Continuous Administration of Oral Contraceptive, Primary Dysmenorrhea: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Continuous Administration of Oral Contraceptive, Primary Dysmenorrhea (NCT00517556), a randomized phase 1, phase 2 study. The primary outcome is Change in Visual Analog Scale (VAS) Score.

2. Clinical Question

The registry describes this as a superiority question: whether the continuous schedule produces greater improvement in subjective pain perception than the cyclic schedule. The primary measure is change in VAS score, for which a negative value means improvement and a positive value means worsening. That direction is important when reading the posted arm results: the mean changes are negative in both groups.

The comparison concerns dosing schedules, not different listed contraceptive ingredients. The registry describes the intervention and control as the same monophasic oral contraceptive, while distinguishing continuous use from the traditional active-and-inactive schedule. The record does not report further details about participant characteristics, eligibility criteria, or how primary dysmenorrhea was established. Consequently, the clinical question can be stated for the enrolled study population, but the record does not support a detailed account of which patients the findings may represent.

3. Trial Design

This completed study is listed as randomized, single-masked, and parallel-group, with phase 1 and phase 2 designations. The registry reports enrollment of 38 participants. The two groups each have 19 participants in the posted primary outcome results. The record identifies Milton S. Hershey Medical Center as the sponsor.

The intervention group received continuous administration of the monophasic oral contraceptive for 168 continuous days through six cycles. The control group received the same listed formulation on a traditional schedule of 21 active days and 7 inactive days, also through six cycles. Thus, as described in the record, the central treatment contrast is the schedule of administration.

The registry lists the study start as 2007-08, primary completion as 2011-03, and status as completed. It identifies one primary outcome measure and one reported analysis. The primary outcome is change in VAS score, assessed at baseline and 6 months. The registry identifies the analysis as a mixed models analysis and labels the comparison as superiority.

Some design details that would help explain how the trial was carried out are not reported in the registry record. These include the method used to generate the random allocation sequence, whether allocation was concealed, who was masked, and how adherence to either schedule was assessed. The record also does not report the sample-size justification or the planned analysis population. Those omissions do not change the design features that are listed, but they limit assessment of implementation and the intended analysis.

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 Change in Visual Analog Scale (VAS) Score, measured over Baseline and 6 months.

The primary endpoint is change in Visual Analog Scale score from baseline to 6 months. The scale records a participant’s subjective perception of pain and ranges from 0, meaning no pain, to 100, meaning worst pain. The registry defines a negative change as improvement in pain and a positive change as worsening.

Using change rather than only a score at the end of follow-up describes how the recorded pain score moved between the two assessments. A scale offers a structured way to record a subjective experience, allowing pain to be summarized numerically for a group comparison. The endpoint is continuous, and the posted arm summaries report means with 95% confidence intervals.

As a general statistical point, a mean gives a summary of the group’s average change, while the spread of individual responses is not fully conveyed by the mean alone. The confidence interval describes uncertainty around the estimated mean under the analysis assumptions; it is not a range containing every participant’s change. The registry does not report a separate between-group confidence interval for the primary comparison, nor does it post individual participant data. Therefore, the arm-level summaries describe each group’s average change but do not by themselves fully quantify the uncertainty in the difference between schedules.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is a continuous measure: change in VAS score. The registry reports each arm’s mean change and 95% confidence interval, then identifies a mixed models analysis for the superiority comparison. These summaries and the reported model result answer related but different questions. The means describe average change within each arm; the inferential analysis addresses the comparison between arms according to the sponsor’s stated method.

What does a mean change describe?

In general, a mean is the arithmetic average of the observed values for a group. For a change score, the values represent movement from the baseline assessment to the later assessment. Here, the registry states that the assessment points are baseline and 6 months and defines negative change as improvement in pain. Accordingly, the negative mean in each group describes average movement toward a lower VAS score. The mean does not show whether individual participants had similar changes or whether responses varied widely.

The posted confidence intervals quantify uncertainty around each arm’s estimated mean under the method used to calculate them. In general, a confidence interval is constructed by a procedure that would capture the target parameter at its stated rate over repeated applications, if the assumptions hold. It should not be interpreted as the probability that the true mean lies in this particular interval, or as a range containing most individual changes. The registry does not identify the method used to calculate the arm-level intervals.

Why is the comparison not just a subtraction of the arm means?

In general, a contrast between groups can be estimated directly, with uncertainty based on the analysis model and available observations. The posted registry record gives the arm means and their intervals but reports the comparative analysis as mixed models. It does not post the model’s between-group estimate or its confidence interval. A simple unadjusted recalculation from summary statistics is not estimable for this continuous comparison in the record, so an independent numerical contrast should not be inferred from the arm summaries.

The intervals around separate arm means are not the same as an interval around a difference between means. The uncertainty in a contrast depends on the variability and relationship of the observations used in the analysis, as well as the model. In general, comparing separate confidence intervals visually is not a formal test of the contrast and does not replace the reported model-based result.

