This page provides an independent statistical analysis and educational interpretation of publicly reported results. ClinicalTrials.gov provides the official trial registry record. Numerical trial results on this page are restricted to the results posted in the ClinicalTrials.gov record; calculations added by Clinical Biostats are labelled as such.
1. Trial at a Glance
This page covers the registry results for Play Intervention for Dementia for Promoting Cognitive Function: A Feasibility Study (NCT02846415), a randomized na study. The primary outcome is Adjusted Post-test Score of Montreal Cognitive Assessment Scale After 2 Months of Intervention.
| Feature | Registry value |
|---|---|
| ClinicalTrials.gov identifier | NCT02846415 |
| Phase | NA |
| Condition | Dementia, Alzheimer Disease |
| Allocation | Randomized |
| Design model | Parallel |
| Masking | Double |
| Enrollment | 30 |
| Arms in the primary outcome | n/a |
| Lead sponsor | The Hong Kong Polytechnic University |
| Results posted | Yes |
2. Clinical Question
Population
People with early to moderate dementia. The listed conditions are dementia and Alzheimer disease.
Intervention
Play Intervention for Dementia, a programme described as 12 weekly sessions, each lasting 45-75 minutes.
Comparator
A wait-list control group receiving usual day-care-centre care, including health and social services and meals.
Primary question
What were the adjusted post-test mean scores on the Montreal Cognitive Assessment Scale after 2 months of intervention, accounting for baseline scores?
The study asks whether cognitive-function scores differ after the intervention period between participants assigned to the play programme and participants assigned to the wait-list group. The primary measure is the Hong Kong version of the 11-item Montreal Cognitive Assessment scale. It assesses global cognitive function, with scores ranging from 0 to 30; lower scores refer to lower levels of cognitive function.
This is identified as a feasibility study, and the record describes a cluster randomized controlled trial conducted at two study sites. The brief description says participants would be allocated to intervention or wait-list groups, with both groups receiving the same programme at different times. The registry record does not report the primary outcome estimates, a between-group contrast, or uncertainty around any contrast. It therefore does not establish from the posted results whether the groups differed on the primary measure, or how precisely any difference was estimated.
3. Trial Design
The registry classifies this study as randomized, double-masked, and parallel, and the brief description calls it a cluster randomized controlled trial at two study sites. The listed enrollment is 30. The brief description says the study aimed to recruit 38 participants, so the record gives both a listed enrollment and a different recruitment target. It does not explain the relationship between those figures or identify how many participants completed each assessment.
The intervention was Play Intervention for Dementia. The description specifies 12 weekly sessions lasting 45-75 minutes each, facilitated by a play specialist, trained elderly volunteers, and centre staff. Participants assigned to the wait-list control group were described as receiving usual day-care-centre care, including health and social services and meals. The groups were to receive the same programme at different times. The record does not report the timing or details of that later programme delivery.
The primary outcome was the adjusted post-test score on the Montreal Cognitive Assessment Scale after 2 months of intervention. The secondary outcomes were adjusted post-test scores for the Fuld Object Memory Evaluation total storage score and the Modified Verbal Fluency Test. A trained research assistant, described as blinded to group allocation, was to assess cognitive function. Centre staff not involved in the programme were to be interviewed, and every alternate session was to be video-taped to understand participants’ experience. Those interviews and recordings describe planned qualitative work; the registry record does not report their findings.
The study is marked completed, with a primary completion date of 2017-04-30. The record does not report the randomization procedure, the unit assigned within the cluster design, or any cluster-level allocation details.
