Article type
Year
Abstract
Objectives:
To describe how to use an innovative approach to addressing missing participant data for dichotomous outcomes in systematic reviews of randomized trials.
Description:
The workshop will consist of the following:
1. A didactic presentation of methods being used by Cochrane and non-Cochrane systematic reviews for dealing with and judging risk of bias associated with missing participant data (5 min).
2. An interactive presentation of the proposed approach: for the primary analysis, we propose either a complete-case study or making plausible assumptions about the outcomes of participants with missing data. The sensitivity analyses may use relatively extreme assumptions about the plausibility and outcomes of participants with missing data. More plausible assumptions draw on the outcome event rates within the trial or in all trials included in a meta-analysis. We will also discuss how to judge risk of bias associated with missing participant data using this approach (25 min).
3. A hands-on exercise will cover conducting primary and sensitivity analyses (using an Excel sheet), and judging the risk of bias. Participants may bring their own data or use data provided by facilitators (40 min).
4. An open discussion of the advantages and limitations of the proposed approach (20 min).
Note: This workshop will not be held in a computer lab. Participants may bring laptops to allow hands-on participation.
To describe how to use an innovative approach to addressing missing participant data for dichotomous outcomes in systematic reviews of randomized trials.
Description:
The workshop will consist of the following:
1. A didactic presentation of methods being used by Cochrane and non-Cochrane systematic reviews for dealing with and judging risk of bias associated with missing participant data (5 min).
2. An interactive presentation of the proposed approach: for the primary analysis, we propose either a complete-case study or making plausible assumptions about the outcomes of participants with missing data. The sensitivity analyses may use relatively extreme assumptions about the plausibility and outcomes of participants with missing data. More plausible assumptions draw on the outcome event rates within the trial or in all trials included in a meta-analysis. We will also discuss how to judge risk of bias associated with missing participant data using this approach (25 min).
3. A hands-on exercise will cover conducting primary and sensitivity analyses (using an Excel sheet), and judging the risk of bias. Participants may bring their own data or use data provided by facilitators (40 min).
4. An open discussion of the advantages and limitations of the proposed approach (20 min).
Note: This workshop will not be held in a computer lab. Participants may bring laptops to allow hands-on participation.