Conservative Treatment of Postprostatectomy Incontinence: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Conservative Treatment of Postprostatectomy Incontinence (NCT00212264), a randomized na study. The primary outcome is Percent Change in Incontinence Episodes on Bladder Diary.

2. Clinical Question

The primary outcome was the percent change in incontinence episodes recorded in bladder diaries. Its definition compares episodes at baseline with episodes at 2 months, scaled relative to the baseline count. A positive change therefore represents fewer recorded episodes at follow-up than at baseline.

The registry’s brief description also frames the study as assessing quality-of-life impact and durability of non-surgical therapies. However, only the primary endpoint is described in the posted results used for this analysis; quality-of-life and longer-term results are not reported in the registry record. This distinction matters: the available primary outcome addresses diary-recorded episodes at the stated time point, not every purpose mentioned in the study description.

3. Trial Design

This was a prospective, controlled, randomized trial with parallel groups and no masking. The registry lists 208 participants enrolled. The outcome summaries report 70 participants in the behavioral therapy arm, 70 in behavioral therapy plus technologies, and 68 in the no-treatment control. The registry classifies the study phase as not applicable.

The behavioral program included pelvic floor muscle training and bladder control strategies. The brief description further lists self-monitoring with bladder diaries, regular office visits, bladder control techniques, and fluid management. The technology arm received the behavioral program together with home pelvic floor electrical stimulation and biofeedback. The comparator is described as no treatment control. Because masking is listed as none and the control received no treatment, participants and study personnel could know the assigned group; details about who recorded or assessed outcomes are not reported in the registry record.

The primary endpoint was assessed at 2 months. The intervention is described as an 8-week program, so the posted endpoint corresponds to the end of that stated program period. The registry lists the study as completed, with a start date of 2003-08 and a primary completion date of 2008-09. Further details on recruitment, adherence, allocation concealment, protocol deviations, and follow-up after the primary endpoint are not reported in the registry record.

The registry lists two outcome measures and two analyses, but only the primary endpoint is detailed in the posted results. The trial’s planned sample-size assumptions, original statistical design calculations, analysis populations, and prespecified handling of missing data are not reported in the registry record. The total enrollment should therefore not be treated as evidence about the assumptions used to choose the trial’s size.

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.

Overall Study

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 Percent Change in Incontinence Episodes on Bladder Diary, measured over 2 months.

The primary endpoint is the percent change in incontinence episodes per week, assessed from bladder diaries at 2 months. The registry defines it by subtracting the 2-month episode count from the baseline count, dividing by the baseline count, and multiplying by 100%. In this definition, a positive value indicates that fewer episodes were recorded at 2 months than at baseline.

This endpoint puts change in the context of each participant’s baseline episode count, rather than reporting only the raw change in episodes. It is relevant to the stated study question because the trial aimed to assess non-surgical approaches to persistent incontinence, and diary-recorded episodes provide a direct measure of the symptom frequency being targeted. A diary can also capture episodes outside a clinic visit, although the diary completion procedures and adherence are not reported in the registry record.

The posted arm summaries are means with 95% confidence intervals. Behavioral therapy had a mean change of 55.0% (95% CI 44.0 to 66.0), behavioral therapy plus technologies had 51.0% (95% CI 37.0 to 65.0), and the no-treatment control had 24.0% (95% CI 10.0 to 39.0). These are group summaries at the stated endpoint; they do not describe every participant’s experience or establish what happened after 2 months. The registry record does not post a separate quality-of-life result or a longer-term durability result among the outcomes detailed.

7. Results Posted in the Registry

• Behavioral Therapy: 55.00 versus 24.00 (% change in episodes per week) on control; rate ratio 2.29 (95% CI 1.13–4.66, derived from the posted confidence limits); p ≈ 0.022.
• Behavioral Therapy Plus Technologies: 51.00 versus 24.00 (% change in episodes per week) on control; rate ratio 2.12 (95% CI 1.02–4.44, derived from the posted confidence limits); p ≈ 0.045.

8. Statistical Interpretation

9. Statistical Methods Explained

The registry reports group means and 95% confidence intervals for the primary endpoint. A mean is a summary of the group’s average percent change in weekly episodes. The confidence interval describes the statistical uncertainty around that estimated mean under the method used to calculate it. It is not a range containing every participant’s result, and it is not a statement that there is a particular probability that the fixed true mean lies inside the calculated interval.

