A Study to Evaluate the Change in Weight After 24 Weeks Treatment With LIK066 in Obese or Overweight Adults: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for A Study to Evaluate the Change in Weight After 24 Weeks Treatment With LIK066 in Obese or Overweight Adults (NCT03100058), a randomized phase 2 study. The primary outcome is Percent Change From Baseline in Body Weight at 24 Weeks.

2. Clinical Question

This is a dose-finding question rather than a comparison of a single LIK066 regimen with placebo. Multiple dose levels and dosing frequencies allow the observed pattern across groups to be considered, but they also mean that individual comparisons should be interpreted in the context of the trial’s full set of analyses. The registry record identifies the endpoint and analysis population but does not report a detailed account of eligibility criteria, treatment adherence, or the allocation procedure beyond stating that allocation was randomized. The later treatment period extends the study to 48 weeks, but the primary endpoint described for this analysis is the 24-week result. Results from that period should not be read as estimates of the effect of the subsequent treatment arrangements.

3. Trial Design

The registry describes a randomized, triple-masked, parallel-group phase 2 study. It enrolled 460 participants with obesity or overweight and evaluated LIK066 against placebo. The study was designed as a dose-finding investigation: eight LIK066 regimens were compared with placebo during the first 24 weeks, followed by 24 weeks involving two LIK066 doses and placebo. The record gives the study status as completed.

For Epoch 3, the listed LIK066 groups were 2.5mg, 10mg, 50mg, and 150mg once daily, and 2.5mg, 5mg, 25mg, and 50mg twice daily. A placebo group was also included. The primary endpoint was measured from baseline to Week 24, so the reported comparison addresses the first treatment period. The listed sample sizes for the primary endpoint range from 38 to 78 across the dose and placebo groups. These are the endpoint analysis counts, not a substitute for the overall enrollment figure.

In Epoch 4, participants were assigned to further treatment arrangements that depended on their earlier regimen, as described in the registry. The record includes outcomes for the later period, but those results are not the focus of the primary endpoint interpretation. The study’s start and primary completion dates are recorded as 2017-05-06 and 2018-03-02, respectively. Specific details about the randomization sequence, concealment, masking procedures, follow-up completion, and protocol-defined analysis plan are not reported in the registry record. The label “triple” describes the recorded masking category but the identities of the masked parties 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: Overall, 674 patients were screened. Of the 460 patients who were randomized to the study, the majority (85.7%) completed Epoch 3. Of the 394 patients who completed Epoch 3 and entered Epoch 4, the majority (93.1%) completed the Epoch 4 study period.

Only the first 6 of 13 groups are shown.

Epoch 3 (24 Weeks of Treatment)

Reasons for not completing this period:

Epoch 4 (Last 24 Weeks of the Study)

Reasons for not completing this period:

Analysis population for the primary outcome, as defined in the registry: Full Analysis Set

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.

Only the first 6 of 10 groups are shown.

6. Primary Endpoint

The registry lists the primary outcome as Percent Change From Baseline in Body Weight at 24 Weeks, measured over Baseline, Week 24 (Epoch 3).

The primary endpoint was percent change from baseline in body weight at Week 24, with the timeframe specified as baseline and Week 24 in Epoch 3. A percent-change measure expresses a participant’s follow-up weight relative to their baseline weight, so it can describe change on a common relative scale even when participants begin at different weights. The registry reports group means and 95% confidence intervals for this endpoint in the Full Analysis Set.

For this measure, negative estimates indicate a mean decrease from baseline, while a value nearer zero indicates less average change in the decreasing direction. The placebo group’s posted mean was -0.63, with a 95% confidence interval from -1.56 to 0.37. The LIK066 group means ranged from -1.24 for 2.5mg once daily to -4.47 for 50mg twice daily. These are within-group estimates; they do not by themselves give the adjusted difference between a LIK066 group and placebo.

The endpoint is used to assess whether the amount of weight change varies across the tested dose regimens relative to placebo after 24 weeks. The registry describes the objective as evaluating the dose-response relationship. A 95% confidence interval gives a range of values compatible with the estimate under the analysis assumptions; it indicates statistical precision, not the probability that an individual participant will experience a particular change. The protocol’s rationale for selecting this endpoint and the detailed clinical interpretation rules are not reported in the registry record.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous: it is a numerical measure of percent change in body weight. The registry reports the mean for each group and a 95% confidence interval. It also lists ANCOVA as the method for the posted comparisons with placebo. These are distinct summaries: group means describe the observed endpoint in each arm, whereas the ANCOVA entries give model-based net comparisons.

What does a confidence interval convey?

