not give the outcome values needed to independently verify a comparison.

Precision matters alongside the estimated effect. In general, a confidence interval communicates uncertainty around an estimate: a narrower interval indicates greater precision under the model and assumptions used, while a wider interval indicates less precision. A p value addresses compatibility of the data with a specified null hypothesis under a statistical model; it does not measure clinical importance or provide the probability that a treatment effect is true. Neither a confidence interval nor a p value for the primary comparison is reported in the registry record.

Why can over-dispersion matter?

Over-dispersion is a general issue for outcomes whose observed variability exceeds what a chosen model assumes. If a model understates variability, standard errors may be too small and uncertainty may appear less than it is. Appropriate modeling or robust uncertainty estimates can address this in some settings. This is a general statistical consideration, not a reported feature of this trial. The registry’s primary endpoint is a continuous score, and it does not report a model, variance assessment, or over-dispersion analysis.

What do the planning assumptions mean?

The stated sample-size illustration is based on an observed effect and is explicitly described as separate from the trial’s own design. Its assumptions specify a two-sided significance level of 0.05, equal allocation between arms, and a normal approximation; the effect to detect is defined as a stated fraction of the observed effect. The illustration is planning information, not a measure of achieved power. Achieved power is not established by substituting the observed effect into a planning calculation, and the numerical sample-size justification for the original trial is not reported in the registry record.

The registry does not report the primary effect estimate needed to assess the illustration’s inputs in this summary, nor does it state the original sample-size assumptions or justification. Thus, a reader should distinguish the planning method from the trial’s actual design decisions and should not interpret a planning calculation as a trial result.

10. Multiplicity, Missing Data and Analysis Populations

The registry lists 26 outcome measures, including the ADHD-RS Total Score and secondary measures covering treatment preference, ADHD hyperactivity/impulsivity, inattention, clinical global severity, social skills, child conflict, continuous performance, and sleep. The primary outcome is noted as having several categories or time points and not being reduced to one comparison. The registry does not state which comparison was designated as primary for statistical testing, how the other outcomes were ordered, or how multiple comparisons were handled.

In general, testing multiple outcomes, time points, or subgroups can increase the chance of observing an apparently notable result by chance. Multiplicity procedures can control or describe that issue, but the appropriate approach depends on the prespecified questions and analysis plan. No multiplicity strategy is reported in the registry record. The registry records zero analyses, so no posted analysis results can clarify how outcome selection or multiplicity was handled.

The primary outcome population description refers to participant flow for participants who did not complete blocks. The participant-flow details needed to determine which participants contributed to each endpoint analysis are not reported in the registry record. The record does not state how missing scores were handled, whether an intention-to-treat or other analysis population was used, or whether sensitivity analyses assessed the influence of missing data. In general, missing-data methods rely on assumptions about why observations are absent; without the method and analysis population, the potential effect of missingness on the estimate cannot be assessed.

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 5% reporting threshold.

Most frequent non-serious adverse event terms

The registry reports serious adverse events by treatment block. For Block 1 ATX, 108 participants were at risk and 0 were reported with a serious adverse event; for Block 1 MPH, 124 were at risk and 0 were reported with a serious adverse event. For Block 2 ATX, 95 were at risk and 0 were reported with a serious adverse event; for Block 2 MPH, 110 were at risk and 0 were reported with a serious adverse event. Deaths are recorded as 0 in each block.

Other adverse events are reported as 24 in Block 1 ATX, 35 in Block 1 MPH, 20 in Block 2 ATX, and 25 in Block 2 MPH. These counts should be read alongside their block-specific at-risk counts. Because the study is a crossover trial, participants may appear in more than one block. The block counts therefore should not be added or interpreted as counts of distinct participants across the full study. The registry does not provide event descriptions for these other adverse events in the listed record or a statistical comparison between treatments.

A zero count means that no event was recorded in that category for the listed block; it does not prove that the underlying risk is absent. These registry counts are descriptive and do not, on their own, establish a comparative safety effect.

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

The registry record establishes that a randomized, double-masked crossover study of atomoxetine and methylphenidate enrolled 232 participants and designated ADHD-RS Total Score as its primary outcome. It also describes the outcome scale, gives a timeframe of up to 14 weeks, and reports block-specific adverse-event counts. These details describe the trial’s purpose, design labels, endpoint, and recorded safety information.

What the record does not establish is the estimated difference in symptom scores between treatments. It does not provide treatment-specific means or standard deviations, a primary treatment contrast, a confidence interval, or a p value. The primary outcome is noted as having several categories or time points and not being reduced to one comparison, and the registry records zero analyses. The direction and magnitude of any treatment difference, and the precision with which it might have been estimated, are therefore not reported in the registry record.