The reported primary endpoint is a percent change, not a count of episodes. The calculation begins with the baseline and 2-month diary counts and expresses their change relative to baseline. This makes the result interpretable as a proportional change in the recorded episode count. Since the denominator is the baseline count, the same absolute change can correspond to different percentage changes for participants with different baseline counts. The registry does not report the distribution of baseline counts or the participant-level data needed to assess this feature further.

The sponsor’s reported analysis is ANOVA across the three groups, with p = .001. In general, ANOVA is a method for assessing whether group means differ overall. An omnibus test does not identify a particular pair of groups as different. The registry does not report the ANOVA model details, the exact estimand, adjustments for covariates, or follow-up pairwise tests. Those details are not reported in the registry record, so the reported p-value should be interpreted as the posted overall result rather than as a complete account of all comparisons.

The recalculations use the posted arm summaries to form active-versus-control rate ratios. A rate ratio compares modeled rates, with one representing equal rates under the comparison. The recalculated estimates are 2.292 for behavioral therapy versus control and 2.125 for behavioral therapy plus technologies versus control. Their 95% confidence intervals are 1.127 to 4.661 and 1.017 to 4.438, respectively. The associated unadjusted p-values are 0.022 and 0.045. These are simple, unadjusted recalculations rather than reported sponsor estimates; because the discrepancy indicator is true, the sponsor’s own analysis takes precedence.

In general, rate-based methods are designed for outcomes expressed relative to exposure or time. The calculation treats the posted summary information in a rate framework, using the stated outcome time frame as exposure. A Poisson model is a common starting point for count rates. It assumes a relationship between the count’s mean and variance that may be too restrictive when participants vary more than the model allows; this is called over-dispersion. In general, over-dispersion can make standard errors too small if it is ignored, which can make confidence intervals too narrow and p-values too small. The registry does not report a diagnostic for over-dispersion, a model fit, or an alternative variance adjustment. The recalculation therefore should not be treated as a replacement for a fully specified participant-level analysis.

The mean percent-change summaries and the recalculated rate ratios arise from different representations of the outcome. The first reports average percentage change within each group. The second models rate information and contrasts each active arm with control. Their numerical values cannot be directly subtracted or interpreted as the same type of effect. In general, the statistical scale should match the question: a mean difference concerns differences in average outcomes, while a ratio compares relative rates. The record does not report sponsor-reported pairwise rate ratios for these arms.

The reported confidence intervals for the arm means are 44.0 to 66.0 for behavioral therapy, 37.0 to 65.0 for behavioral therapy plus technologies, and 10.0 to 39.0 for control. Overlap between separate group confidence intervals is not itself a formal test of the between-group difference. A direct contrast and its uncertainty are needed for that question. The sponsor reports an overall ANOVA p-value, while the pairwise rate ratios and their p-values are recalculations with no adjustment reported for multiple comparisons.

Statistical significance and clinical importance are not interchangeable concepts. A p-value describes how compatible the observed data are with a specified null model, subject to the analysis assumptions. It does not measure the size or practical importance of a difference. The posted endpoint estimates describe the magnitude of the group-level changes, but the registry does not report a threshold for a clinically important change. The record also does not report a prespecified analysis plan or enough detail to determine whether the reported analyses followed such a plan.

10. Confidence Intervals and Precision

The 95% confidence intervals for the mean percent change are 44.0 to 66.0 for behavioral therapy, 37.0 to 65.0 for behavioral therapy plus technologies, and 10.0 to 39.0 for the no-treatment control. These intervals indicate the precision of the estimated group means under the calculation used. The intervals are not participant-level ranges, and they do not show how much individuals varied around their group mean.

The two active-arm intervals are relatively broad in relation to their point estimates, as is the control interval. This means the posted summaries leave uncertainty around the exact mean change in each group. The registry does not report standard deviations or individual-level data in this outcome summary, so the amount and pattern of within-arm variation cannot be examined from these values alone.

The recalculated rate-ratio intervals are 1.127 to 4.661 for behavioral therapy versus control and 1.017 to 4.438 for behavioral therapy plus technologies versus control. They span a range of ratio values, so the recalculated point estimates should not be treated as exact. Both intervals exclude one, but they are recalculated, unadjusted contrasts, and the sponsor’s reported ANOVA is the analysis that takes precedence where there is a discrepancy.

In general, a confidence interval combines an estimate with information about its uncertainty. Wider intervals indicate less precision, while narrower intervals indicate more precision under the same modeling assumptions. Precision depends on factors such as the amount of information and variability in the data, but the registry does not provide enough detail to identify the contribution of each factor in this trial. The available intervals concern the 2-month endpoint and do not quantify uncertainty about longer-term durability or quality-of-life outcomes.

