Study to Assess the Benefit of Midodrine in the Treatment of Patients With Neurogenic Orthostatic Hypotension: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Study to Assess the Benefit of Midodrine in the Treatment of Patients With Neurogenic Orthostatic Hypotension (NCT00555880), a randomized phase 4 study. The primary outcome is Time to Onset of Near-syncopal Symptoms During Tilt Table Testing.

2. Clinical Question

3. Trial Design

This was a Phase 4, randomized, quadruple-masked, placebo-controlled crossover study of midodrine hydrochloride. The registry record describes the study as multi-center and double-blind in its official title, and records masking as quadruple. Enrollment was 24. The study status is completed; its start date was 2004-09-08 and its primary completion date was 2005-03-21.

A crossover design means participants receive treatments in a sequence, rather than being assigned to a single treatment for the entire study. The safety groups are named Midodrine/Placebo and Placebo/Midodrine, consistent with two treatment sequences. In general, crossover studies can make comparisons within participants, but interpretation depends on the planned handling of treatment periods, sequence, and possible carryover. Those details are not reported in the registry record, so the posted summary means should not be taken as a full account of the crossover analysis.

The primary outcome was assessed 1 hour post-dose in the Full Analysis Set. That set included randomized subjects who received at least one dose of study drug and had at least one measurement of time to syncope during tilt-table testing. The posted primary outcome means use 24 subjects for each treatment. The registry record also lists a per-protocol population for secondary analyses, with 21 subjects in each treatment group for the posted per-protocol means.

The registry record does not report the original sample-size justification, the intended statistical model for the primary endpoint, details of treatment-period allocation, or procedures for handling missing outcome measurements. It also does not report the protocol’s planned interim analyses or a full prespecified analysis plan. The available information supports describing the randomization, masking, crossover model, treatments, and outcome populations, but not filling in these design details by assumption.

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.

Treatment Period 1 (1 Day)

Washout (1 Day)

Treatment Period 2 (1 Day)

Analysis population for the primary outcome, as defined in the registry: The Full Analysis Set (FAS), defined as subjects who were randomized, received at least one dose of study drug, and had at least one measurement of time to syncope during tilt table testing.

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: The Safety and Full Analysis Set (FAS) populations, defined as all participants who received at least one dose of investigational product (Safety) and all participants who were randomized, received at least one dose of investigational product, and had at least one measurement of the time to near syncope during a tilt table test (FAS).

6. Primary Endpoint

The registry lists the primary outcome as Time to Onset of Near-syncopal Symptoms During Tilt Table Testing, measured over 1 hour post-dose.

The primary endpoint was time to onset of near-syncopal symptoms during tilt-table testing, measured in seconds at 1 hour post-dose. The test began after subjects rested on a horizontal table for at least 10 minutes. The table was then raised to a 70-degree angle over a period of up to 30 seconds. The assessment was designed to last 10 minutes.

Near-syncope symptoms were defined as dizziness, lightheadedness, feeling faint, or feeling as though the subject might black out. The endpoint was a confirmed symptom report severe enough that the patient asked for the table to be returned to horizontal. It therefore measures how long the subject continued the tilt test before reaching that symptom threshold, rather than a general symptom score or a direct measure of everyday functioning.

Time to symptom onset is useful for this laboratory challenge because it captures both whether symptoms emerge during the test and when they emerge. In general, an endpoint based on elapsed time can distinguish earlier from later symptom onset, while its interpretation remains tied to the test conditions and symptom definition. The posted analysis treats the measure as continuous and reports means and standard deviations. The registry record does not describe how observations without symptom onset during the test were handled, so that aspect of the endpoint’s analysis cannot be inferred.

7. Results Posted in the Registry

• Midodrine HCl: mean 551.30 versus 461.00 on control; difference 90.30 (95% CI 1.06 to 179.54), standardized effect d = 0.57; z-test p = 0.047.

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.

