Clinical Efficacy of Midodrine in Symptomatic Orthostatic Hypotension: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Clinical Efficacy of Midodrine in Symptomatic Orthostatic Hypotension (NCT01515865), a randomized phase 4 study. The primary outcome is Percent of Subjects Who Failed to Maintain a Response.

2. Clinical Question

3. Trial Design

This was a Phase 4 randomized-withdrawal study with a double-blind, placebo-controlled, parallel-group design. The registry also describes masking as quadruple. It does not specify which people or roles were included in that masking description, so the masking label should not be expanded beyond what the record states.

The study compared Midodrine HCl with placebo in subjects with symptomatic orthostatic hypotension. Enrollment was 98. The registry lists a start date of 2012-05-23, a primary completion date of 2013-11-11, and a completed status. Those dates describe the registry record; they do not by themselves explain the timing or conduct of each study phase.

The primary endpoint was reported for the randomized portion, with 33 participants in the Midodrine HCl group and 34 in the placebo group. The endpoint was assessed 30 minutes post-dose on Day 16. The Full Analysis Set was defined as all randomized subjects who received at least 1 dose of double-blind investigational product. The registry does not report further detail about allocation procedures, the sequence of the withdrawal design, or the handling of participants who did not contribute to the posted outcome.

The study included open-label and randomized parts in its adverse-event reporting. The registry lists Midodrine HCl open-label groups for Part A and Part B, as well as randomized Midodrine HCl and placebo groups for Part C. These safety populations should be read separately from the primary outcome groups; the record does not establish that their denominators represent the same analysis population or exposure period.

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 the dose and frequency of Midodrine HCl that they had been receiving during their non-study treatment prior to enrolling in this study.

Part A (Open-label)

Reasons for not completing this period:

Part B (Open-label)

Reasons for not completing this period:

Part C (Randomized)

Analysis population for the primary outcome, as defined in the registry: The Full Analysis Set was defined as all randomized subjects who received at least 1 dose of double-blind investigational product.

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 Enrolled Population consisted of all subjects who participated in Part A baseline procedures starting at Day -1.

6. Primary Endpoint

The registry lists the primary outcome as Percent of Subjects Who Failed to Maintain a Response, measured over 30 minutes post-dose on Day 16.

The primary endpoint was the percentage of participants who failed to maintain a response. It was assessed 30 minutes post-dose on Day 16. Failure was defined using two criteria, both of which had to be met. First, the OHSA Item 1 score had to increase by >=4 points compared with baseline. OHSA Item 1 is a dizziness scale from 0, no dizziness, to 10, severe dizziness; a lower score indicates less severe symptoms. Second, the number or severity of syncopal or near-syncopal events within 15 minutes of standing had to increase compared with baseline.

Syncope was defined as loss of consciousness. Near syncope was described as a feeling such as dizziness, lightheadedness, or feeling faint or as though one would black out, which without intervention would lead to loss of consciousness. The combined definition therefore required both a change in the dizziness rating and a change in standing-related events. It was not simply a measure of dizziness alone.

A percentage with an event is useful because it communicates how many participants met the defined failure criteria in each group. The definition makes the outcome clinically interpretable as a composite of reported symptoms and events, but it also means that the endpoint does not isolate either component. The registry record does not report a separate primary result for the OHSA score criterion or the syncopal-event criterion.

7. Results Posted in the Registry

• Midodrine HCl: 30.3% (10/33) versus 44.1% (15/34) on control; risk difference -13.8 percentage points (95% CI -36.7 to 9.1), risk ratio 0.69 (0.36–1.30); unadjusted two-proportion z-test p = 0.242.

8. Statistical Interpretation

9. Statistical Methods Explained

What does a percentage with an event describe?

The endpoint is binary for each participant: the person either met the combined definition of failure to maintain a response or did not. The group percentage expresses the proportion meeting that definition. In general, this gives a direct summary of event frequency, but it does not show the timing or severity of every participant's symptoms, nor does it separate the two criteria required for the event.

The registry reports 30.3% in the Midodrine HCl group and 44.1% in the placebo group. It also reports 10 events among 33 participants and 15 among 34 participants in the recalculation details. These counts and percentages are descriptions of the posted outcome groups. They should be interpreted in light of the stated Full Analysis Set and the endpoint's combined definition.