In general, a registered aim is not evidence that a treatment produced a particular outcome. A design label does not identify the result, and a sample-size planning illustration does not show that the trial achieved a particular level of precision. Similarly, zero serious adverse events recorded in the listed blocks is a description of the reported data, not proof that a treatment has no serious risk. The other adverse-event counts are also descriptive and are not accompanied by a reported comparative analysis.

The most defensible interpretation is consequently limited: the record documents a completed trial with a specified symptom measure, crossover design, and block-level safety counts, but does not report the analysis needed to answer the primary comparative question. No conclusion about the relative symptom outcomes or comparative safety of the medications can be drawn from these registry entries alone.

13. Why This Trial Matters Statistically

This trial is statistically notable because its crossover design makes the structure of treatment periods central to interpretation. When participants receive treatments across blocks, an analysis may need to account for within-participant observations and for possible period or sequence effects. The registry identifies the design but does not report the treatment sequences, washout details, or analysis method. That gap illustrates why design labels are informative but insufficient to reconstruct an estimand or analysis.

The primary endpoint is a continuous symptom score with a defined scale and direction. Such an endpoint can support a direct comparison of average scores, but the registry does not report those averages or a treatment contrast. This highlights the difference between a well-described measurement instrument and a reported statistical result. Knowing the endpoint’s range and interpretation does not reveal the size or precision of an effect.

The record also lists 26 outcome measures and notes that the primary outcome has several categories or time points without reducing them to one comparison. This raises general questions about prespecification, multiplicity, and which comparison should be treated as primary. The registry does not report the analysis plan or multiplicity handling, so those questions remain unresolved rather than answerable from the outcome list alone.

Finally, the block-specific safety counts show why denominators and study structure matter. At-risk counts differ by block, and crossover participants can contribute to multiple blocks. Clear reporting of the analysis population, missing-data handling, and treatment comparison would help readers judge what the posted estimates represent. Those analytic results and details are not reported in the registry 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 main limitation for statistical interpretation is the absence of a reported primary-outcome comparison. The registry supplies the ADHD-RS Total Score description but not treatment-specific scores, a treatment difference, uncertainty estimates, or a test result. It also records zero analyses and states that the primary outcome has several categories or time points without reducing them to one comparison. The registered endpoint therefore cannot be used to assess the size or precision of a treatment contrast.

The crossover design is not described in enough detail to establish how treatment order, periods, or possible carryover were addressed. The registry does not report the analysis model, randomization procedures, masking procedures, or whether within-participant information was used. It also does not report the original sample-size justification or a statistical analysis plan. Numerical planning illustrations are not a substitute for those trial-specific design details.

The primary outcome population description points to participant flow for those who did not complete blocks, but the needed flow information is not reported in the registry record. The analysis population, missing-data method, and any sensitivity analyses are also not reported. These omissions make it difficult to assess how incomplete observations may affect interpretation.

There are 26 outcome measures, yet the registry does not report a multiplicity strategy or identify a single comparison among the listed categories and time points. The safety data are block-specific and descriptive; the record provides no comparative analysis, and crossover participation means block counts should not be treated as unique participant counts. These limitations concern what can be concluded from the registry record, not necessarily what was done outside the record.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Stimulant Versus Nonstimulant Medication for Attention Deficit Hyperactivity Disorder in Children — NCT00183391.
• Registry record last updated 2018-06-06; status last verified 2018-05.
• Results first posted 2018-06-06.
• 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

The registry record describes a completed phase 4 randomized, double-masked crossover study sponsored by Icahn School of Medicine at Mount Sinai. It lists enrollment of 232 participants and compares atomoxetine, a non-stimulant, with methylphenidate, a stimulant. The study’s stated purpose was to assess medication effectiveness for ADHD symptoms in children and adolescents.

The primary endpoint was ADHD-RS Total Score, a continuous measure on a possible 0-54 scale, with higher scores indicating a higher probability of diagnosis. Its timeframe was up to 14 weeks. The registry lists 26 outcome measures and provides block-specific adverse-event counts, including zero serious adverse events and zero deaths in each reported block.

The registry records zero analyses and does not report a single primary-outcome comparison, treatment estimates, uncertainty measures, or a statistical analysis plan. Details on treatment sequence, participant flow, missing-data handling, and multiplicity are not reported in the registry record. The available information describes the trial’s design and recorded outcomes, but does not establish the comparative symptom result.