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.

Closer look at effect sizes

Closer look at effect sizes

From the course: Meta-analysis for Data Science and Business Analytics

Start my 1-month free trial

Closer look at effect sizes

- [Instructor] Let's take a closer look at the effect size. After all, it's the fundamental building block of meta-analysis. As an example, suppose that you were interested in determining whether behavior therapy is better than nothing at all when measured by something such as the Minnesota Multiphasic Personality Inventory, or MMPI. You collect two random samples of 20 subjects each and expose one of the samples to six months of behavior therapy. The other samples spend six months living life as usual. You can assume that you have taken the two samples from different populations. Those who will at some point receive behavior therapy and those who receive no psychotherapy at all. At the end of the six months, you give both groups the MMPI. Suppose there were a 10 point difference in the average scores of the two samples. If your statistical analysis told you that the resulting p value was, say, .05, then you might conclude that there was only one chance in 20, .05, that the two…

Contents