Time to Onset of Near-syncopal Symptoms in The Per-protocol Population

• 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:
  • Midodrine HCl: mean 544.30 versus 447.90 on control; difference 96.40 (95% CI -3.62 to 196.42), standardized effect d = 0.58; z-test p = 0.059.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Midodrine HCl and the control. The interval gives the range of effects that remain compatible with the data.

Time to Onset of Near-syncopal Symptoms in The Per-protocol Population Analysis #2

• 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 errors.
• Result:
  • Midodrine HCl: mean 545.10 versus 447.20 on control; difference 97.90 (95% CI -4.38 to 200.18), standardized effect d = 0.58; z-test p = 0.061.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Midodrine HCl and the control. The interval gives the range of effects that remain compatible with the data.

Time to Near-syncopal Symptoms at Treatment Visit 1

• 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 errors.
• Result:
  • Midodrine HCl: mean 539.50 versus 448.40 on control; difference 91.10 (95% CI -41.81 to 224.01), standardized effect d = 0.55; z-test p = 0.179.
• Interpretation:
  • The 95% confidence interval includes no difference, so these data do not show a statistically significant difference between Midodrine HCl and the control. The interval gives the range of effects that remain compatible with the data.

The secondary outcomes extend the assessment beyond the primary Full Analysis Set comparison. They include time to symptom onset in the per-protocol population, a further per-protocol analysis, time to symptoms at the first treatment visit, duration of effect at 3 hours post-dose, the Orthostatic Hypotension Symptom Assessment and its component items, and clinician and patient global-impression ratings. The registry lists 15 posted secondary outcomes and records 18 outcome measures and 16 analyses overall.

The posted secondary results do not form a uniform statistical pattern. The per-protocol mean comparison has a registry-reported Sign test p = 0.227, while the separate per-protocol Analysis #2 reports ANOVA p = 0.042. The first-treatment-visit analysis reports ANOVA p = 0.193. The associated recalculations also do not all align with the registry analyses. Those differences reinforce the need to distinguish sponsor-reported tests from simple recalculations rather than treating all estimates as outputs of one common model.

These outcomes relate to the primary result by examining similar symptom timing in different analysis sets or visits, and by adding symptom scores and global assessments. They do not replace the primary endpoint, which concerns time to symptoms during tilt-table testing in the Full Analysis Set at 1 hour post-dose. The registry record does not report a hierarchy assigning confirmatory status to the secondary measures.

General statistical explanation: testing many outcomes can produce apparently notable findings by chance, even when each test is considered separately. Unadjusted secondary results therefore carry less weight than a prespecified primary analysis unless the analysis plan establishes a clear multiplicity strategy. The registry record does not report such a strategy. Secondary findings are best read as supporting context and as prompts for further study, not as independent confirmation of a single treatment effect.

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

• Time to Onset of Near-syncopal Symptoms in The Per-protocol Population
• Time to Onset of Near-syncopal Symptoms in The Per-protocol Population Analysis #2
• Time to Near-syncopal Symptoms at Treatment Visit 1
• Duration of The Effect of Treatment at 3 Hours Post-dose
• Total Score of the Orthostatic Hypotension Symptom Assessment (OHSA)
• Scores for 6 Items of The OHSA
• Number of Participants With Improvement of Clinician Clinician's Global Impression- Improvement (CGI-I) Scores After Tilt Table Test
• Number of Participants With Improvement of Patient CGI-I Scores After Tilt Table Test

9. Statistical Interpretation

10. Statistical Methods Explained

What does a mean represent?

For a continuous outcome, the mean is the arithmetic average of the observed measurements. The primary endpoint is continuous because it records elapsed time in seconds. The posted mean was 551.3 seconds for Midodrine HCl and 461.0 seconds for placebo. A mean gives a concise description of the group’s central value, but it does not show the full distribution, the range of individual responses, or how treatment responses pair within participants in a crossover trial.

The primary outcome also reports standard deviations of 115.6 seconds for Midodrine HCl and 190.7 seconds for placebo. A standard deviation describes how spread out individual measurements are around the group mean. The larger placebo standard deviation indicates more spread in the posted placebo measurements than in the Midodrine HCl measurements. General statistical interpretation: when observations vary considerably, the mean difference is estimated less precisely unless there is enough information to offset that variability.