How is a risk difference interpreted?

A risk difference subtracts the event proportion in the comparator group from the event proportion in the intervention group. A value below zero means the observed proportion is lower in the intervention group; a value above zero means it is higher. The recalculated risk difference is -0.138, with an interval from -0.367 to 0.091. The estimate summarizes the observed contrast, while the interval represents uncertainty around that contrast under the recalculation's assumptions.

In general, a risk difference is expressed on the proportion scale and is often straightforward to relate to event frequencies. It depends, however, on which groups and outcome definition are used. Here, the recalculation is an unadjusted comparison of the posted proportions. The registry's own analysis is separately reported as a Fisher Exact analysis with a “Mean Difference (Final Values)” parameter label; the record does not explain that label further.

What do the p-values tell the reader?

The unadjusted recalculation reports p = 0.242. The sponsor-reported analysis gives p = 0.315. In general, a p-value measures how incompatible the observed data are with a specified null model, under the assumptions of the test. It does not measure the probability that the null hypothesis is true, the probability that the result will replicate, or the clinical importance of an estimate.

The two p-values arise from separately described analyses and should not be blended. The registry identifies Fisher Exact as the sponsor's method. The recalculation is an unadjusted comparison of proportions. The registry does not report enough detail about the sponsor analysis to establish how the stated parameter label was operationalized for this outcome.

Why can intervals be more informative than a single test result?

In general, a confidence interval gives a range of effect estimates compatible with the data and the method used to construct it. Its width communicates precision: a wider interval leaves more uncertainty about the magnitude and potentially the direction of the effect. The recalculated risk-difference interval extends from -0.367 to 0.091. The sponsor-reported 95% confidence interval extends from -37.6 to 9.8 on its stated scale. Both ranges include zero, but the estimates are reported on differently labelled scales and should be interpreted as separate results.

Interval interpretation also depends on the analysis population, outcome definition, and statistical method. An interval does not account automatically for unreported sources of bias, missing data, or multiple testing. The registry record does not report the original statistical analysis plan or details of missing-data handling.

What does Fisher's exact method generally do?

In general, Fisher's exact test evaluates association in a two-by-two table of counts, using an exact probability calculation rather than relying on a large-sample approximation. It is commonly used for categorical outcomes. The registry reports Fisher Exact as the analysis method, but also gives the parameter label “Mean Difference (Final Values).” Because the record does not provide further specifications, the method name and reported estimate should be quoted as recorded rather than used to infer unreported analysis details.

The recalculated comparison instead summarizes the binary outcome as a risk difference from the posted event proportions. This distinction matters: a test method, an effect estimate, and its interval are related components of an analysis, but they are not interchangeable descriptions. Reading the estimate together with its interval preserves information about direction and precision that a p-value alone does not convey.

What is the role of the analysis population?

The Full Analysis Set is defined in the registry as all randomized subjects who received at least 1 dose of double-blind investigational product. The primary outcome groups contain 33 and 34 participants. In general, stating an analysis population helps readers understand which randomized participants contribute to a result. The registry record does not report whether any other analysis populations were used, how participants without endpoint data were handled, or whether all randomized participants contributed to this outcome.

These methods describe the reported comparison and general statistical concepts. They do not establish that the original study design assumptions, analysis plan, or data-handling procedures followed any particular approach beyond what the registry record states.

10. Confidence Intervals and Precision

The recalculated risk difference is -0.138, with an interval from -0.367 to 0.091. The interval crosses zero, encompassing a lower event proportion with Midodrine HCl, no difference, and a higher event proportion. Its breadth indicates that the point estimate should not be treated as a precise estimate of the size or direction of the group contrast.

The registry's reported analysis gives an estimate of -13.8 and a 95% confidence interval from -37.6 to 9.8. The registry labels this analysis “Mean Difference (Final Values)” and identifies Fisher Exact as the method. Because the registry does not further explain the parameter scale, this interval should be read using its stated label and kept distinct from the recalculated risk-difference interval.