What does a mixed models analysis generally do?

General explanation: mixed models can represent repeated measurements and account for dependence among observations from the same participant, while also estimating average patterns across participants. The exact model specification matters: it can include particular time effects, treatment terms, covariates, or assumptions about the structure of repeated observations. The registry record names a mixed models analysis but does not report its specification, the observations included in the model, or the assumptions used. Those details cannot be reconstructed from the method label alone.

The reported p-value is 0.05, and the analysis is labeled superiority. In general, a p-value summarizes how unusual the data would be under a specified null hypothesis and the analysis assumptions. It does not measure the probability that the null hypothesis is true, the probability that the result will replicate, or the size of the treatment contrast. The registry does not report whether the p-value is one-sided or two-sided, or provide the model estimate and its interval. The p-value should therefore be read as the inferential result the record reports, not as a complete account of effect magnitude and precision.

How should sample-size illustrations be read?

General explanation: a sample-size calculation for a future study depends on a target effect, a significance level, allocation, and assumptions about the outcome and analysis. The registry’s sample-size illustrations are described as planning illustrations based on the observed effect, using a two-sided significance level of 0.05, equal allocation, and a normal approximation; the target effect is expressed as a stated fraction of the observed effect. Such illustrations are not the trial’s original sample-size justification, and the original justification is not reported in the registry record. They are not observed power and do not show that the trial had a particular probability of detecting an effect. The numerical planning results are not stated in the registry record material summarized in this explanation, so no sample-size values are inferred.

For this trial, the key distinction is between the posted arm summaries and the sponsor’s model-based comparison. The former show average changes and their arm-level intervals; the latter is represented by a p-value without a posted comparative estimate or interval. A sound reading keeps those quantities separate and avoids treating any one of them as a complete description of the result.

10. Analyses Reported by the Sponsor

The registry reports the sponsor’s primary comparison as a mixed models analysis, labeled superiority, with p = 0.05. It does not report the model’s estimated between-group effect, its confidence interval, or enough model detail to reproduce the analysis from the posted results.

A direct unadjusted recalculation from the arm-level summary statistics is not estimable for this continuous endpoint in the registry record. There is therefore no recalculated between-group estimate to compare numerically with the sponsor’s result. The posted mean changes and arm-level confidence intervals describe each group separately; they do not supply the missing model contrast. The record indicates no discrepancy between a sponsor result and a recalculation, but the absence of a recalculated comparison also means that agreement cannot be assessed through an independent numerical contrast.

The sponsor’s p-value is consequently the only posted inferential result for the comparison. It should be read alongside the descriptive arm results, while recognizing that the registry does not provide the comparative effect estimate or precision needed for a fuller statistical interpretation. The record does not report additional details that would permit an independent reproduction of the mixed models analysis.

11. Multiplicity, Missing Data and Analysis Populations

The registry lists one primary outcome measure and one reported analysis, and it lists zero secondary outcomes posted. This describes the outcomes and analysis appearing in the registry record; it does not establish that no other outcomes or analyses were considered during the study. A multiplicity adjustment or strategy for handling multiple outcomes, time points, or analyses is not reported in the registry record.

Multiplicity matters in general because conducting multiple tests can increase the chance of obtaining at least one apparently unusual result under a collection of null hypotheses. Whether adjustment is appropriate depends on the planned questions and analysis strategy. The registry’s listing alone does not provide enough information to determine what testing family was planned or whether any adjustment was used. Interim analyses and any associated statistical rules are not reported in the registry record.

The primary outcome is described as measured at baseline and 6 months, but the record does not state how missing outcome measurements were handled. It does not report the number of participants with observed VAS data at each assessment, reasons for missingness, imputation methods, or sensitivity analyses. The posted arm sample sizes are 19 in each group, but the record does not establish that every enrolled participant contributed complete observations to the mixed models analysis.

The planned analysis population is also not reported in the registry record. Randomization is listed, but the record does not say whether the analysis followed an intention-to-treat principle, used a per-protocol population, or applied another rule for inclusion. These omissions matter because the analyzed population and handling of incomplete data can affect the interpretation of an estimated treatment contrast. No conclusion about missing-data bias or the extent of protocol adherence can be drawn from the posted summaries alone.

12. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 5% reporting threshold.

The registry reports zero serious adverse events among 19 participants at risk in the study group and zero among 19 participants at risk in the control group. It also reports zero other adverse events affecting participants in each group, with 19 at risk in each. Deaths are reported as zero in both groups. No serious adverse event terms are listed.

These figures describe what the registry reports for the participants counted at risk. A report of zero events is not proof that an event cannot occur, and it does not establish that the groups have identical safety profiles. With no events reported in either group, the record does not provide an event-based comparison that can distinguish the schedules’ risks.