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
| Stage | PID Group | Wait-list Control Group |
|---|---|---|
| STARTED | 18 | 12 |
| COMPLETED | 15 | 11 |
| NOT COMPLETED | 3 | 1 |
Reasons for not completing this period:
| Reason | PID Group | Wait-list Control Group |
|---|---|---|
| Lost to Follow-up | 2 | 0 |
| Withdrawal by Subject | 1 | 1 |
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.
| Characteristic | Unit | PID Group | Wait-list Control Group | Total |
|---|---|---|---|---|
| Participants analysed | 18 | 12 | 30 | |
| Age, Continuous | years | 81.1 (SD 7.41) | 85.3 (SD 6.56) | 83.2 (SD 7.18) |
| Sex: Female, Male: Female | Participants | 13 | 9 | 22 |
| Sex: Female, Male: Male | Participants | 5 | 3 | 8 |
| Race and Ethnicity Not Collected | Participants | — | — | 0 |
| Region of Enrollment: Hong Kong | participants | 18 | 12 | 30 |
| Marital status: Married | Participants | 7 | 5 | 12 |
| Marital status: Single/Divorced/Widowed | Participants | 11 | 7 | 18 |
| Educational level: No formal schooling/primary | Participants | 12 | 10 | 22 |
| Educational level: Secondary/tertiary | Participants | 6 | 2 | 8 |
6. Primary Endpoint
The registry lists the primary outcome as Adjusted Post-test Score of Montreal Cognitive Assessment Scale After 2 Months of Intervention, measured over At Baseline, after 2 months (T1).
| Element | Registry entry |
|---|---|
| Result type | Mean |
| Measure of spread | 95% Confidence Interval |
| Unit | score on a scale |
| Endpoint classification | Continuous Endpoint |
The primary endpoint is the adjusted post-test mean score on the Hong Kong version of the 11-item Montreal Cognitive Assessment scale after 2 months of intervention. The scale measures global cognitive function. Scores range from 0 to 30, and lower scores refer to lower levels of cognitive function.
The record says the post-test scores were adjusted using baseline measures as a covariate in ANCOVA. In general, adjusting for baseline can account for starting scores when comparing post-test outcomes, rather than treating post-test scores as if all participants began at the same level. The adjusted mean describes the model-based average score for a group after that baseline adjustment. The registry record does not state the exact model specification beyond the baseline covariate and ANCOVA description.
A continuous score can retain information across its scale, rather than reducing each participant to a simple category. Its interpretation still depends on the score distribution, the reliability of measurement, and the contrast between groups. The record identifies the measurement instrument and the direction of scoring, but does not report the adjusted group means, a between-group estimate, a confidence interval, or a p-value. Without those results, the size and precision of any observed difference cannot be assessed from the registry record.
7. Why No Re-analysis Is Shown
8. Statistical Interpretation
The registry record identifies the primary outcome and says that adjusted post-test means were to be estimated using ANCOVA with baseline scores as a covariate. It does not report the adjusted means or a direct comparison between the randomized groups. Consequently, the posted record does not quantify the primary outcome result. There is no reported estimate from which to describe the direction, size, or precision of a between-group difference.
The record also does not report a confidence interval or p-value for the primary outcome. A confidence interval would communicate the range of values compatible with the estimated contrast under the analysis assumptions. Without an estimate and interval, readers cannot judge how much uncertainty surrounds the result. The absence of a reported p-value likewise means there is no registry-record basis for describing a statistical test result. It would be inappropriate to infer an outcome from the trial title, aims, or planned analyses.
The measure is a cognitive-function score for which lower scores refer to lower cognitive function. This direction helps interpret a reported score, but it does not substitute for group estimates or a between-group contrast. Even if group means were available, interpretation would need to consider their uncertainty, the baseline adjustment, the cluster design, and the number of participants contributing outcome data. The record does not report those participant counts by analysis or explain how clustering was handled in the primary analysis.
The registry lists two additional adjusted post-test outcomes: the Fuld Object Memory Evaluation total storage score and the Modified Verbal Fluency Test. It does not provide their results. It also describes staff interviews and video recordings intended to help understand participants’ experiences, but no qualitative findings are reported. Thus, the available record outlines measures and planned data collection, not a complete account of outcome evidence.
The study is described as a feasibility study. That designation places the stated purpose in context, but the record does not report feasibility measures or thresholds, such as recruitment or retention targets, or results on those measures. Nor does it report a sample-size justification. The enrollment listing and recruitment aim are not, by themselves, evidence about precision or feasibility outcomes.