What does the recalculated mean difference describe?

The posted unadjusted recalculation compares the two treatment means and gives a mean difference of 90.3 seconds. Its confidence interval is 1.062 to 179.5 seconds, and its unadjusted p-value is 0.047. This is a simple recalculation from summary statistics. It is not the same as a model that accounts for paired observations, treatment sequence, or period effects in a crossover design. The registry’s reported primary method is a Sign test, with Sign Statistic 3.0 and p = 0.146. Because the sponsor-reported result differs from the recalculation, the sponsor’s analysis takes precedence.

In general, a p-value measures how compatible the observed data are with a specified null model, under the assumptions of the test. It is not the probability that the null hypothesis is true, nor does it measure the size or clinical importance of an effect. The two p-values should not be treated as interchangeable: they arise from different analyses and answer their questions under different assumptions.

Why does the crossover structure matter?

General statistical explanation: crossover data can use within-participant comparisons, because each participant may receive both treatments. Such analyses can account for the fact that measurements from the same person are related. An unpaired comparison of treatment summaries does not make that pairing explicit. Treatment sequence, period, and carryover can also affect interpretation. The registry record does not describe the sponsor’s primary model or provide enough detail to reconstruct those features. The reported Sign test is therefore the primary analysis to cite, rather than an assumed crossover model.

The primary analysis population was the Full Analysis Set, defined as randomized subjects who received at least one dose of study drug and had at least one measurement of time to syncope during tilt-table testing. A per-protocol population is also referenced for secondary analyses. The registry record does not provide the full eligibility rules for that population, so the difference between the sets cannot be explained beyond the posted counts and labels.

What do standard errors and least-squares means add?

Some secondary outcomes report least-squares means and standard errors rather than ordinary means and standard deviations. In general, a least-squares mean is a model-based estimate adjusted for terms included in the statistical model. A standard error describes the estimated uncertainty in an estimate, rather than the spread of individual observations. These quantities are not interchangeable with a mean and standard deviation. The registry record does not describe the full models used for the secondary least-squares means.

For the per-protocol analysis labeled Analysis #2, the reported least-squares mean difference is 97.9 seconds and the registry reports ANOVA with p = 0.042. The simple recalculation from those posted estimates gives an unadjusted p-value of 0.061 and a confidence interval from -4.38 to 200.2 seconds. This difference illustrates why the analysis method matters; the recalculation is not a substitute for the reported ANOVA.

How should significance and uncertainty be read together?

General statistical explanation: a conventional significance threshold is one possible decision rule, but a p-value alone does not show the range of effect sizes supported by the data. A confidence interval helps communicate that uncertainty. Here, the sponsor’s primary Sign test has no confidence interval reported, while the separate recalculation supplies one. Readers should keep those sources distinct and avoid combining a p-value from one analysis with an interval from another as if they formed a single test.

Finally, the registry lists multiple secondary outcomes and analyses. General statistical explanation: when many hypotheses are tested, the chance of finding at least one apparently notable result by chance can increase. The registry record does not report a multiplicity adjustment or a hierarchy for interpreting these secondary tests. That makes the secondary results more exploratory than a single prespecified primary comparison, unless a fuller analysis plan establishes otherwise.

11. Confidence Intervals and Precision

The primary summary statistics show means of 551.3 seconds for Midodrine HCl and 461.0 seconds for placebo, with standard deviations of 115.6 and 190.7 seconds, respectively. The posted unadjusted recalculation estimates a mean difference of 90.3 seconds. Its 95% confidence interval ranges from 1.062 to 179.5 seconds. The range conveys uncertainty about the estimated difference under the recalculation’s method; it is not an interval reported for the sponsor’s Sign test.

