Rehabilitation in Primary Care: A Project to Maximize the Health Status of Adults With Chronic Illness: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Rehabilitation in Primary Care: A Project to Maximize the Health Status of Adults With Chronic Illness (NCT00229957), a randomized na study. The primary outcome is SF-36 Physical Component.

2. Clinical Question

The registry describes the study purpose as determining whether occupational therapy and physiotherapy delivered in a primary-care setting to adults with chronic illness are effective in improving health. The posted primary outcome focuses more narrowly on health-related quality of life, measured using the SF-36 Physical Component. Its scale ranges from 0 to 100.

This is a comparison of group averages at the reported assessment time, not a description of every participant’s experience. The intervention group had a reported mean score of 42.6, while the control group had a reported mean score of 43.1. The estimated mean difference, expressed as intervention minus control, was -0.5 units on a scale. The estimate describes the observed group contrast; by itself, it does not establish why the groups differed or whether an individual participant’s score changed.

The record does not report which people were masked, the exact intervention schedule, or a detailed definition of the primary analysis population. Those details are important when interpreting how the research question was implemented, and are not reported in the registry record.

3. Trial Design

The study is registered as a randomized, single-masked, parallel-group trial. The registry lists an enrollment of 303 and classifies the study phase as not applicable. The sponsor is Hamilton Health Sciences Corporation. The record marks the study as completed, with a start date of 2004-06 and primary completion in 2006-08.

The intervention is described in the registry as rehabilitation in primary care. Occupational therapy, physiotherapy and self-management are listed as behavioral interventions. The control group received usual care in primary care. The record does not give a fuller account of the content, frequency, duration or delivery of each intervention, nor does it say which party was masked. The label “single” does not identify the masked party in the registry record.

The primary outcome was the SF-36 Physical Component score at 15 months. The registry reports group means and standard deviations for the outcome: 42.6 with a standard deviation of 11.8 in the intervention group, and 43.1 with a standard deviation of 11.9 in the control group. The outcome denominators are 132 and 139, respectively. The record does not explain the difference between those denominators and the total enrollment, and does not report reasons for any difference.

Secondary outcomes listed include hospital service use; independence in activities of daily living and instrumental activities of daily living; functional limitations; falls and injuries; home falls and accident screening; self-management and self-efficacy; physical abilities, including strength and balance; and patient satisfaction. Although these outcomes are named, their results are not included in the posted results. The registry record does not report the original sample-size justification, detailed randomization procedures, or a fuller statistical analysis plan.

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 SF-36 Physical Component, measured over 15 months.

The primary endpoint is the SF-36 Physical Component score, reported as a mean on a scale from 0 to 100. The registry describes it as a measure of health-related quality of life and gives the assessment timeframe as 15 months. The posted results summarize the score for each group using a mean and standard deviation.

A continuous score retains information about the degree of a measured characteristic rather than reducing participants to categories. Comparing group means can therefore describe the average score difference at the chosen assessment time. The standard deviation describes how dispersed individual scores are around each group’s mean; it is not a measure of uncertainty in the estimated difference itself.

The SF-36 Physical Component is relevant to the stated study purpose because the registry frames the intervention as rehabilitation intended to improve health in adults with chronic illness. The recorded outcome provides a standardized way to assess a health-related quality-of-life dimension. However, the registry record does not report the population-specific eligibility details, the scoring direction, or a threshold for interpreting a change as important to patients. The score comparison should consequently be read as a difference in the reported scale values, not as a direct measure of clinical importance.

The endpoint description does not identify every component used to construct the score or explain how incomplete questionnaires were handled. Those details are not reported in the registry record.

7. Results Posted in the Registry

• Intervention Group: mean 42.60 versus 43.10 on control; difference -0.50 (95% CI -3.32 to 2.32), standardized effect d = -0.04; z-test p = 0.728.

8. Statistical Interpretation

9. Statistical Methods Explained

The primary outcome is continuous, and the registry reports a mean and standard deviation for each group. A mean is the arithmetic average of the recorded scores. A standard deviation describes the spread of participant scores around that average. The intervention-group mean was 42.6 with a standard deviation of 11.8; the control-group mean was 43.1 with a standard deviation of 11.9. These summaries describe the observed distributions in the participants included in the respective outcome summaries, but do not show the full distribution or identify individual values.

What does the mean difference represent?

The reported contrast is the intervention-group mean minus the control-group mean. Its estimate is -0.5 units on a scale. A negative value means the intervention-group mean was lower than the control-group mean in this comparison. This sign describes the direction of the numerical contrast only; the registry does not specify the score direction in a way that would support a judgment about the meaning of a higher or lower score.