In general, a result from a cluster randomized trial needs analysis that recognizes the way participants were grouped for assignment. The record explicitly indicates that a simple individual-level re-analysis would be misleading and that only the sponsor’s own analysis is shown. No such analysis estimates are included in the registry record, however. There are therefore no sponsor results to interpret and no basis for independently recalculating them. The central statistical conclusion is limited: the study’s outcome definitions and intended adjustment are documented, while its numerical outcome findings are not reported in the registry record.
9. Statistical Methods Explained
The methods described in the registry record include random allocation, a parallel comparison, baseline-adjusted post-test means, and a cluster randomized design. The record does not provide the numerical outcome analyses. The explanations below describe the general statistical ideas behind the stated methods; they do not fill in missing protocol details or results.
What does random allocation contribute?
In general, random allocation is intended to make comparison groups similar, on average, with respect to both measured and unmeasured characteristics at the time of assignment. It does not guarantee that the groups will be identical, particularly in a small study. The registry says this was a randomized study and describes a cluster randomized controlled trial at two sites. It does not report how the random sequence was generated, how assignments were concealed, or precisely which units were randomized. Those details are not reported in the registry record.
Why does the cluster design matter?
In general, participants within a cluster may have more similar outcomes to one another than to participants in other clusters. An analysis that treats every participant as wholly independent can therefore understate uncertainty when assignment or delivery occurs by cluster. Appropriate methods account for the clustering structure. The registry’s own note warns that a simple individual-level re-analysis would be misleading and says only the sponsor’s own analysis is shown. The record does not describe the sponsor’s method for accounting for clusters, identify the cluster allocation unit, or report cluster-level counts. A reader cannot verify those aspects from the registry record.
What does baseline adjustment mean?
The primary outcome is described as an adjusted post-test mean, with the baseline measure included as a covariate in ANCOVA. In general, ANCOVA estimates post-test group means while accounting for baseline values. This can improve the relevance of a group comparison when baseline scores are related to post-test scores, and it can address chance baseline imbalances in the model. The adjustment does not itself show that groups differed, and it does not eliminate the need to report the estimates and their uncertainty. The registry does not report the fitted coefficients, adjusted means, contrast, confidence interval, or p-value.
How should a confidence interval be read?
In general, a confidence interval describes uncertainty around an estimated quantity under the statistical model and its assumptions. For a between-group contrast, its position and width help readers assess the plausible range of differences compatible with the data and analysis. The primary outcome is described as having a 95% confidence interval, but no interval values are reported in the registry record. The confidence level alone does not show the interval’s width or where it lies, and it cannot be used to infer an outcome.
What can be said about planning illustrations?
The record describes a sample-size planning illustration based on a stated fraction of an observed effect, using a two-sided significance level of 0.05, equal allocation, and a normal approximation. It specifies that non-time-to-event illustrations would be expressed as participants per arm. The actual illustration values are not reported in the registry record. These are planning illustrations, not observed power, and they do not replace a prespecified sample-size justification. The record does not report a sample-size justification for this trial, the target effect used in its own design, or whether any planned design assumptions were met.
What is not specified about the analysis?
The registry record does not report whether the primary analysis followed intention-to-treat principles, how missing outcome data were handled, whether covariates beyond baseline were included, or what model diagnostics were assessed. It also does not report interim analyses or a statistical analysis plan. These details should not be inferred from the use of ANCOVA or from the outcome wording. The record lists no analysis entries, so there are no posted numerical estimates on which to conduct an independent check. General statistical concepts can clarify what methods are intended to do, but they cannot recover unreported trial results.
10. Multiplicity, Missing Data and Analysis Populations
The registry lists a primary cognitive outcome and two secondary cognitive outcomes. Considering several outcomes raises a general multiplicity issue: the more statistical comparisons that are made, the greater the chance that at least one result may appear notable by chance if each is interpreted in isolation. This is a general consideration, not a finding about this study. The registry record does not report whether multiplicity was addressed, whether the primary outcome was designated before analysis, or how secondary outcomes were to be interpreted. No adjustment method or testing hierarchy is reported.