In general, a confidence interval describes the uncertainty around an estimate under the statistical model and sampling assumptions used to construct it. A narrower interval indicates greater precision than a wider interval on the same measurement scale. It does not describe the spread of individual participant outcomes, and it is not a range expected to contain every participant’s result. Nor is it a direct statement about the probability that the true effect lies within the particular calculated interval. The registry reports 95% confidence intervals for the primary group means and the listed net comparisons.

For the primary group means, the intervals indicate that the estimates are not infinitely precise. For instance, the placebo mean is -0.63, with limits of -1.56 and 0.37. The 150mg once-daily group mean is -4.37, with limits of -5.36 and -3.37. These intervals concern each arm’s mean. They are not the same as the ANCOVA confidence intervals for LIK066-versus-placebo contrasts, which incorporate the comparison model.

What does ANCOVA add?

In general, analysis of covariance compares groups while accounting for one or more covariates included in the model. When baseline measurement is included, ANCOVA can estimate a treatment-group contrast adjusted for baseline differences, often with improved precision compared with a simple comparison of follow-up means. The registry identifies ANCOVA for the listed primary contrasts, but the covariates, model specification, handling of missing observations, and any additional adjustments are not reported in the registry record. It is therefore appropriate to describe the method named in the record without assuming specific model details.

The posted net estimates are negative, which indicates a difference in the direction of a greater decrease in the LIK066 group relative to placebo on the percent-change scale. The registry labels most as mean differences, but lists the 10mg once-daily result as a median difference. The record also contains two distinct entries for the 2.5mg twice-daily group. These labels and entries should not be silently harmonized. The reported analysis values are retained as recorded.

How should p-values be read?

In general, a p-value measures how unusual data at least as incompatible with a specified null hypothesis would be under the model assumptions, if that null hypothesis were true. It is not the probability that the null hypothesis is true, and it does not measure the size or clinical importance of an estimated difference. The registry lists p < 0.001 for the primary ANCOVA comparisons. Such a threshold gives limited information about the exact p-value, and interpretation also depends on the prespecified testing strategy and the number of analyses performed.

Multiple dose groups mean that several comparisons with placebo are available. In general, testing multiple hypotheses without adjustment can increase the chance of obtaining at least one apparently small p-value when all null hypotheses hold. Whether and how multiplicity was handled is not reported in the registry record. The listed p-values should therefore be read as the reported results, not assumed to be multiplicity-adjusted.

What is the role of the group means?

Group means give a readable description of average change, but a mean alone does not show the distribution of participant-level outcomes. The registry does not provide a dispersion statistic alongside the primary means; it provides confidence limits instead. The mean also may not capture skewness or the experiences of participants at different parts of the outcome distribution. The reported ANCOVA contrasts and their intervals add information about relative differences, but do not replace examination of individual-level distributions or details of the analysis plan.

Because this is a dose-finding study, the pattern across the dose arms is relevant. A sequence of increasingly negative means can be consistent with a dose-related pattern, but a formal dose-response conclusion depends on the model, planned contrasts, and uncertainty across the full set of regimens. The registry objective refers to a dose-response relationship, but the model used to evaluate that relationship beyond the posted pairwise ANCOVA comparisons is not reported in the registry record.

What can planning illustrations tell the reader?

In general, a sample-size planning illustration applies assumptions about an effect, variability, significance level, allocation, and statistical model to estimate a future study size. The registry’s displayed illustration is explicitly computed from an observed effect and is not the trial’s own design calculation. It assumes a two-sided significance level of 0.05, equal allocation, and a normal approximation, and considers planning for 100%, 75%, and 50% of the observed effect. These values are planning illustrations, not observed power and not evidence that the original trial was designed around those assumptions. The registry’s sample-size justification and its original planning assumptions are not reported in the registry record.

10. Analyses Reported by the Sponsor

The registry’s posted primary comparisons are ANCOVA analyses and should be distinguished from simple recalculations based on arm-level summary statistics. The ANCOVA entries are the sponsor’s reported analyses in the registry record; no discrepancy between those analyses and recalculations is flagged. They are therefore the relevant reported model-based contrasts for describing the primary endpoint, while the arm means remain useful for showing the overall pattern in each group.

The sponsor-reported entries compare individual LIK066 groups with placebo rather than comparing dose groups directly. Most are identified as mean differences, with the 10mg once-daily result identified as a median difference. The 2.5mg twice-daily group appears in two separate entries with different estimates. These record details should be preserved rather than recast as a single, internally consistent set of estimates. The confidence intervals and p-values are quoted as posted; the record does not provide enough model detail to independently reproduce the ANCOVA results.

