From the course: Meta-analysis for Data Science and Business Analytics
Unlock the full course today
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Raw mean difference
From the course: Meta-analysis for Data Science and Business Analytics
Raw mean difference
- [Instructor] When a meta analysis involves only one metric. Your task is often much easier. If all or many studies use such a metric, there's normally no need to standardize their effect sizes. If you're synthesizing the results of studies of a blood pressure medication, you could just take the average blood pressure in the studies for the treatment group and compare it to the average blood pressure in the control group. The point is, if everyone uses the same metric to measure an outcome, then it's already a standard. But when the outcome measured is arbitrary, such as one developed by the experimenter and you want to include different measures in a meta analysis, you usually need to work with a standardized effect size. Things are easiest when all the studies that you would like to synthesize, use the same metric. So, a set of studies of the effect of medication on blood pressure, very likely all report systolic and diastolic blood pressures measured as millimeters of mercury. As…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.