Dulcolax vs Placebo in Functional Constipation: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Dulcolax vs Placebo in Functional Constipation (NCT00526097), a randomized phase 3 study. The primary outcome is Mean Number of Complete Spontaneous Bowel Movements (CSBMs) Per Week Over the 4 Weeks Treatment Period.

2. Clinical Question

The study record describes a phase 3 trial comparing four weeks of once-daily bisacodyl tablets with placebo in patients with functional constipation. Its stated objective included assessment of efficacy and safety, and it also evaluated quality of life and general health status. The primary outcome is a weekly measure of complete spontaneous bowel movements, rather than a count of all bowel movements or a measure of symptoms considered separately.

The comparison concerns average outcomes in the two randomized groups. Randomization is intended to support a fair comparison by distributing participant characteristics across groups on average, while double masking is intended to limit influences arising from knowledge of treatment assignment. These design features do not by themselves establish the size, precision, or clinical importance of an observed difference; those require examination of the outcome estimates and their uncertainty.

The primary analysis population was not simply every person enrolled. It required randomization, at least one recorded dose in the eDiary, and some primary-outcome data. The registry record reports 368 enrolled participants, while the primary outcome arm counts are 117 for placebo and 239 for bisacodyl. The record does not explain the difference between enrollment and the analysis counts in detail. The primary question should therefore be read as a comparison in the stated analysis population, not as a result necessarily based on every enrolled participant.

3. Trial Design

This was a randomized, double-blind, parallel-group phase 3 study. Participants were assigned to bisacodyl or placebo, and the registry describes the active treatment as bisacodyl 10 mg once daily for four weeks. The placebo group received matching tablets. The study is listed as completed, with functional constipation as the condition under study.

The parallel-group structure means that the treatment groups were compared with one another over the same study period rather than participants crossing from one treatment to another. Random allocation supports an intention to create comparable groups at entry. Double masking means that treatment assignment was concealed from participants and study personnel identified in the record; the registry record does not give further detail about who remained masked or how masking was maintained.

The registry reports enrollment of 368. For the primary outcome, the Full Analysis Set included randomized patients who recorded at least one dose of trial medication in the eDiary and provided any primary-outcome data. The reported primary arm counts are 117 for placebo and 239 for bisacodyl. The record does not report a detailed flow of participants from enrollment through treatment, follow-up, and analysis, nor does it explain exclusions from the primary analysis population.

The four-week treatment period is also the primary outcome timeframe. The outcome description says weekly CSBM counts were adjusted for the number of days with available data in each week, multiplied by seven, and rounded to the next integer. The resulting weekly values were averaged over weeks with data. This approach is intended to express the outcome on a weekly scale when the number of observed days varies, but it also means that availability of weekly data is relevant to the final measure.

The registry lists additional outcomes concerning CSBMs and spontaneous bowel movements, as well as quality of life and general health status in the study summary. The specific statistical plan, details of allocation concealment, the trial’s original sample-size justification, and any planned interim analyses are not reported in the registry record.

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: Participants were randomised into the treatment period only, when functional constipation and compliance with rescue medication were confirmed by eDiary data in the two-weeks baseline period without study medication.

Overall Study

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full Analysis Set (FAS): All randomised patients, who recorded at least one dose of trial medication in the eDiary and provided any data for the primary outcome measure

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 Mean Number of Complete Spontaneous Bowel Movements (CSBMs) Per Week Over the 4 Weeks Treatment Period, measured over 4 Weeks.

The primary endpoint is the mean number of complete spontaneous bowel movements (CSBMs) per week over the four-week treatment period. A CSBM is defined in the registry as a complete bowel movement not induced by rescue medication. The measure therefore aims to capture bowel movements that meet the completeness criterion without counting those induced by rescue medication as spontaneous.

For each treatment week, the recorded number of CSBMs was adjusted for the number of days with available data: the weekly count was divided by observed days, multiplied by seven, and rounded to the next integer. The resulting weekly values were then averaged across the weeks with data. The endpoint is thus a weekly-rate summary across available treatment weeks, rather than a simple total of all recorded bowel movements during the period.