The record describes the primary endpoint as a baseline-adjusted post-test mean and states that baseline scores were used as a covariate in ANCOVA. It does not report an analysis population, such as whether all randomized participants were included in the primary analysis, or how participants who did not complete follow-up were handled. Although the listed enrollment is 30 and the brief description gives an aim to recruit 38, the registry record does not state the number contributing data to each outcome or analysis.
Missing data can affect interpretation if outcome availability is related to group assignment or participants’ outcome values. In general, complete-case analysis, imputation, and other approaches make different assumptions; a reader needs the stated method and relevant counts to assess them. The registry record does not report missing-data methods, reasons for missing assessments, or sensitivity analyses. It also does not report whether all planned outcomes were collected or how deviations from the planned methods were handled. These omissions prevent assessment of potential selection effects and the robustness of the reported analysis; no outcome analysis estimates are reported to evaluate in the first place.
11. Safety Results
The registry reports serious adverse events as affected participants divided by participants at risk.
| Arm | Participants with serious adverse events | Participants at risk | Percentage |
|---|---|---|---|
| PID Group | 0 | 18 | 0.0% |
| Wait-list Control Group | 0 | 12 | 0.0% |
Deaths
| Arm | Deaths (participants affected of at risk) |
|---|---|
| PID Group | 0 of 18 |
| Wait-list Control Group | 0 of 12 |
Other (non-serious) adverse events
Participants with at least one non-serious event at or above the registry's 0% reporting threshold.
| Arm | Participants affected of at risk |
|---|---|
| PID Group | 0 of 18 |
| Wait-list Control Group | 0 of 12 |
The registry lists 0 serious adverse events among 18 participants at risk in the PID group and 0 among 12 participants at risk in the wait-list control group. It also lists 0 other adverse events among 18 participants at risk in the PID group and 0 among 12 participants at risk in the wait-list control group. Deaths are listed as 0 in each group, and no serious-event terms are listed.
These entries describe what is recorded in the registry, not proof that no adverse events occurred under every possible definition or that all events were captured. The record does not explain the adverse-event collection procedures, observation period, severity criteria, or completeness of reporting. The listed numbers at risk are the denominators used in the safety entries; the record does not give additional detail about exposure time or the timing of events.
Zero recorded events in these groups does not establish the absence of risk, and it should not be interpreted as a comparative safety estimate. With no events listed and no further information on surveillance or follow-up, the registry figures support only the narrow statement that no serious or other adverse events, and no deaths, are recorded for these groups.
12. What the Result Does, and Does Not, Mean
The record documents a randomized feasibility study of Play Intervention for Dementia and identifies a baseline-adjusted cognitive score as its primary endpoint. It also specifies a wait-list comparison and lists two secondary cognitive measures. These details help readers understand the question the study was designed to address and the outcomes chosen to assess it.
The record does not report numerical results for the primary or secondary outcomes. It therefore cannot support a conclusion about the direction or size of any group difference, the precision of an estimate, or whether an analysis met a statistical threshold. No effect estimate should be reconstructed from the study’s aims, design description, or outcome names. The registry record also does not report qualitative findings from staff interviews or video recordings.
The study’s feasibility label should not be taken as evidence that feasibility criteria were met: the record does not state such criteria or report results against them. The listed enrollment is 30, while the description says the study aimed to recruit 38 participants. Those figures describe the registry entry and recruitment aim; they do not provide a complete account of retention or outcome availability.
More generally, a randomized design can help structure a comparison, but design labels alone do not establish the quality or precision of the resulting evidence. Understanding the estimate would require reported analyses, uncertainty, participant flow, missing-data handling, and an account of how clustering was incorporated. Those details are not reported in the registry record. The appropriate interpretation is therefore limited to the documented study design, intervention, measurement plan, and safety entries—not a claim about whether the intervention changed cognitive function.
