Source: Chemist; Public Domain http://openclipart.org/detail/8959/woman-chemist-by-gerald_g-8959
This tutorial is going to teach you about mete-analysis. Now, meta-analysis is different than performing a regular experiment. With a regular experiment, someone decides that they're going to perform the experiment, they collect data from it, and they analyze it. And that's where the story ends.
But what if someone else does a similar experiment? Maybe their analysis and their data are similar to the first one, or maybe they're different, or maybe they're even contradictory? And what if someone else does a third experiment and they get different data, as well? Well, sometimes it's useful to pull all those analyses from the different experiments together and put them into a single document. That's called meta-analysis, where you take all of the previously done work and try and synthesize it.
So, meta-analysis is the process of gathering the data from multiple different experiments that multiple different people have done. In meta-analysis, the goal is not to analyze data, itself. It's to look for overall trends within the experiment. And the nice thing about meta-analysis is if the experimental designs were similar between the experiments that were done, we can, in theory, combine the results to have a more powerful result because of the larger sample size.
Essentially, you're pooling all the sample sizes from the previous experiments that were done. This increases the replication, and we saw earlier that the more you increase replication, the more powerful the result is going to be because you can see overall trends that you might have missed in smaller experiments.
And so, to recap, meta-analyses piggyback off stuff that's already been done before. The goal is to find overall trends in the data, not to produce data yourself. And the goal is to be able to combine the results of some experiments to find some larger trend and be able to confirm it. And then the terms that we used were meta-analysis. Good luck and we'll see you next time.
The practice of gathering data from several similar studies to look for overall trends in the data that the studies may have overlooked individually.