A continuous measure such as this can summarize how often participants experienced the defined event, while retaining more information about differences in frequency than a binary outcome that classifies participants only as having or not having an event. The mean is useful for a group comparison, but it does not describe how outcomes are distributed among individuals. Participants may have different patterns even when the group average is the same.

The registry reports least-squares means and standard errors for the primary endpoint and a mean difference from an ANCOVA analysis. The population definition and the week-by-week data adjustment are important for interpreting those estimates: the result pertains to the stated analysis population and the endpoint construction described in the record. The registry record does not report additional details about handling missing weekly observations.

7. Results Posted in the Registry

• Bisacodyl: mean 5.20 versus 1.90 on control; difference 3.30 (95% CI 2.45 to 4.15), standardized effect d = 0.82; z-test p = <0.001.

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.

Number of CSBMs at Week 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:
  • Bisacodyl: mean 6.30 versus 2.00 on control; difference 4.30 (95% CI 3.30 to 5.30), standardized effect d = 0.90; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Bisacodyl than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Number of CSBMs at Week 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:
  • Bisacodyl: mean 4.90 versus 1.40 on control; difference 3.50 (95% CI 2.47 to 4.53), standardized effect d = 0.73; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Bisacodyl than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

Number of CSBMs at Week 3

• 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:
  • Bisacodyl: mean 4.60 versus 1.80 on control; difference 2.80 (95% CI 1.83 to 3.77), standardized effect d = 0.63; z-test p = <0.001.
• Interpretation:
  • The 95% confidence interval excludes no difference, so the mean is statistically higher for Bisacodyl than for the control. This is an unadjusted, secondary comparison, so it is suggestive rather than confirmatory.

The reported weekly CSBM analyses in the early treatment period follow the same broad direction as the primary result: the bisacodyl group has higher reported means than the placebo group in the weeks with numerical results. The differences are also positive in the corresponding ANCOVA analyses. This pattern is consistent with the primary comparison, but it should be treated as supporting context rather than as a collection of separate confirmatory findings.

Weekly outcomes from the same participants are related observations, not independent replications. A participant’s bowel-movement pattern in one week may be associated with that in another week. The analyses also refer to related versions of the same outcome, so agreement across them does not provide the same kind of evidence as a result reproduced in a separate study.

The registry lists additional secondary outcomes, including other weekly CSBM and SBM measures. The study summary also says that quality of life and general health status were evaluated. The numerical secondary results described in the record include early weekly CSBM measures; a full interpretation of other outcome domains would require their estimates and analysis details.

Many outcomes and time points create multiple opportunities for apparently notable results, even when no real treatment difference exists for some outcomes. Unless an appropriate multiplicity strategy is specified, unadjusted secondary p-values can overstate the strength of evidence when considered collectively. The registry record does not report a multiplicity adjustment or a hierarchy for interpreting secondary outcomes. The primary endpoint therefore carries greater inferential weight, while secondary results are best viewed as exploratory or supportive unless their testing plan is documented.

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

• Number of CSBMs at Week 1
• Number of CSBMs at Week 2
• Number of CSBMs at Week 3
• Number of CSBMs at Week 4
• Mean Number of SBMs Per Week Over the 4 Weeks Treatment Period
• Number of SBMs at Week 1
• Number of SBMs at Week 2
• Number of SBMs at Week 3

9. Statistical Interpretation

10. Statistical Methods Explained

Several statistical ideas help explain the reported estimates. The primary outcome is continuous: it records a weekly frequency rather than assigning each participant to a yes-or-no outcome category. The registry reports a least-squares mean for each arm. A least-squares mean is a model-based group mean; in an analysis of covariance, it is generally estimated while accounting for variables included in the model. The registry identifies the method as ANCOVA, but the covariates and further model details are not reported in the registry record.

What does the mean difference represent?

The mean difference expresses the distance between the group means in the original outcome units, which are CSBMs per week. The reported ANCOVA mean difference is 3.3. It gives the estimated contrast between bisacodyl and placebo, with a positive value corresponding to the higher mean in the bisacodyl group. Unlike a standardized effect, it remains interpretable on the scale of the outcome itself.