13. Why This Trial Matters Statistically
This trial is statistically notable because its design is described as cluster randomized, while the outcomes are measured on individual participants. That combination matters for analysis: observations within a cluster may be related, and a method that ignores that structure can give misleading uncertainty. The registry explicitly cautions against simple individual-level re-analysis and says only the sponsor’s own analysis should be shown. This is a useful reminder that the unit of randomization and the unit of measurement are not always the same.
The primary outcome also illustrates the distinction between a raw post-test score and an adjusted estimate. The record specifies baseline adjustment through ANCOVA, which can make the comparison account for participants’ starting scores. For readers, the model description is helpful, but it is not enough to judge the result without adjusted estimates and their uncertainty. Those numbers are not reported in the registry record.
The entry further distinguishes a feasibility study from a definitive efficacy analysis in its stated purpose, while leaving feasibility results unreported. The record lists both an enrollment figure and a larger recruitment aim, and it identifies multiple cognitive outcomes. Without participant flow, outcome availability, and multiplicity details, the precision and completeness of any analysis cannot be evaluated.
Finally, the safety entries show how registry figures should be read in context. The counts are zero in both groups, but the record does not describe event ascertainment or follow-up sufficiently to treat those entries as a broad safety conclusion. Overall, the statistical importance lies in recognizing what the design and planned analyses imply, while keeping those implications separate from results that the record does not report.
14. 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 limitation for statistical interpretation is that the registry record does not report the numerical primary outcome results. Adjusted group means, a between-group contrast, a confidence interval, and a p-value are not reported. The secondary outcome results are also not reported. As a result, the magnitude, direction, and precision of the cognitive outcomes cannot be assessed from this record.
The design is described as cluster randomized, but the cluster allocation unit, number of clusters, and analysis method for clustering are not reported. The record warns that an individual-level re-analysis would be misleading, but does not provide details sufficient to evaluate how the sponsor handled the design. The study is identified as double-masked, while the brief description specifically states that the outcome assessor was blinded; the record does not explain who else was masked or how masking was maintained.
The record lists an enrollment of 30, whereas the description states an aim to recruit 38 participants. It does not explain this difference or report participant flow, retention, or the number assessed at each time point. Missing-data methods, analysis populations, and sensitivity analyses are not reported. Neither a sample-size justification nor details of interim analyses or a statistical analysis plan are reported.
Additional limitations include no reported multiplicity strategy for the primary and secondary outcomes, no reported qualitative findings, and limited information about adverse-event ascertainment and follow-up. These are omissions in the registry record; they do not establish that the trial did not use such procedures, only that they are not reported there.
15. Related Tutorials
16. Related Statistical Calculators
17. Sources
- ClinicalTrials.gov: Play Intervention for Dementia for Promoting Cognitive Function: A Feasibility Study — NCT02846415.
- Registry record last updated 2023-10-23; status last verified 2023-10.
- Results first posted 2020-12-03.
- 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.
Continue through the Clinical Biostats statistical pathway
Use this trial's endpoint as a starting point for deeper study of effect measures, confidence intervals, and sample-size planning.
18. Record Summary
NCT02846415 is a completed randomized, double-masked, parallel feasibility study sponsored by The Hong Kong Polytechnic University. It is described as a cluster randomized controlled trial at two study sites and compares Play Intervention for Dementia with a wait-list control group receiving usual day-care-centre care. The listed enrollment is 30; the study description states an aim to recruit 38 participants.
The intervention description specifies 12 weekly sessions of 45-75 minutes. The primary outcome is the baseline-adjusted post-test mean on the Hong Kong version of the 11-item Montreal Cognitive Assessment scale after 2 months. Secondary outcomes are adjusted post-test scores on the Fuld Object Memory Evaluation total storage score and Modified Verbal Fluency Test.
The record does not report numerical outcome analyses, missing-data methods, or analysis populations. It lists no serious or other adverse events and no deaths in either group. The study began on 2016-08-01 and has a primary completion date of 2017-04-30.