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 sample-size figures are planning illustrations based on the observed effect, not the trial’s original design calculations. The stated assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation; each illustration targets the stated fraction of the observed effect. These figures are participants per arm, not total participants or total events. The trial’s own original sample-size assumptions are not reported in the registry record.

For the comparison with behavioral therapy, planning for 100% of the observed effect gives 5 participants per arm for 80% power and 6 participants per arm for 90% power. Planning for 75% of the observed effect gives 8 participants per arm for 80% power and 11 participants per arm for 90% power. Planning for 50% of the observed effect gives 19 participants per arm for 80% power and 26 participants per arm for 90% power.

For behavioral therapy plus technologies, planning for 100% of the observed effect gives 6 participants per arm for 80% power and 7 participants per arm for 90% power. Planning for 75% of the observed effect gives 10 participants per arm for 80% power and 13 participants per arm for 90% power. Planning for 50% of the observed effect gives 24 participants per arm for 80% power and 32 participants per arm for 90% power.

In general, 80% power means that a study planned under the stated assumptions would have an 80% chance of detecting the specified effect if that effect were the true one; the 90% column uses a higher target chance under those assumptions. Smaller effects need more participants to detect reliably, which is why the illustrations increase as the target fraction of the observed effect decreases. This is not observed power: the figures are planning illustrations and do not describe the trial’s probability of having detected an effect after the results were known.

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, λ₀ and λ₁ are event rates per patient-year, and T is follow-up per participant in years. This assumes Poisson counts and equal follow-up.

Worked calculation for this trial

1. Control rate λ₀ = 24.0000; treatment rate λ₁ = 55.0000 events per patient-year; follow-up T = 0.17 years.
2. n = (1.96 + 0.842)² × (1/24.0000 + 1/55.0000) / (0.17 × [ln(2.292)]²) = 4.1, rounded up to 5 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
lambda0 <- 24                      # control rate, events per patient-year
lambda1 <- 55                      # treatment rate
tt      <- 0.166666666666667                       # follow-up per participant, years
n_per_arm <- function(power, frac = 1) {
  l1 <- lambda0 * (lambda1 / lambda0)^frac   # smaller effect = fraction of the observed log rate ratio
  ceiling(round((z_a + qnorm(power))^2 * (1 / lambda0 + 1 / l1) / (tt * log(l1 / lambda0)^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 = ",")))

# Simulation 1: Poisson counts. Simulation 2: over-dispersed counts (variance = 1.5 x mean), analysed with the matching variance.
set.seed(212264)
n    <- n_per_arm(0.80)
reps <- 20000
m0 <- lambda0 * n * tt; m1 <- lambda1 * n * tt
x0 <- rpois(reps, m0); x1 <- rpois(reps, m1)
z  <- log(x1 / x0) / sqrt(1 / x0 + 1 / x1)
cat(sprintf("Simulated power, Poisson counts, n = %s per arm: %.3f\n", format(n, big.mark = ","), mean(abs(z) > z_a, na.rm = TRUE)))
phi <- 1.5
y0 <- rnbinom(reps, mu = m0, size = m0 / (phi - 1)); y1 <- rnbinom(reps, mu = m1, size = m1 / (phi - 1))
z2 <- log(y1 / y0) / sqrt(phi * (1 / y0 + 1 / y1))
cat(sprintf("Simulated power, over-dispersed counts (phi = 1.5), same n: %.3f\n", mean(abs(z2) > z_a, na.rm = TRUE)))

Output from running the code

100% of observed effect: n per arm = 5 (80% power), 6 (90% power)
 75% of observed effect: n per arm = 8 (80% power), 11 (90% power)
 50% of observed effect: n per arm = 19 (80% power), 26 (90% power)
Simulated power, Poisson counts, n = 5 per arm: 0.898
Simulated power, over-dispersed counts (phi = 1.5), same n: 0.744

The first simulation draws Poisson counts and should land close to the target power. The second allows extra variability (variance 1.5 times the mean, a purely illustrative value), which lowers the power at the same sample size, so rate trials usually need more participants than the Poisson formula suggests.

13. Analyses Reported by the Sponsor

The sponsor-reported result is an ANOVA across the three groups, with p = .001. The registry does not provide an associated estimate, confidence interval, degrees of freedom, model details, or pairwise results for that analysis. Its p-value is therefore best read as the reported overall test, not as a quantified contrast between each active arm and control.