The recalculation uses posted arm summaries to obtain an unadjusted comparison. It reports the same mean difference, 3.3, but its confidence interval differs from the registry’s ANCOVA interval. That difference is expected to be possible because methods can use different information and assumptions. The recalculation is not a replacement for the model-based result reported by the trial. In this record, the discrepancy flag is false, but the two intervals should still be understood as results from different approaches.

Why report a standard error?

The standard error describes the estimated uncertainty around a group mean. It is not a description of the spread of individual participants’ outcomes. A smaller standard error generally corresponds to a more precisely estimated mean, conditional on the analysis and its assumptions. The registry reports standard errors for the arm means, while the recalculated comparison uses those summaries to estimate uncertainty for the difference.

In general, variability among individual outcomes and the amount of information available both influence standard errors. Standard errors are useful for constructing confidence intervals and testing hypotheses, but they do not show the full distribution of outcomes. In a continuous outcome, participants can vary substantially around the average; group means alone do not reveal how much the individual observations overlap.

What does the confidence interval add?

A confidence interval presents a range of values compatible with the data and the statistical method at the stated confidence level. The registry reports a 95% confidence interval for its ANCOVA estimate. In repeated use of the same procedure under its assumptions, intervals of this type are designed to contain the true parameter at the stated rate. This is a property of the method over repeated samples, not a claim that there is a 95% probability that a fixed parameter lies inside this particular interval.

The width of an interval is a practical indication of precision: narrower intervals indicate more precise estimates, while wider intervals leave more uncertainty about the size of the difference. The interval’s position also matters. An interval that spans zero is compatible with no difference under the model, while an interval entirely on one side is not. These interpretations assume that the model and data-handling choices are appropriate; an interval cannot account for bias or unreported analysis decisions.

How should the p-values be read?

The registry reports p < 0.001 for the ANCOVA result. The unadjusted recalculation reports p < 0.001. A p-value describes how unusual results at least as incompatible with a specified null hypothesis would be under that hypothesis and the analysis assumptions. It is not the probability that the null hypothesis is true, and it does not measure the size or practical value of an effect.

The reported ANCOVA p-value belongs to the trial’s model-based analysis. The recalculated p-value is unadjusted and derives from a different calculation. Neither should be interpreted without considering the estimate and its confidence interval. Because the primary endpoint was designated as primary, it has a different evidential role from numerous secondary outcomes. The registry record does not report a multiplicity adjustment for secondary comparisons.

Why can over-dispersion matter?

General statistical explanation: count outcomes often vary more across participants than a simple count model assumes. This extra variation is called over-dispersion. If a model assumes less variability than the data actually contain, its standard errors can be too small and its intervals too narrow. A model that accounts for over-dispersion can produce uncertainty estimates more consistent with the observed variation. The registry record identifies ANCOVA for the reported primary comparison but does not describe a count model or report a specific over-dispersion assessment. The CSBM outcome is summarized as a weekly mean, so model details matter when judging how its uncertainty was estimated.

What are the limits of the recalculated effect summaries?

The recalculated summaries include a pooled standard deviation estimated from reported standard errors and arm counts, and the record marks this standard deviation as approximate. Such a standardized summary places a mean difference on a scale relative to estimated outcome variability, which can aid comparison across measures. It is not the primary endpoint scale and should not replace the clinically interpretable mean difference. Since the underlying standard deviation is approximate, the standardized result should be treated as descriptive rather than as a precise trial-reported quantity.

Model assumptions, outcome construction, available data, and participant selection all affect interpretation. The registry supplies the outcome definition and the FAS entry criteria, but does not report a full statistical analysis plan, covariate list, detailed missing-data procedure, or interim-analysis plan. The posted analysis can be described precisely only to the extent that those details are documented.

11. Confidence Intervals and Precision

The registry’s primary ANCOVA estimate is a mean difference of 3.3 CSBMs per week, with a 95% confidence interval from 2.6 to 4.0. The interval is centered around the reported estimate and spans values on the positive side of zero. It communicates that the estimated difference is more precise than a result with a much wider interval would be, while still leaving uncertainty about the exact size of the difference.