In general, a confidence interval reflects both the estimated effect and its precision. A narrower interval indicates greater precision under the assumptions used to calculate it; a wider interval leaves more uncertainty about the effect’s size. The recalculated interval spans values close to no difference as well as larger positive differences. The lower endpoint is just above zero, but that feature should be interpreted alongside the fact that the recalculated analysis differs from the registry’s reported test.

The sponsor’s reported primary Sign test gives p = 0.146 and no confidence interval is posted for that analysis. Consequently, the registry record does not provide a direct interval-based description of the sponsor analysis’s precision. The unadjusted interval cannot fill that gap, because it is based on a different method and does not account explicitly for the paired crossover structure.

The primary endpoint standard deviations also show substantial variation in observed times, particularly for placebo. General statistical explanation: variation among observations contributes to uncertainty in group comparisons, and accounting for within-participant pairing can alter precision in crossover studies. The registry record does not report enough information to assess the sponsor’s precision calculation or the contribution of the crossover pairing. The reported means and recalculated interval should therefore be read as descriptive and supplementary, not as a full reconstruction of the primary analysis.

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 planning figures are participants per arm, not total events. They are illustrations based on the observed effect, not the trial’s original design calculation. The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. Each scenario uses a stated fraction of the observed effect as the effect to detect. The original trial’s own sample-size assumptions and justification are not reported in the registry record.

The 80% power column gives the illustrated number of participants per arm for a design that would have an 80% chance of detecting the specified effect under those planning assumptions, if that effect were the true one. The 90% power column gives the corresponding illustration for a 90% chance. These are design-planning concepts, not probabilities that the observed result is correct. The figures are not observed power.

The displayed scenarios consider planning for 100%, 75%, and 50% of the observed effect. For the primary comparison, planning for 100% of the observed effect corresponds to 48 participants per arm for 80% power and 65 participants per arm for 90% power. Planning for 75% corresponds to 86 and 114 participants per arm, respectively; planning for 50% corresponds to 192 and 257 participants per arm, respectively.

Smaller effects are harder to distinguish from random variation, so they require more participants under the same assumptions. These calculations use the observed effect as their starting point, which may not represent the effect a future study should expect. They also use a normal approximation and equal allocation, and they do not reproduce the original crossover design assumptions. The registry record does not report the trial’s initial sample-size rationale, so these illustrations should not be read as evidence that the original enrollment was chosen to achieve a particular power.

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 = 90.300; pooled standard deviation σ = 157.721.
2. n = 2 × (1.96 + 0.842)² × 157.721² / 90.300² = 47.9, rounded up to 48 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 <- 90.3                      # observed difference in means
sigma <- 157.721343672947                     # 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(555880)
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 = 48 (80% power), 65 (90% power)
 75% of observed effect: n per arm = 86 (80% power), 114 (90% power)
 50% of observed effect: n per arm = 192 (80% power), 257 (90% power)
power.t.test: 48.9 
Simulated power at n = 48 per arm: 0.799 (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 registry’s primary analysis reports a Sign test, Sign Statistic 3.0, and p = 0.146. The posted summary-statistic recalculation instead compares the treatment means and gives a mean difference of 90.3 seconds, a 95% confidence interval from 1.062 to 179.5 seconds, and an unadjusted p-value of 0.047. These results differ because the recalculation is not the sponsor’s reported test.

The recalculation is a simple, unadjusted comparison based on the posted means and standard deviations. It does not reconstruct the sponsor’s analysis or account explicitly for the within-subject pairing, sequence, or period structure of a crossover trial. The registry record does not provide enough information to determine the exact reasons for the discrepancy or to reproduce the reported Sign test.

Because the sponsor’s own reported analysis and the recalculation differ, the sponsor’s analysis takes precedence. The recalculated result can still help describe the group means and provide a supplementary estimate, but it should not be substituted for the reported primary analysis or used to claim that the sponsor found a statistically significant primary result. The two analyses should remain clearly distinguished whenever their results are discussed.