A difference in means is expressed in the original score units, which makes the estimate directly interpretable on the SF-36 Physical Component scale. It is a group-level summary. It does not imply that every participant had a score difference of -0.5, and it does not describe within-person change unless a change score analysis is specifically reported. The registry record does not identify the comparison as an adjusted analysis or describe a model that accounts for baseline scores or other variables.

How should the confidence interval be understood?

A confidence interval gives a range of values compatible with the observed data under the assumptions of the statistical procedure. The reported 95% confidence interval for the mean difference is -3.322 to 2.322. In repeated use of a valid procedure under its assumptions, intervals constructed in this way would cover the underlying parameter at the stated rate. For this particular result, the interval is a measure of uncertainty around the estimated group difference; it is not a range containing a stated proportion of individual participants’ scores.

Because the interval extends across zero, the data do not establish a direction for the average difference. A confidence interval is more informative than a p-value alone because it displays a range of plausible estimates and their direction. Its interpretation still depends on the analysis being appropriate and on the assumptions and data handling being adequately addressed. Details of those procedures are not reported in the registry record.

What does the p-value say?

The unadjusted p-value is 0.728. In general, a p-value describes how compatible the observed data are with a specified null model, assuming that model and the analysis assumptions hold. It is not a measure of effect size, does not give the probability that the null hypothesis is true, and does not indicate the probability that the result will be reproduced. A comparatively large p-value does not prove that the groups are equivalent. An equivalence analysis requires a clinically justified margin and a suitable inferential procedure; neither is reported in the registry record.

The comparison is presented as a mean difference with a confidence interval and an unadjusted p-value. The record does not report whether the analysis was prespecified, whether it adjusted for baseline values or other variables, or how assumptions were checked. The posted group summaries alone do not establish those details.

Why do spread and uncertainty differ?

The standard deviations, 11.8 and 11.9, describe variability among participant scores. Uncertainty in the mean difference also depends on the outcome denominators and the analysis method. The standard error is a measure of the sampling uncertainty of an estimate, whereas the standard deviation characterizes variation in the data. They answer different questions and should not be used interchangeably.

In general, statistical methods may need to account for over-dispersion when observed variability exceeds what a chosen model expects. Such adjustments can affect standard errors and confidence intervals. The primary endpoint is analyzed as a continuous score in the posted summaries, and the registry does not report an over-dispersion adjustment or provide enough detail to assess model diagnostics. No claim about such an adjustment can be made from this record.

What analysis details remain unclear?

The registry record does not report the trial’s original sample-size justification, the planned primary analysis model, the handling of missing outcomes, the analysis population, or the role of any interim analyses. It also does not describe whether the reported comparison followed a prespecified plan. These omissions limit assessment of the inferential procedure and its assumptions. The posted summaries support a description of the reported group means and their estimated contrast, but they do not resolve these methodological uncertainties.

10. Confidence Intervals and Precision

The estimated mean difference is -0.5 units on a scale, and its 95% confidence interval runs from -3.322 to 2.322. The interval is the main indicator of precision for this comparison: it shows that the estimate is uncertain enough to be compatible with values on both sides of zero. The result therefore does not specify whether the intervention-group mean was lower or higher in the population represented by the analysis.

The endpoints also help show the range of effect sizes that remain compatible with the posted summary under the interval’s assumptions. They should not be read as predictions for individual participants, or as a guaranteed range for the true effect. Confidence intervals quantify statistical uncertainty, not all forms of uncertainty. For example, they do not address whether the registry fully describes the intervention, whether outcome data were missing, or whether the selected analysis was appropriate.

The group standard deviations were 11.8 in the intervention group and 11.9 in the control group. These values indicate variation in participant scores, not uncertainty around the mean difference. The outcome denominators were 132 and 139, but the record does not explain the relationship of those denominators to the total enrollment of 303. That missing information makes it difficult to assess the possible influence of incomplete outcome data.

The registry does not report a clinically important difference threshold for the scale. Consequently, the interval cannot be used to determine whether all, some or none of its compatible values would be important to patients. The safest statistical reading is that the posted estimate is close to zero, while the interval remains broad enough to leave the direction and practical importance unresolved.

11. Planning a Similar Trial: Sample Size

This is a planning illustration, not a re-evaluation of the original trial. It asks: if a new study wanted to detect a difference like the one observed, or a smaller one, how large would it need to be? It is deliberately not “observed power” of the finished trial, which is not a meaningful quantity.

The planning figures describe participants per arm, not total events. They are illustrations based on the observed effect, not the trial’s original design calculation. The planning assumptions are a two-sided significance level of 0.05, equal allocation between the two arms, and a normal approximation. The effect to detect is set at the stated fraction of the observed effect. The registry record does not report the assumptions used for the original trial design or its sample-size justification.