The unadjusted recalculation gives a 95% interval from 2.449 to 4.151. It is wider than the interval reported for ANCOVA and comes from a different method. The recalculated limits should not be mistaken for the trial’s own adjusted interval. The registry analysis remains the main result to quote when describing the trial’s reported statistical finding; the recalculation is an independent summary-statistic comparison.

Confidence intervals are not ranges containing every participant’s response, and they do not describe the spread of individual outcomes. They concern uncertainty in the estimated group difference under the method’s assumptions. The registry also reports standard errors for the group means, but those values likewise describe precision of the means rather than person-to-person variability.

The reported p-value, p < 0.001, conveys evidence against a null difference under the ANCOVA analysis, but a small p-value is not a substitute for judging the interval and estimate. Precision and clinical relevance are separate questions. The registry record does not report a clinical threshold against which the interval could be assessed, nor does it provide enough detail to evaluate all sources of uncertainty, such as missing-outcome handling or model specification.

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 in this trial, not the trial’s original design calculation. The stated planning assumptions are a two-sided significance level of 0.05, equal allocation between two arms, and a normal approximation. The effect to detect is set to a stated fraction of the observed effect. The trial’s own original sample-size assumptions and justification are not reported in the registry record.

The 80% power column gives the number of participants per arm that the planning calculation estimates would be needed to have an 80% chance of detecting the chosen effect under the stated assumptions, if that effect were the true one and the analysis assumptions held. The 90% power column uses a higher probability of detection, so it requires more participants per arm for the same assumed effect. These are planning probabilities under a hypothetical design, not probabilities that the trial result is correct.

The planning rows consider the full observed effect, 75% of the observed effect, and 50% of the observed effect. The estimates rise as the assumed effect gets smaller: smaller effects are harder to distinguish from random variation, so more participants are generally needed to detect them with the same target power. The displayed figures are planning illustrations and should not be read as observed power for this completed trial.

The calculations also assume equal allocation, whereas the primary analysis arm counts are unequal. This is another reason to treat the planning estimates as illustrations under their listed assumptions rather than as a reconstruction of the trial’s design. They do not account for any unreported original design decisions, outcome-specific missingness, or analysis details beyond the assumptions stated in the registry material.

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 = 3.300; pooled standard deviation σ = 4.018.
2. n = 2 × (1.96 + 0.842)² × 4.018² / 3.300² = 23.3, rounded up to 24 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 <- 3.3                      # observed difference in means
sigma <- 4.01818641104396                     # 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(526097)
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 = 24 (80% power), 32 (90% power)
 75% of observed effect: n per arm = 42 (80% power), 56 (90% power)
 50% of observed effect: n per arm = 94 (80% power), 125 (90% power)
power.t.test: 24.3 
Simulated power at n = 24 per arm: 0.794 (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 sponsor’s reported primary analysis is an ANCOVA comparison of final values. It gives a mean difference of 3.3, a 95% confidence interval from 2.6 to 4.0, and p < 0.001. These are the trial’s reported model-based results and should lead interpretation of the primary endpoint.

The simple recalculation from the posted summary statistics gives the same estimated mean difference, 3.3, but a 95% confidence interval from 2.449 to 4.151 and an unadjusted p-value of <0.001. It is an unadjusted calculation, not a replication of the ANCOVA model. It does not have access to the participant-level information or model details that may inform the sponsor’s analysis.

The recalculation is useful as a check on the direction and approximate size of the group contrast using the published summaries. Its interval is not a correction to the sponsor’s interval, and the two p-values should not be treated as if they came from identical tests. The registry record does not report the ANCOVA covariates or full analysis specification, limiting independent assessment of how the model was implemented.

Because the record does not flag a discrepancy between the reported and recalculated estimate, both approaches point to the same estimated mean difference. For the trial’s formal conclusion about its primary endpoint, the sponsor’s own reported analysis takes precedence over the unadjusted recalculation.