For the posted pharmacokinetic outcomes, no sponsor-reported comparison analyses are listed. Any simple comparisons calculated from the summary means and standard deviations are unadjusted recalculations, not the sponsor’s own model-based inference. They should not displace reported analyses if those become available. They also do not answer the primary weight endpoint question. The registry does not report further detail on the sponsor’s analysis plan, including how the several primary dose comparisons were handled as a family.

11. Multiplicity, Missing Data and Analysis Populations

The registry identifies the Full Analysis Set for the primary outcome and reports endpoint counts for the arms. It does not describe the exact membership rules for that analysis set, how participants were handled if they stopped treatment or missed a measurement, or the method used to address missing Week 24 values. Those details are not reported in the registry record. Without them, the effect of missing data on the estimates cannot be assessed from the posted summaries alone.

In general, missing outcome data can affect an analysis when the probability of a missing measurement is related to the outcome or differs between groups. Different assumptions and methods for handling missing observations can lead to different estimates. The registry’s use of a Full Analysis Set label does not by itself establish how missing data were handled or whether all randomized participants contributed to the Week 24 estimate. No sensitivity analyses for missing data are reported in the registry record.

Multiplicity is also relevant because the primary question involves eight LIK066 dose regimens compared with placebo. The registry posts multiple ANCOVA comparisons, but does not report whether a correction, gatekeeping procedure, or other approach was used to control the overall error rate across these tests. The number of outcome measures and analyses is also substantial in the record: 20 outcome measures and 148 analyses. These counts do not establish that every analysis was tested as a confirmatory hypothesis, but they underscore why the analysis hierarchy and testing strategy matter. Those details are not reported in the registry record.

The registry does not report whether interim analyses were conducted, whether the sample size was determined using a particular power calculation, or what assumptions informed the original design. The planning illustrations based on observed effects are not evidence about the trial’s original design rationale. Further details on protocol deviations, analysis populations for secondary outcomes, and sensitivity analyses are also not reported in the registry record. These gaps limit assessment of robustness and confirmatory status; they do not erase the numerical results that are posted.

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 2% reporting threshold.

Most frequent serious adverse event terms

Most frequent non-serious adverse event terms

Serious events with the highest arm-level rate: anaemia (2.6%), angina pectoris (2.6%), atrial fibrillation (2.6%), abdominal pain lower (2.6%), abdominal pain upper (2.6%).

The registry’s adverse-event summaries include serious adverse events, other adverse events, and deaths by listed treatment group. For serious adverse events, the reported counts range from 1 to 5 among groups with 38 to 77 participants at risk. One death is listed in the 10mg once-daily/25mg once-daily sequence and one in the 2.5mg twice-daily/35mg once-daily sequence; the remaining listed groups report zero deaths. These are counts in the record, not adjusted comparisons between treatments.

Other adverse events are recorded for 24 to 55 participants across the groups, with group counts at risk ranging from 38 to 77. The registry also lists serious-event terms with a percentage of 2.6% for anaemia, angina pectoris, atrial fibrillation, lower abdominal pain, upper abdominal pain, and duodenal ulcer. The record does not provide enough context in these summaries to determine how events were adjudicated, whether a participant could contribute multiple events, or how exposure duration varied between groups.

These figures are descriptive. They should not be treated as proof that one regimen is safer or less safe than another, especially without a prespecified comparison, exposure-adjusted rates, or uncertainty estimates. The listed safety groups include treatment sequences extending across the later study period, so they are not directly interchangeable with the Epoch 3 primary endpoint groups. The registry record does not report additional detail on causality assessments or comparative safety analyses.

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

The posted primary results describe average percent change in body weight at Week 24 across eight LIK066 regimens and placebo. All LIK066 group means are negative, and the means are more negative for several of the higher listed doses than for lower doses. The registry’s ANCOVA entries report negative net comparisons with placebo and p < 0.001 for each listed comparison. These are the statistical results recorded for the endpoint; they are not, on their own, a complete assessment of clinical importance or a guarantee about individual outcomes.

The estimates do not establish which LIK066 dose is preferable, because the posted contrasts are against placebo and do not directly compare regimens with one another. The registry also does not report the decision criteria for selecting doses for further study. Interpretation across all comparisons is limited by the absence of information about multiplicity handling, missing-data methods, and the detailed ANCOVA model. The record’s duplicate entry for the 2.5mg twice-daily comparison and the differing label for the 10mg once-daily estimate are additional reasons to retain the exact reported wording.

The result is specific to the 24-week primary endpoint in the Full Analysis Set. It should not be extended to the later treatment period, to the other secondary outcomes, or to populations and circumstances not described in the registry record. The pharmacokinetic summaries address exposure measures rather than weight change. The safety figures are descriptive event counts and do not establish comparative safety.