The 80% power column gives the illustrative number of participants per arm for a design with an 80% chance of detecting the chosen effect under the stated assumptions, if that effect is real and the model assumptions hold. The 90% power column gives the corresponding planning number for a 90% chance under those assumptions. These are prospective planning concepts: they do not describe the probability that the completed study detected an effect, and they are not observed power.

The rows use the full observed effect and smaller fractions of that observed effect. For planning for 100% of the observed effect, the figures are 8,820 participants per arm for 80% power and 11,807 participants per arm for 90% power. For planning for 75% of the observed effect, they are 15,679 and 20,990 participants per arm, respectively. For planning for 50% of the observed effect, they are 35,278 and 47,227 participants per arm, respectively.

The pattern reflects a general statistical principle: smaller effects are harder to distinguish from random variation, so detecting them with the same planned power requires more participants. These calculations are illustrations based on the observed estimate and stated assumptions. They should not be interpreted as a judgment about the trial’s design quality or as evidence about the chance that the trial’s result is correct.

12. How the Sample Size Is Derived

Power is the probability that a study of a given size rejects the null hypothesis when a specific true effect exists. It depends on four things: the effect to detect, the variability of the outcome, the significance level (here a two-sided α of 0.05, so z_1−α/2 = 1.960) and the desired power (z_1−β = 0.842 for 80% and 1.282 for 90%).

Formula

n is the number of participants in each arm, Δ is the difference in means to detect and σ is the common standard deviation.

Worked calculation for this trial

1. Observed difference Δ = -0.500; pooled standard deviation σ = 11.851.
2. n = 2 × (1.96 + 0.842)² × 11.851² / -0.500² = 8,819.4, rounded up to 8,820 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 <- -0.5                      # observed difference in means
sigma <- 11.8514065170015                     # 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(229957)
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 = 8,820 (80% power), 11,807 (90% power)
 75% of observed effect: n per arm = 15,679 (80% power), 20,990 (90% power)
 50% of observed effect: n per arm = 35,278 (80% power), 47,227 (90% power)
power.t.test: 8820.3 
Simulated power at n = 8,820 per arm: 0.801 (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.

13. Multiplicity, Missing Data and Analysis Populations

The registry lists secondary outcomes covering hospital service use; independence in activities of daily living and instrumental activities of daily living; functional limitations; falls and injuries; a home falls and accident screening tool; self-management and self-efficacy; physical abilities such as strength and balance; and patient satisfaction. Their results are not posted in the registry record. The posted results therefore do not provide a complete view of the outcomes named in the registration.

When a study assesses multiple outcomes or makes multiple comparisons, the chance of at least one apparently unusual result can increase. Statistical methods can address this multiplicity, for example by adjusting significance thresholds or by defining a hierarchy of outcomes. This is a general statistical concern, not a claim about a procedure used in this trial. The registry record does not report a multiplicity strategy, a hierarchy among outcomes, or whether the reported p-value was part of a broader family of tests.

The registry reports a total enrollment of 303 and primary-outcome denominators of 132 in the intervention group and 139 in the control group. It does not state how many enrolled participants were randomized, which participants were included in the primary analysis, or why the outcome denominators differ from enrollment. The analysis population is therefore not reported in the registry record.

The record also does not report the extent or pattern of missing primary-outcome data, the reasons for missingness, or the method used to handle missing observations. In general, missing-data methods rely on assumptions about why values are unavailable, and different assumptions can lead to different estimates. Without a reported approach, the potential influence of missing data cannot be evaluated from the registry summary alone.

Other analysis details not reported include whether baseline score adjustment was used, whether the analysis followed an intention-to-treat principle, whether there were interim analyses, and whether the posted analysis was specified in advance. These gaps limit assessment of the analysis plan and of how the primary result relates to all randomized participants and all registered outcomes.

14. Safety Results

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

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

The registry reports serious adverse events for 0 of 152 participants at risk in the intervention group and 0 of 151 participants at risk in the control group. It also reports 0 other adverse events in each group, with the same respective numbers at risk. These figures describe the adverse-event counts recorded in the registry for the stated groups and categories.

A count of zero in a posted category means no events were recorded for that category in the reported data. It does not establish that no events occurred outside the reporting period, that every possible event was captured, or that the groups have identical safety profiles. The registry record does not provide event definitions, the surveillance process, follow-up completeness, or additional detail about how events were assessed.

Deaths are listed as null for both groups. In this context, null means that a death count is not reported in the registry record; it should not be interpreted as a reported count of zero. No serious adverse-event terms are listed. The event figures should be read as registry reporting, not as a comprehensive evaluation of every possible safety outcome.