15. Multiplicity, Missing Data and Analysis Populations

Multiplicity arises when several hypotheses are tested, as can happen when a trial examines multiple endpoints or measures an outcome at multiple time points. Each test carries a chance of a false-positive finding under its null hypothesis. Considering many unadjusted tests together increases the chance that at least one appears unusually favorable by chance. Methods such as prespecifying a hierarchy or adjusting significance thresholds can address this issue, but they require a defined plan.

The registry identifies a primary endpoint and lists a substantial set of secondary outcome measures, including weekly CSBM and SBM outcomes. It reports ANCOVA analyses for the primary endpoint and several weekly secondary CSBM measures. A multiplicity procedure, testing hierarchy, or prespecified strategy for drawing conclusions across these outcomes is not reported in the registry record. Therefore, the primary result should be distinguished from secondary p-values, which should not be interpreted as if each were the sole planned test.

Missing data also affect interpretation. The primary outcome definition uses available days within a week and averages the resulting values over weeks with data. The FAS included randomized patients who recorded at least one dose and had any data for the primary outcome. This defines who could enter the primary analysis, but it does not fully describe what happened when a participant had a missing week, discontinued treatment, or had incomplete follow-up.

Specific imputation methods, assumptions about missingness, sensitivity analyses, and reasons for unavailable outcome data are not reported in the registry record. Without these details, it is not possible to assess how robust the estimate is to different assumptions about missing observations. The reported arm counts for the primary endpoint are 117 for placebo and 239 for bisacodyl, but a participant-flow account explaining the analyzed and non-analyzed records is not reported.

The primary population is described as a Full Analysis Set, but its definition is tied to dosing and available outcome information. The registry does not report a separate intention-to-treat analysis or an analysis including every randomized participant regardless of data availability. These distinctions matter because the statistical target depends partly on who is included and how missing outcomes are handled. They do not negate the posted estimate, but they limit how fully its sensitivity can be evaluated.

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: pregnancy (0.8%), fall (0.8%), tibia fracture (0.8%), chest pain (0.4%).

The registry reports serious adverse events for 2 participants in the placebo group, with 121 at risk, and 1 participant in the bisacodyl group, with 247 at risk. These are counts reported by group, not estimates of causation. The record also reports other adverse events affecting 14 participants in the placebo group and 159 in the bisacodyl group, with the corresponding at-risk counts of 121 and 247. The registry summary does not provide enough detail to interpret the nature, timing, severity, or treatment relationship of all these events.

The serious-event terms listed include Pregnancy at 0.8%, Fall at 0.8%, Tibia fracture at 0.8%, and Chest pain at 0.4%. The record does not identify an arm-specific mapping for these terms in the listed summary, so they should not be assigned to a treatment group on that basis. Death counts are not reported in the registry record.

Adverse-event counts need context, including how events were defined and collected, how long participants were followed, and whether events were judged related to treatment. Those details are not reported in the registry record. The figures should therefore be read as registry-reported counts rather than as a complete comparative safety assessment.

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

The primary result describes a difference in average weekly CSBMs between the bisacodyl and placebo groups during the four-week treatment period. The registry’s ANCOVA estimate is 3.3 CSBMs per week, with a 95% confidence interval from 2.6 to 4.0. The direction of the estimate favors a higher mean in the bisacodyl group on this defined outcome, and the reported p-value is p < 0.001.

This is a group-level statistical result. It does not mean that every participant experienced the estimated difference, and it does not describe the full range of individual outcomes. Group means can conceal variation in response, and the registry does not provide participant-level distributions in the material summarized for this analysis.

The result also does not, by itself, determine whether the observed difference is clinically important. That judgment would require a meaningful threshold or other clinical context, which is not reported in the registry record. Statistical evidence and clinical importance are related but distinct: a precise estimate can still require clinical interpretation, and a statistically notable result is not automatically important to every patient.

The endpoint is based on complete spontaneous bowel movements and is constructed from weekly records with available data. It does not directly summarize all aspects of constipation, overall health, or quality of life. Although the study summary says quality of life and general health status were evaluated, the information described for the primary analysis does not establish what happened on those outcomes.