15. Multiplicity, Missing Data and Analysis Populations

The registry record lists multiple outcomes and analyses, including several measures of symptom timing, symptom-assessment scores, and global-impression ratings. It does not report whether the trial used a prespecified hierarchy of hypotheses, an adjustment for multiple comparisons, or another strategy to control the overall false-positive risk. Without that information, it is not possible to determine whether the secondary p-values were intended to be confirmatory or exploratory.

General statistical explanation: when researchers test many outcomes, the chance of at least one apparently unusual result can rise. Adjustments or a planned testing hierarchy can address this issue, but the record does not describe either. Accordingly, isolated secondary p-values should be interpreted cautiously and should not be given the same weight as a clearly prespecified primary test.

The primary analysis population is described as the Full Analysis Set: randomized subjects who received at least one dose and had at least one tilt-table time-to-syncope measurement. A per-protocol population is used in secondary analyses, and its posted sample counts differ from the Full Analysis Set. The registry record does not report the full per-protocol criteria, the reasons participants were excluded from that population, or how missing endpoint values were handled.

The record also does not report whether missing observations were imputed, whether all available crossover periods were analyzed, or how incomplete treatment sequences were handled. It does not provide enough detail to assess sensitivity analyses for missing data or deviations from the planned treatment sequence. Those omissions matter because missingness and exclusions can affect both the composition of the analysis population and the estimated treatment contrast.

The registry’s primary Sign test is reported, but a complete statistical analysis plan, including details of crossover-period handling and any interim analyses, is not reported in the registry record. These unknowns do not invalidate the posted analysis; they limit the extent to which readers can independently reconstruct or audit it from the registry entry alone.

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 5% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: multiple sclerosis aggravated (7.7%).

The safety record groups participants by treatment sequence. In the Midodrine/Placebo group, 13 participants were at risk for serious adverse events and 1 was affected. In the Placebo/Midodrine group, 11 participants were at risk and 0 were affected. The registry lists “Multiple sclerosis aggravated” as a serious adverse-event term at 7.7%, but the record does not establish which sequence group that term belongs to.

The record also lists other adverse events affecting 3 of 13 participants in the Midodrine/Placebo group and 2 of 11 in the Placebo/Midodrine group. Deaths are not reported in the registry record. These counts describe events recorded for the two sequences; they do not by themselves establish that an event was caused by either treatment. In a crossover study, participants may receive both study treatments, so sequence-level safety counts should not be read as a simple parallel-group comparison of exposure to one treatment alone.

General statistical explanation: adverse-event counts from a small study can be imprecise, and an event count does not estimate comparative risk with precision on its own. The registry record does not provide event timing, exposure-adjusted rates, or enough attribution detail to interpret the listed serious event by treatment period. The figures should therefore be treated as a descriptive account of the posted safety record, not as a complete comparative safety analysis.

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

The primary results address a focused question: how long subjects continued a controlled tilt-table test before reporting near-syncopal symptoms severe enough to request that the table be lowered. The posted means were 551.3 seconds for Midodrine HCl and 461.0 seconds for placebo. These are measurements under a defined laboratory challenge at 1 hour post-dose, not direct measures of symptoms in daily life.

The registry’s reported primary analysis is a Sign test with p = 0.146. The unadjusted recalculation from summary statistics produces a different p-value and a confidence interval, but it is not the same analysis. The sponsor’s reported result takes precedence. The recalculated mean difference and interval can supplement description of the posted means, but should not be used to overturn or reinterpret the reported primary test as if it were the trial’s prespecified method.

The result does not, by itself, establish the size or clinical importance of any difference outside the tilt-table setting. The registry record does not provide a threshold for a clinically meaningful difference in seconds, nor does it connect the endpoint to patient-important outcomes beyond the listed symptom and global-impression measures. It also does not report enough details to reconstruct the crossover model, missing-data approach, or original analysis plan.

The result should not be generalized beyond the studied population and test conditions without supporting evidence. The trial enrolled 24 subjects with moderate to severe neurogenic orthostatic hypotension, and the primary outcome used the defined Full Analysis Set. The posted analysis is one study’s evidence; it is not a complete account of all possible benefits, risks, or outcomes. No medical recommendation follows from the statistical comparison alone.