In general, a confidence interval describes uncertainty around an estimate under the chosen method and assumptions. It is not a range containing the true value with certainty, and it does not include every source of uncertainty, such as possible bias or unreported data-handling decisions. A wide interval can remain compatible with substantively different interpretations. Here, both reported intervals include zero, and the recalculated interval is broad relative to its point estimate.

The group sizes for the primary result are 33 and 34. Those modest group counts provide limited information for estimating an uncommon or variable binary outcome precisely. No further precision should be inferred from the p-values alone. The registry record does not report a prespecified precision target or a confidence-interval planning rationale.

11. 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 event counts. They are illustrations calculated from the observed effect, not the trial's own design justification. The listed assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation; each scenario uses the stated fraction of the observed effect as the effect to detect. The original trial's sample-size assumptions are not reported in the registry record.

For planning for 100% of the observed effect, the figures are 191 participants per arm for 80% power and 256 participants per arm for 90% power. For planning for 75% of the observed effect, they are 347 participants per arm for 80% power and 464 participants per arm for 90% power. For planning for 50% of the observed effect, they are 793 participants per arm for 80% power and 1,061 participants per arm for 90% power.

In plain terms, the 80% power column gives the estimated number of participants per arm for a future study to have an 80% chance of detecting the specified effect under the planning assumptions, if that effect is present. The 90% column applies the same idea with a higher chance of detection, which requires more participants in these illustrations. Smaller effects need more participants to detect because they are harder to distinguish from random variation.

These are planning illustrations, not observed power. They do not establish the power of the completed trial, and they should not be interpreted as a justification for its enrollment.

12. 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, p₀ and p₁ are the control and treatment proportions, and p̄ is their average.

Worked calculation for this trial

1. Control proportion p₀ = 0.441; treatment proportion p₁ = 0.303; average p̄ = 0.372.
2. First term: z_1−α/2 × √[2p̄(1−p̄)] = 1.96 × 0.6836 = 1.3398.
3. Second term: z_1−β × √[p₀(1−p₀) + p₁(1−p₁)] = 0.842 × 0.6766 = 0.5694.
4. n = (1.3398 + 0.5694)² / (-0.1381)² = 191.0, rounded up to 191 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
p0 <- 0.441176470588235                          # control proportion
p1 <- 0.303030303030303                          # treatment proportion
n_per_arm <- function(power, frac = 1) {
  q1 <- p0 + (p1 - p0) * frac               # smaller effect = fraction of the observed difference
  pbar <- (p0 + q1) / 2
  z_b <- qnorm(power)
  ceiling(round((z_a * sqrt(2 * pbar * (1 - pbar)) + z_b * sqrt(p0 * (1 - p0) + q1 * (1 - q1)))^2 / (q1 - p0)^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 (unrounded n per arm)
cat("power.prop.test:", round(power.prop.test(p1 = p0, p2 = p1, power = 0.80)$n, 1), "\n")

# Simulation: how often does the z-test reject at the 80%-power sample size?
set.seed(1515865)
n    <- n_per_arm(0.80)
reps <- 20000
x0 <- rbinom(reps, n, p0); x1 <- rbinom(reps, n, p1)
ph <- (x0 + x1) / (2 * n)
z  <- ((x1 - x0) / n) / sqrt(ph * (1 - ph) * 2 / n)
cat(sprintf("Simulated power at n = %s per arm: %.3f (%d replicates)\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE), reps))

Output from running the code

100% of observed effect: n per arm = 191 (80% power), 256 (90% power)
 75% of observed effect: n per arm = 347 (80% power), 464 (90% power)
 50% of observed effect: n per arm = 793 (80% power), 1,061 (90% power)
power.prop.test: 191 
Simulated power at n = 191 per arm: 0.803 (20000 replicates)

The simulation draws many pairs of event counts at the planned sample size and counts how often the two-proportion z-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.

13. Analyses Reported by the Sponsor

The registry reports the sponsor's analysis as Fisher Exact, with the parameter labelled “Mean Difference (Final Values).” The reported estimate is -13.8, its 95% confidence interval runs from -37.6 to 9.8, and p = 0.315. These values describe the analysis as recorded, even though the parameter label is not explained further in the registry entry.