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

The primary outcome comparison reports similar group means at 15 months: 42.6 in the intervention group and 43.1 in the control group. The estimated difference was -0.5 units on a scale, with a 95% confidence interval from -3.322 to 2.322 and an unadjusted p-value of 0.728. Statistically, the posted estimate is close to zero, but the interval remains compatible with differences in either direction. The result does not establish that the groups are equivalent.

The finding concerns the average SF-36 Physical Component score at the stated assessment time. It does not establish what happened to each participant, whether scores changed from baseline, or whether another outcome differed. The registry lists additional outcomes, but their results are not posted. The record also does not report a threshold for a clinically important difference on this score, so the practical importance of values in the confidence interval cannot be determined from the registry information alone.

The study’s stated purpose concerned occupational therapy and physiotherapy delivered in primary care for adults with chronic illness. The registry also lists self-management as an intervention. The recorded outcome comparison is not a complete evaluation of all aspects of rehabilitation or all health consequences. Intervention details, analysis population, missing-data handling and the original sample-size justification are not reported in the registry record.

Accordingly, the posted result is best understood as a statistical description of the reported group means and their uncertainty, rather than a definitive claim about the effect of the intervention. It neither proves benefit nor proves absence of benefit. Interpretation also depends on design and analysis details that the registry record does not provide.

16. Why This Trial Matters Statistically

This trial illustrates why an estimate and its uncertainty should be read together. The point estimate, -0.5 units on a scale, is close to zero, but a point estimate alone would conceal how uncertain the comparison is. The confidence interval from -3.322 to 2.322 displays that uncertainty and leaves the direction unresolved. A p-value of 0.728 cannot replace that information, and it does not demonstrate equivalence.

The study also illustrates the difference between variability among people and precision about a group comparison. The reported standard deviations, 11.8 and 11.9, describe the spread of individual scores within groups. Precision for the estimated contrast is conveyed by its confidence interval. These quantities are related through the analysis but answer distinct questions.

Planning calculations based on an observed effect can also be easy to misread. The registry-derived illustrations give much larger participant requirements when planning to detect smaller fractions of the observed effect. That pattern reflects the general relationship between effect size and the amount of information needed for detection. These figures are planning illustrations, not evidence about the trial’s power after completion and not the original design justification.

Finally, registry results need to be interpreted alongside reporting completeness. The primary comparison is posted, while the secondary outcome results and important details about missing data, analysis populations and multiplicity are not. This limits what can be concluded from the record, even when the reported numbers themselves are clear. Distinguishing observed summaries, inferential uncertainty and unreported methods is central to a careful statistical reading.

17. 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 registry record gives limited detail about the intervention. It names occupational therapy, physiotherapy and self-management, and describes the study purpose as rehabilitation in primary care, but does not report the specific activities, intensity, duration or implementation. The control description is limited to usual care in primary care. This makes it difficult to assess how consistently the intervention was delivered or what services differed between groups.

The record identifies the trial as single-masked but does not say who was masked. It does not describe allocation concealment or the detailed randomization procedure. These design details are not reported in the registry record, so the potential for bias related to assignment or outcome assessment cannot be evaluated from the posted information.

The primary result includes group means, standard deviations and outcome denominators, but the record does not explain why the denominators differ from total enrollment or how missing outcomes were handled. It also does not state the analysis population, whether baseline adjustment was used, or whether the reported method followed a prespecified plan. These omissions limit assessment of how robust the estimate is to data handling and analysis choices.

The registry names secondary outcomes but does not post their results. It also does not report a multiplicity strategy, a clinically important difference threshold for the primary score, an original sample-size justification, or details about interim analyses. The primary comparison therefore cannot by itself support conclusions about all outcomes or settle the clinical importance of the estimated difference.

18. Related Tutorials

19. Related Statistical Calculators

20. Sources

• ClinicalTrials.gov: Rehabilitation in Primary Care: A Project to Maximize the Health Status of Adults With Chronic Illness — NCT00229957.
• Registry record last updated 2010-07-20; status last verified 2009-09.
• Results first posted 2010-07-07.
• 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.

21. Record Summary

NCT00229957 is a completed randomized, single-masked, parallel-group study sponsored by Hamilton Health Sciences Corporation. The registry lists an enrollment of 303, a start date of 2004-06 and primary completion in 2006-08.

The study examined rehabilitation in primary care for adults with chronic illness. Occupational therapy, physiotherapy and self-management are listed as behavioral interventions; the control group received usual care in primary care. The primary outcome was the SF-36 Physical Component score at 15 months.

The posted mean scores were 42.6 in the intervention group and 43.1 in the control group. The estimated mean difference was -0.5 units on a scale, with a 95% confidence interval from -3.322 to 2.322 and an unadjusted p-value of 0.728. The registry record lists secondary outcomes but does not post their results or report several analysis details, including missing-data handling and the analysis population.