The rate ratios and their confidence intervals in the comparison summaries are simple, unadjusted recalculations from posted summary statistics. They are not sponsor-reported estimates. For behavioral therapy versus control, the recalculated ratio is 2.292 (95% CI 1.127 to 4.661; unadjusted p = 0.022); for behavioral therapy plus technologies versus control, it is 2.125 (95% CI 1.017 to 4.438; unadjusted p = 0.045). The registry marks a discrepancy between the sponsor analysis and these recalculations. Where they differ, the sponsor’s own analysis takes precedence.

The results should not be collapsed into one interchangeable test. The sponsor’s omnibus ANOVA and the recalculated pairwise rate-ratio analyses use different statistical summaries and address different contrasts. The registry does not report enough detail to reconcile the discrepancy or determine whether the sponsor’s model incorporated additional information. The recalculations provide context from the posted summaries, not a correction to or substitute for the reported sponsor analysis.

14. Multiplicity, Missing Data and Analysis Populations

The registry reports an overall ANOVA across three groups and the results summaries include two active-versus-control recalculations. The sponsor’s reported p-value is .001. The recalculated p-values are unadjusted: 0.022 for behavioral therapy versus control and 0.045 for behavioral therapy plus technologies versus control. The registry does not report a multiplicity adjustment for the recalculated contrasts or a prespecified hierarchy for testing outcomes. In general, when multiple hypotheses are tested, the chance of at least one false-positive result can increase unless the analysis plan addresses multiplicity. The record does not establish whether or how multiplicity was handled in the sponsor’s analysis.

The registry lists two outcome measures and two analyses, but no secondary outcomes are posted in the results. It does not report whether other outcomes were collected, whether they were prespecified, or why any results are absent. Quality of life and durability are mentioned in the study description, but corresponding results are not reported in the registry record.

Missing-data methods and analysis populations are also not reported in the registry record. There is no posted account of the number of participants with complete diaries at each time point, how missing diary entries were handled, whether participants were analyzed according to random assignment, or whether any per-protocol or other populations were used. These omissions limit assessment of possible bias from incomplete outcome measurement or departures from the assigned intervention.

Randomization can support fair comparisons when allocation and follow-up are handled appropriately, but the registry record does not report allocation concealment, adherence, crossover, exclusions after randomization, or protocol deviations. No adjustment variables or model diagnostics are reported. Consequently, the posted summaries support a description of the stated outcomes and analyses, but they do not allow a full audit of the trial’s analysis choices or robustness.

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 0% reporting threshold.

Most frequent non-serious adverse event terms

The serious adverse event summaries list 70 participants at risk in behavioral therapy, 70 in behavioral therapy plus technologies, and 68 in the no-treatment control. The posted number with a serious adverse event is 0 in each group. No serious adverse event terms are listed. These figures describe the recorded serious adverse events in the registry results; they do not establish that no other events occurred outside the categories or reporting period represented.

For other adverse events, the summaries list 0 of 70 in behavioral therapy, 2 of 70 in behavioral therapy plus technologies, and 0 of 68 in the control. The registry does not give event terms for these two entries in the information. It also does not report whether events were judged related to the intervention, their severity, timing, or whether participants experienced more than one event.

Deaths are not reported in the registry record. The adverse-event summaries are limited to the posted group counts and should not be interpreted as a complete account of all possible harms or as evidence that risks are absent. The available event counts are also not a substitute for a detailed safety analysis.

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

The registry reports mean reductions in diary-recorded weekly incontinence episodes, expressed as percent change from baseline to 2 months, in all three groups. The mean changes were 55.0% with behavioral therapy, 51.0% with behavioral therapy plus technologies, and 24.0% in the no-treatment control. The sponsor’s overall ANOVA is reported with p = .001. These are the results posted for the primary endpoint at the stated time point.

The arm-level means alone do not establish the size or precision of a treatment contrast. The registry’s reported analysis is an overall test, and it does not post pairwise sponsor estimates for each active arm versus control. Separate rate-ratio comparisons are recalculations from the posted summaries; they are unadjusted and should not supersede the sponsor’s own analysis, particularly given the recorded discrepancy.

These results do not show whether any changes persisted beyond 2 months. Although the study description includes durability and quality of life among its aims, results for those outcomes are not reported in the registry record. The results also do not establish how consistently participants completed the behavioral program or diaries, nor do they give individual-level responses or a threshold for a clinically important change.