18. Why This Trial Matters Statistically

This trial illustrates why the analysis method matters as much as the numerical contrast. The posted group means differ, and a simple recalculation from those summaries gives an unadjusted estimate and interval. The registry’s reported primary test, however, is a Sign test with a different p-value. These are not interchangeable summaries of one identical calculation. Keeping the sponsor’s analysis distinct from a supplementary recalculation prevents a descriptive exercise from being mistaken for the trial’s reported inferential result.

The crossover design makes that distinction especially important. General statistical explanation: comparisons in crossover studies can use the relationship between observations from the same participant, while simple comparisons of group summaries may not represent that pairing. Period and sequence can also matter. The registry record identifies the crossover model and treatment sequences but does not describe enough of the analysis to reproduce the primary method.

The trial also shows how endpoint definition shapes interpretation. Time to a sufficiently severe symptom during tilt-table testing is a specific, timed laboratory outcome. It can be summarized as a mean in seconds, but the result remains tied to the test procedure and the symptom threshold. It should not be casually interpreted as a measure of every aspect of orthostatic symptoms or everyday function.

Finally, the registry includes multiple secondary outcomes and analyses without reporting a multiplicity strategy. Their findings may add context, but isolated secondary results need cautious interpretation. Together, these features make the study useful for learning to distinguish endpoint meaning, analysis populations, sponsor-reported inference, summary-statistic recalculation, and uncertainty.

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.

Several limitations are specific to the information available for this trial. The primary outcome was measured during a tilt-table test, with symptoms defined by a confirmed report severe enough to prompt a request to return the table to horizontal. That protocolized endpoint may not capture the full range of symptoms or experiences outside the laboratory. The registry record does not report how observations were handled if no qualifying symptom occurred during the test.

The crossover design creates an important interpretive constraint. Although the registry identifies the design and safety sequences, it does not report the primary model’s handling of within-participant correlation, treatment period, sequence, or possible carryover. The unadjusted recalculation from group summaries does not explicitly account for those features. This is why it should remain secondary to the sponsor’s reported Sign test.

The discrepancy between the recalculated and sponsor-reported primary results limits what can be inferred from the recalculation alone. The registry gives no primary confidence interval for the Sign test and does not provide enough methodological detail to reproduce it. The sponsor-reported analysis takes precedence, but the posted record does not allow independent verification of all its analytical choices.

The registry does not report the original sample-size rationale, detailed missing-data procedures, the full per-protocol definition, or a multiplicity strategy. These omissions limit assessment of precision, population exclusions, and the evidential weight of secondary findings. The sample-size illustrations are based on the observed effect and stated planning assumptions, not the original crossover design. Safety counts are descriptive and the record does not provide event timing or treatment-period attribution for the listed serious-event term.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Study to Assess the Benefit of Midodrine in the Treatment of Patients With Neurogenic Orthostatic Hypotension — NCT00555880.
• Registry record last updated 2021-06-14; status last verified 2021-06.
• Results first posted 2015-05-21.
• 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

NCT00555880 is a completed Phase 4 randomized, quadruple-masked, placebo-controlled crossover study of midodrine hydrochloride in patients with moderate to severe neurogenic orthostatic hypotension. Enrollment was 24. The primary outcome was time to onset of near-syncopal symptoms during tilt-table testing at 1 hour post-dose, measured in seconds in the Full Analysis Set.

The posted means were 551.3 seconds for Midodrine HCl and 461.0 seconds for placebo. The registry’s reported primary Sign test has p = 0.146. An unadjusted recalculation from the posted summary statistics gives a mean difference of 90.3 seconds, with a 95% confidence interval from 1.062 to 179.5 seconds and p = 0.047. Because the results differ, the sponsor’s reported analysis takes precedence.

The registry lists multiple secondary outcomes, but does not report a multiplicity strategy, the original sample-size justification, or complete details of the crossover analysis and missing-data handling. Safety figures are descriptive sequence-level counts, and deaths are not reported in the registry record.