More generally, statistical evidence and clinical importance are related but different questions. In general, a small p-value does not indicate how meaningful an effect is, while an estimate and its confidence interval help describe magnitude and precision. The registry does not report a threshold for clinically important weight change or a formal interpretation rule for the endpoint. Accordingly, the results support an account of the observed group pattern and the reported statistical contrasts, while leaving questions of practical importance, robustness, and treatment choice unresolved.

14. Why This Trial Matters Statistically

This trial is statistically informative because it examines several doses and two dosing frequencies within a randomized, parallel-group design. Rather than asking only whether one selected dose differs from placebo, the dose-finding objective makes the pattern across arms important. The endpoint means show how the average weight change varied across the tested regimens, while the registry’s ANCOVA entries provide model-based comparisons with placebo. Keeping these summaries distinct prevents within-group changes from being mistaken for treatment contrasts.

The study also illustrates why estimates, confidence intervals, and p-values answer different questions. The point estimates describe the direction and size of the posted group means or net comparisons; confidence intervals show their precision under the analysis; p-values address compatibility with a null hypothesis under model assumptions. None of these alone determines clinical relevance. That distinction matters especially in a study with multiple dose comparisons and a broad set of secondary measures.

Its record also makes transparent some interpretive limits that often matter in registry-based statistical reading. The reported ANCOVA contrasts are not accompanied by the detailed model specification, and the multiplicity strategy and missing-data approach are not reported. The reported comparison entries include a duplicate for one dose group and a different parameter label for another. These features argue for describing the posted results faithfully rather than smoothing inconsistencies or inferring unreported analysis choices.

Finally, the pharmacokinetic outcomes and adverse-event summaries serve different purposes from the primary endpoint. Exposure measures add information about drug concentrations, while event counts describe recorded safety outcomes. Neither can be treated as an independent substitute for the weight endpoint. This combination makes the trial a useful example of reading a multi-arm dose-finding result with attention to estimands, precision, analysis structure, and limits of the registry record.

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 posted primary summary is limited to group means, confidence intervals, and listed ANCOVA contrasts. The record does not report the covariates or full specification for the ANCOVA, the handling of missing values, or sensitivity analyses. Consequently, the model-based results cannot be independently reproduced from the registry summaries alone. The Full Analysis Set is named, but its operational definition is not reported in the registry record.

The multiplicity strategy for the several dose-versus-placebo comparisons is not reported. This matters when interpreting the collection of reported p-values and when considering whether the results were intended as confirmatory or exploratory. The registry also includes multiple outcomes and analyses but does not report an analysis hierarchy. The primary entries contain two reported estimates for the 2.5mg twice-daily group and describe the 10mg once-daily estimate as a median difference while other entries are labeled mean differences. These details make it important not to present the comparisons as a uniform set of estimates without qualification.

The numerical secondary summaries available in the record focus on pharmacokinetic outcomes. Numerical results for the other listed secondary outcomes are not reported in the registry record, limiting assessment of how those outcomes relate empirically to the weight endpoint. The adverse-event summaries provide counts by treatment sequence but do not include comparative uncertainty estimates or exposure-adjusted rates in the information. The registry’s planning illustrations are based on observed effects, not the original sample-size justification.

Finally, the description of the later treatment period does not supply enough detail to interpret the Epoch 4 outcomes as a simple continuation of the randomized Epoch 3 comparison. Results from the first 24 weeks are the basis for the primary interpretation. Protocol details on eligibility, treatment adherence, participant flow, interim analyses, and deviations are not reported in the registry record, limiting evaluation of generalizability and robustness.

16. Related Tutorials

17. Related Statistical Calculators

18. Sources

• ClinicalTrials.gov: A Study to Evaluate the Change in Weight After 24 Weeks Treatment With LIK066 in Obese or Overweight Adults — NCT03100058.
• Registry record last updated 2020-02-06; status last verified 2020-01.
• Results first posted 2020-02-06.
• 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.

19. Record Summary

The registry record describes NCT03100058 as a completed randomized, triple-masked, parallel-group phase 2 dose-finding study sponsored by Novartis Pharmaceuticals. It enrolled 460 obese or overweight adults and evaluated eight LIK066 regimens against placebo during the first 24 weeks, followed by a further 24-week treatment period.

The primary endpoint was percent change from baseline in body weight at Week 24, analyzed in the Full Analysis Set. The posted group means were negative in all LIK066 arms, and the registry reports ANCOVA comparisons against placebo. The record also includes secondary outcomes, pharmacokinetic summaries, and adverse-event counts. The detailed multiplicity strategy, missing-data handling, original sample-size rationale, and full statistical model specifications are not reported in the registry record.