In general, adverse-event summaries depend on the period of observation, definitions, collection procedures, and completeness of reporting. The registry record does not provide further detail on these matters or report how adverse events were elicited and classified. The zero counts should therefore be read as registry-reported counts, not as evidence of absence of all possible harms.

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

The posted results show negative mean changes in VAS score for both groups between baseline and 6 months. Under the endpoint definition, negative change indicates improvement in the recorded pain score. The study group’s posted mean is more negative than the control group’s posted mean, while the reported mixed models comparison has p = 0.05.

That description does not establish the size of the comparative effect. The registry does not report the model-based between-group estimate or its confidence interval. The arm-level means and intervals are not substitutes for those comparative statistics. The reported p-value gives an inferential result under the sponsor’s model, but by itself does not convey the magnitude, clinical importance, or precision of a difference between schedules.

The result is specific to the measured outcome, the stated baseline-to-6-month timeframe, the participants enrolled, and the regimens described in the registry. It does not provide evidence about outcomes beyond the VAS measure or after the reported assessment period. Details about participant eligibility, adherence, missing observations, and the analysis population are not reported in the registry record, which constrains conclusions about how broadly the findings apply.

The safety figures are also limited: the registry reports zero serious adverse events, zero other adverse events affecting participants, and zero deaths in each group. These reported counts should not be read as proof of no risk. Overall, the posted material allows a description of the observed arm summaries and the sponsor’s reported test, but not a complete estimate of comparative benefit and uncertainty or a broad conclusion about safety.

14. Why This Trial Matters Statistically

This trial is statistically interesting because it compares two schedules of the same listed oral contraceptive formulation. The question is therefore framed around continuous versus traditional cyclic administration, rather than a comparison of different listed ingredients. That makes clarity about the treatment contrast, outcome timing, and statistical estimate especially important.

The registry provides useful descriptive information: arm-level mean changes, confidence intervals, and a reported mixed models p-value. At the same time, these statistics answer different questions. The group means describe average change within each arm, while the model-based comparison is the inferential test of superiority. Without the model’s estimated contrast and its confidence interval, the comparative result is less fully characterized than the arm summaries might initially suggest.

The case also illustrates a general principle in interpreting confidence intervals. Intervals around separate group means are not the same as an interval for the difference between those means. A direct comparative estimate communicates both direction and magnitude, while an interval for that contrast indicates its precision under the model. The registry does not post those quantities for the primary comparison.

Finally, the record shows why a reported p-value needs context. The p-value is not an effect size, and it cannot by itself show whether a difference is large, clinically meaningful, or precisely estimated. Reading the endpoint definition, arm summaries, model label, and reporting gaps together gives a more disciplined account than relying on a single inferential statistic.

15. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The main reporting limitation is the absence of the estimated between-group effect and its confidence interval for the primary outcome. The registry reports arm-level means and intervals and a mixed models p-value, but not the comparative estimate needed to describe the magnitude and precision of the schedule contrast directly. A recalculated unadjusted comparison is not estimable from the posted summary statistics.

The mixed models analysis is named but not described in enough detail to reproduce. The model specification, included observations, covariance structure, and any adjustment variables are not reported in the registry record. The method used to calculate the arm-level confidence intervals is also not stated.

Important conduct and analysis details are absent. The record does not report the randomization procedure, allocation concealment, identity of the masked party, adherence assessment, planned analysis population, or handling of missing outcomes. It does not provide participant-level outcome data or details about eligibility and participant characteristics. These gaps limit assessment of internal validity, generalizability, and the robustness of the result.

The registry identifies one primary outcome and one analysis, but multiplicity procedures and interim analyses are not reported. The original sample-size justification is not reported in the registry record; any sample-size illustrations based on the observed effect are planning exercises rather than evidence about the trial’s original design or observed power. The limited adverse-event summaries also do not describe ascertainment methods or the duration of safety surveillance in detail.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: Continuous Administration of Oral Contraceptive, Primary Dysmenorrhea — NCT00517556.
• Registry record last updated 2017-04-28; status last verified 2017-03.
• Results first posted 2017-04-28.
• 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.

19. Record Summary

NCT00517556 is a completed randomized, single-masked, parallel-group study listed as phase 1 and phase 2, with enrollment of 38. It compares continuous administration of a monophasic oral contraceptive with the traditional 21 active days and 7 inactive days schedule, through six cycles.

The primary endpoint is change in VAS score from baseline to 6 months. Mean change was -74.8 in the study group and -58.7 in the control group; negative change indicates improvement. The registry reports a mixed models superiority analysis with p = 0.05, but does not post a comparative effect estimate or confidence interval.

The registry reports zero serious adverse events, zero other adverse events affecting participants, and zero deaths in each group. Details on missing data, analysis populations, model specification, and the original sample-size justification are not reported in the registry record.