Skip to main content

Table 3 Summary of planned primary, secondary and sensitivity analyses

From: Varied overground walking-task practice versus body-weight-supported treadmill training in ambulatory adults within one year of stroke: a randomized controlled trial protocol

Objective/Variable

Hypothesis

Outcome measure (type)

[continuous (c), binary (b)]

Method of Analysis

1) Primary

   

Walking speed at post-intervention (T2)

MLWP > BWSTT

Comfortable gait speed (c)

ANCOVA

2) Secondary (T2, T3)

   

Secondary outcomes

   

a) Fast walking speed

MLWP > BWSTT

Fast Gait Speed (c)

ANCOVA

b) Walking endurance

MLWP > BWSTT

Six minute walk test(c)

ANCOVA

c) Balance and walking related self-efficacy

MLWP > BWSTT

Activities-specific Balance Confidence Scale (c)

ANCOVA

d) Dynamic balance

MLWP > BWSTT

Functional Balance Test(c)

ANCOVA

e) Mobility participation

MLWP > BWSTT

Life Space Questionnaire (c)

ANCOVA

f) Health-related quality of life

MLWP > BWSTT

Stroke Impact Scale 3.0 (c)

ANCOVA

g) Goal attainment

MLWP > BWSTT

Patient Specific Function Scale(c)

ANCOVA

h) Walking participation

MLWP < BWSTT

Mean daily step activity

ANCOVA

i) Training staff requirement

MLWP < BWSTT

Total number of trainers/number of training sessions (c)

T-test

j) Meaningful change in gait speed of ≥ 0.14 m/s

MLWP > BWSTT

Comfortable gait speed change score T2-T1 ≥ 0.14 m/s)(b)

Chi-square test

Adverse events (count)

   

a) Falls during session

 

Therapist report (b)

Chi-square test

b) Injury during session

 

Therapist report (b)

Chi-square test

c) Falls between session

 

Patient report (b)

Chi-square test

d) Myocardial Infarction

 

Patient report/health record (b)

Chi-square test

e) New stroke

 

Patient report/health record (b)

Chi-square test

f) Hospitalization

 

Patient report/health record (b)

Chi-square test

g) Death (all causes)

 

Health record/Physician (b)

Chi-square test

3) Sensitivity Analysis

   

a) All outcomes analysed simultaneously to account for correlation among them

 

Primary and secondary outcomes

MANOVA

b) Serial correlation of all outcomes at baseline, T2, T3

 

Primary and secondary outcomes

GEE

c) Completers (≥ 12 sessions)

MLWP > BWSTT

Comfortable Gait speed

ANCOVA

  1. IMPORTANT REMARKS:
  2. The GEE2 is a technique that allows to specify the correlation structure between patients within a hospital and this approach produces unbiased estimates under the assumption that missing observations will be missing at random. An amended approach of weighted GEE will be employed if missingness is found not to be at random3.
  3. In all analyses results will be expressed as coefficient, standard errors, corresponding 95% and associated p-values. Goodness-of-fit will be assessed by examining the residuals for model assumptions and chi-squared test of goodness-of-fit
  4. Tukey's HSD method will be used to adjust the overall level of significance for multiple secondary outcomes
  5. 1Perera S, Mody SH, Woodman RC, Studenski SA. Meaningful change and responsiveness in common physical performance measures. Journal of American Geriatrics Society 2006. 54: 743-749.
  6. 2Hardin JW. Generalized Estimating Equations. New York: Chapman and Hall/CRC, 2001
  7. 3 Diggle PJ, Liang K-Y, Zeger S. Analysis of Longitudinal Data. Oxford: Oxford Science Publications, 1994.