The separate recalculation uses the posted binary event proportions and reports an unadjusted risk difference of -0.138, an interval from -0.367 to 0.091, and p = 0.242. This recalculation is a straightforward comparison of the posted summary statistics; it is not a replacement for the sponsor's analysis or a reconstruction of unreported analysis details. The registry marks no discrepancy between the posted results and the recalculation.

The estimate labels and scales differ, so the values should not be compared as though they were the same statistic. The sponsor's reported estimate, interval, and p-value are the registry's own analysis; the risk difference and associated statistics are supplementary unadjusted calculations. Both intervals include zero, but that shared feature does not make the two analyses identical.

14. Multiplicity, Missing Data and Analysis Populations

The registry lists one primary outcome measure and one reported analysis, and it reports no secondary outcomes. It does not report a multiplicity adjustment or a plan for controlling error rates across multiple outcomes or analyses. With only the posted primary result available, the record does not permit assessment of whether additional planned comparisons were conducted but not reported. No multiplicity procedure should be assumed.

The registry defines the Full Analysis Set as all randomized subjects who received at least 1 dose of double-blind investigational product. It does not report the number of randomized participants who were excluded from that set, whether all participants in the analysis population had an observed Day 16 outcome, or how missing endpoint data were handled. The posted group counts are 33 for Midodrine HCl and 34 for placebo, but the record does not explain the relationship between those counts and all enrolled participants.

The registry record does not report whether an intention-to-treat analysis was conducted, whether sensitivity analyses addressed missing observations, or whether any imputation method was used. These omissions matter because the analyzed set and treatment of missing outcomes can affect the interpretation of a group comparison, particularly when the outcome is assessed at a defined follow-up time.

The original statistical analysis plan, any interim analyses, and the rationale for selecting the primary endpoint are not reported in the registry record. The posted data therefore support interpretation of the reported endpoint and analyses, but do not establish the full analysis strategy or whether other planned analyses were undertaken.

15. 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 non-serious adverse event terms

The serious adverse event entries report 0 affected participants in each listed group: Midodrine HCl open-label Part A, Midodrine HCl open-label Part B, Midodrine HCl randomized Part C, and placebo randomized Part C. The corresponding numbers at risk are 98, 71, 33, and 34. These are the registry's reported serious adverse event counts for those groups.

The record also reports other adverse events affecting 5 participants in open-label Part A and 2 in open-label Part B, with 0 in each randomized Part C group. Those figures are distinct from the serious adverse event counts and should not be combined with them. The registry lists no serious adverse event terms.

Death counts are not reported in the registry record. The adverse-event groups span open-label and randomized parts, and the registry does not provide additional detail about exposure duration or whether all groups are directly comparable. A count of zero in a listed group does not establish absence of risk, particularly when the group size and period of observation are limited. These entries are descriptive safety reporting, not a comparative safety analysis.

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

The posted outcome shows that 30.3% of participants in the Midodrine HCl group and 44.1% in the placebo group met the defined failure-to-maintain-response criteria at the Day 16 assessment. The unadjusted recalculated risk difference is -0.138, with an interval from -0.367 to 0.091 and p = 0.242. The point estimate is in the direction of fewer observed failures in the midodrine group, but the interval includes zero and allows for differences in either direction.

The sponsor-reported analysis gives an estimate of -13.8, a 95% confidence interval from -37.6 to 9.8, and p = 0.315. Its parameter label is “Mean Difference (Final Values),” while the primary outcome is described as a percentage. The registry does not explain the scale further, so the sponsor result should be retained in its recorded form rather than assigned a more specific interpretation.

The result does not establish that one group had a reliably different outcome from the other. Nor does it show that the groups were equivalent: a wide interval including zero can reflect limited precision rather than evidence of no meaningful difference. In general, establishing equivalence would require a prespecified equivalence margin and an analysis designed for that question; such details are not reported in the registry record.

The endpoint is a composite requiring a change in both a dizziness score and standing-related syncopal or near-syncopal events. The outcome therefore cannot identify which component contributed to each event, and the registry does not report separate primary results for those components. The result applies to the recorded groups, population definition, and Day 16 assessment; it does not establish effects at other times or on outcomes not reported.