The randomized design is relevant to comparing assigned groups, but the registry does not report enough detail about analysis populations, missing data, adherence, or allocation procedures to assess all potential sources of bias. The absence of reported serious adverse events in the posted summaries should not be interpreted as proof that there was no risk. Overall, the evidence described is limited to the registered group summaries and analysis for the short-term diary endpoint, together with the stated adverse-event counts.

17. Why This Trial Matters Statistically

This trial illustrates why the scale of an outcome and the scale of an analysis need to be kept distinct. The primary endpoint is a mean percent change in weekly diary episodes, while the recalculated pairwise results are rate ratios. Both can describe aspects of the posted data, but they answer different statistical questions and their estimates cannot be directly compared as though they were the same quantity.

It also demonstrates the difference between an omnibus test and specific contrasts. The sponsor reports ANOVA across three groups with p = .001. That overall result does not, on its own, give the size or uncertainty of each active-arm comparison with control. Pairwise recalculations may appear to address that question, but they are not the sponsor’s estimates and are explicitly unadjusted. The recorded discrepancy makes the distinction particularly important: interpretation should give priority to the sponsor’s own analysis while treating recalculations as secondary context.

Confidence intervals add information that a p-value alone cannot convey. The arm means and recalculated ratios have intervals showing uncertainty around their estimates, while the registry lacks detail needed to evaluate several assumptions behind those intervals. The record also does not report missing-data methods, analysis populations, or multiplicity handling, all of which can affect how robustly a result answers a research question.

Finally, a stated study aim is not the same as a posted result. Quality of life and durability appear in the study description, but the results detailed in the registry concern the primary diary outcome at 2 months. A careful reading keeps the conclusions tied to the outcome, time point, and statistical analysis actually reported.

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.
• Rate comparisons use a Poisson approximation unless the sponsor posted confidence limits; real event counts are often over-dispersed.

The registry record gives limited detail about how randomization was implemented. Allocation is listed as randomized, but the method of sequence generation and allocation concealment are not reported in the registry record. Masking is listed as none, and the comparator is no treatment, so expectations and awareness of group assignment may have influenced participant-reported diary outcomes. The record does not state who collected or reviewed the diaries.

The endpoint relies on bladder diaries, but diary completion, adherence, missing entries, and the handling of incomplete diaries are not reported in the registry record. The baseline distribution of episode counts and participant-level results are also unavailable in the posted summaries. Without those details, it is not possible to assess individual variation, the influence of baseline values on percent change, or the potential impact of missing outcome data.

The results emphasize a 2-month endpoint. Although the study description names durability and quality of life, corresponding results are not reported in the registry record. The available results therefore cannot address longer-term persistence or the other stated aims. The registry also does not report the protocol’s original sample-size assumptions, prespecified analysis plan, analysis populations, adherence, or protocol deviations.

The sponsor’s reported ANOVA is not accompanied by model details or a pairwise breakdown. The recalculated pairwise rate ratios are unadjusted, and the record flags a discrepancy; the sponsor’s own analysis takes precedence. The registry does not explain the discrepancy or report whether multiplicity was handled. The adverse-event information is similarly limited: the posted counts do not include event descriptions for the two other events, attribution, timing, or details about deaths, which are not reported in the registry record.

19. Related Tutorials

20. Related Statistical Calculators

21. Sources

• ClinicalTrials.gov: Conservative Treatment of Postprostatectomy Incontinence — NCT00212264.
• Registry record last updated 2016-04-11; status last verified 2016-03.
• Results first posted 2016-04-11.
• 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

NCT00212264, titled “Conservative Treatment of Postprostatectomy Incontinence,” is listed as a completed randomized, parallel-group trial with no masking and 208 participants enrolled. It compared behavioral therapy, behavioral therapy plus biofeedback and home pelvic floor electrical stimulation, and a no-treatment control. The registry describes an 8-week behavioral program and a primary endpoint of percent change in weekly incontinence episodes at 2 months.

The posted mean changes were 55.0% for behavioral therapy, 51.0% for behavioral therapy plus technologies, and 24.0% for control. The sponsor reports an overall ANOVA p-value of .001. Unadjusted rate-ratio recalculations are also available, but a discrepancy is recorded and the sponsor’s analysis takes precedence. Serious adverse events are listed as 0 in each group; other adverse events are listed as 0, 2, and 0, respectively. Further details on secondary outcomes, longer-term results, missing data, and analysis populations are not reported in the registry record.