The finding pertains to the stated four-week treatment period and the primary analysis population. It does not establish longer-term outcomes, outcomes in populations not represented in the trial, or the balance of benefits and risks beyond the registry’s reported information. The safety summary is limited to event counts and selected serious-event terms, with further details not reported. The estimates should be interpreted as trial results, not as individualized predictions or medical advice.

18. Why This Trial Matters Statistically

This trial illustrates why a treatment comparison should be read through both its estimate and its uncertainty. The mean difference gives an interpretable contrast in CSBMs per week, while the confidence interval indicates the range of values compatible with the ANCOVA analysis. A p-value alone would not show the magnitude or precision of the contrast, and the mean difference alone would not convey its uncertainty.

It also highlights the distinction between a trial’s own model-based analysis and a simple recalculation from summary statistics. Both give a mean difference of 3.3, but their intervals and p-values differ because the methods differ. Reporting both can help readers understand what can be reconstructed from group summaries and what depends on the original model. The sponsor’s ANCOVA result remains the formal reported analysis.

The endpoint construction is statistically consequential. Weekly values are adjusted for days with available information and averaged over weeks with data, so the handling of incomplete weeks and the definition of the analysis population shape the estimand. The registry reports the construction and FAS criteria, but not all missing-data assumptions. Readers can therefore understand the stated outcome while recognizing that important implementation details remain undocumented.

Finally, the secondary outcomes and planning illustrations show why statistical evidence needs a hierarchy. Multiple time points and outcomes can generate many comparisons, while sample-size illustrations based on an observed effect can be mistaken for the trial’s original design calculation. Keeping the primary endpoint distinct, interpreting secondary results cautiously, and labeling planning figures as hypothetical helps prevent overstatement. These principles are broadly useful when reading registry-based trial results.

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 specific to this record affect interpretation. The primary analysis counts are 117 for placebo and 239 for bisacodyl, while enrollment is reported as 368. The registry does not provide a participant-flow explanation that reconciles enrollment with the primary analysis population or details the reasons participants may not have contributed outcome data.

The primary outcome depends on diary-recorded bowel movements and on data availability during each week. The registry describes the adjustment for observed days and averaging across weeks with data, but does not report a detailed missing-data strategy, sensitivity analyses, or the extent and pattern of missing weekly records. The FAS definition also requires at least one dose and some primary-outcome data, so the result does not necessarily represent all randomized participants.

The ANCOVA method is named, but covariates and other model specifications are not reported. The recalculated interval uses an approximate pooled standard deviation and an unadjusted comparison; it cannot reproduce the trial model from summary statistics alone. The registry does not report the full statistical analysis plan or an interim-analysis plan.

The record lists a broad set of secondary outcomes, but a multiplicity strategy is not reported. Secondary findings therefore have less definitive status than the primary analysis. The study summary says quality of life and general health status were evaluated, but numerical results for those domains are not included in the outcome information described in this record.

The safety information is also limited. Counts are reported for serious and other adverse events, and selected serious-event terms are listed, but the record does not provide a full account of event timing, severity, relatedness, or arm-specific mapping for the listed terms. Death counts are not reported in the registry record. These gaps limit conclusions about the completeness of safety reporting.

20. Related Tutorials

21. Related Statistical Calculators

22. Sources

• ClinicalTrials.gov: Dulcolax vs Placebo in Functional Constipation — NCT00526097.
• Registry record last updated 2014-01-15; status last verified 2013-12.
• Results first posted 2010-08-06.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

23. Record Summary

The registry describes a completed, randomized, double-blind, parallel-group phase 3 study of bisacodyl 10 mg once daily versus matching placebo for four weeks in patients with functional constipation. The primary outcome was mean CSBMs per week over the treatment period in the Full Analysis Set.

The reported ANCOVA mean difference was 3.3 CSBMs per week, with a 95% confidence interval from 2.6 to 4.0 and p < 0.001. An unadjusted recalculation gives the same estimate with a wider interval. The primary result is positive in direction, but clinical importance cannot be established from the registry information alone.

Interpretation is limited by unreported details about missing data, ANCOVA specification, multiplicity, and participant flow. Secondary results broadly align in direction, while safety reporting is summarized as event counts and selected terms.