The data describe a small randomized comparison with substantial uncertainty in the estimated contrast. They should be read as a statistical account of the posted results, not as medical advice or a general conclusion about treatment.

17. Why This Trial Matters Statistically

This trial illustrates why a difference in observed percentages and a clear conclusion about the size of a group effect are not the same thing. The Midodrine HCl group had a lower posted failure percentage than the placebo group, but the recalculated interval ranges across zero and extends in both directions. Looking at the estimate together with its uncertainty avoids treating the observed contrast as exact.

It also shows the value of defining a binary endpoint carefully. Failure to maintain a response required both a specified rise in the OHSA Item 1 dizziness score and an increase in the number or severity of syncopal or near-syncopal events after standing. This captures more than one aspect of symptoms in a single event definition, but it makes the result harder to attribute to either component separately.

The registry's reported analysis and the supplementary unadjusted recalculation demonstrate why method and parameter labels matter. The sponsor analysis is identified as Fisher Exact, while its parameter is labelled “Mean Difference (Final Values).” The recalculation expresses the contrast as a risk difference from the posted proportions. Readers should keep those analyses distinct rather than compare their estimates as if they were on an identical scale.

The planning illustrations also clarify that a trial's observed sample size and a future-study planning estimate answer different questions. The illustrations show increasing participant requirements for smaller effects and higher target power, under stated assumptions. They do not tell the reader what assumptions guided the original trial, which are not reported in the registry record.

Together, these points emphasize interpretation of effect estimates, precision, endpoint construction, and analysis reporting rather than reliance on a single p-value.

18. 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.
• Participant counts were reconstructed from posted percentages and arm sizes, so small rounding differences are possible.

The primary outcome groups are relatively small, with 33 participants receiving Midodrine HCl and 34 receiving placebo. The resulting recalculated interval is broad and includes differences in either direction. The point estimate therefore has limited precision, and the data do not tightly locate the size of the group contrast.

The registry outcome definition combines two criteria: change in OHSA Item 1 and change in the number or severity of standing-related syncopal or near-syncopal events. No separate primary results for those components are reported. The combined outcome cannot show whether one criterion or both drove the observed group percentages.

The sponsor analysis is described with a potentially unclear parameter label, “Mean Difference (Final Values),” alongside a Fisher Exact method for a percentage outcome. Further methodological detail is not reported in the registry record. The recalculated risk difference is thus useful as a transparent unadjusted description, but it cannot resolve the ambiguity in the sponsor's analysis description.

The registry does not report the original sample-size justification, complete statistical analysis plan, missing-data procedures, interim analyses, or multiplicity strategy. It also does not explain the relationship between the enrollment of 98 and the smaller primary outcome group counts. These omissions limit assessment of the study's planned precision, analysis population, and potential influence of unavailable outcomes.

Only one outcome measure and one analysis are posted, with no secondary outcomes reported. The results consequently offer limited context for understanding other dimensions of the study or whether the primary outcome is consistent with other measures. The safety entries include different open-label and randomized groups, and the registry does not provide details sufficient to compare exposure or observation periods across them.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Clinical Efficacy of Midodrine in Symptomatic Orthostatic Hypotension — NCT01515865.
• Registry record last updated 2021-06-09; status last verified 2021-05.
• Results first posted 2014-10-22.
• 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.

22. Record Summary

NCT01515865 is a completed Phase 4 randomized-withdrawal, double-blind, placebo-controlled, parallel-group study of Midodrine HCl in symptomatic orthostatic hypotension. The registry describes masking as quadruple and reports enrollment of 98.

The primary outcome was the percentage of participants who failed to maintain a response, assessed 30 minutes post-dose on Day 16. The posted percentages were 30.3% for Midodrine HCl and 44.1% for placebo. The unadjusted recalculated risk difference was -0.138, with an interval from -0.367 to 0.091 and p = 0.242. The sponsor-reported analysis gave an estimate of -13.8, a 95% confidence interval from -37.6 to 9.8, and p = 0.315.

The primary outcome groups included 33 and 34 participants. Serious adverse events were reported for 0 participants in each listed group. The registry does not report the original sample-size rationale, missing-data procedures, or a fuller statistical analysis plan.