Our meta-analysis app allows you to conduct your own meta-analyses online using our data.
First, select a program that you would like to examine. We currently have data for ten programs. These initial topics were selected through a Kickstarter campaign. Any study that appears to be an impact evaluation of the effects of that program is included; as you can see by reading more about our meta-analyses, we are purposefully not restrictive. By including a lot of information about each study, we allow you to narrow down the programs at a later step – for example, choosing to focus on only those school meals programs that were fortified with iron.
Second, select an outcome variable. The outcome variables available will depend on the program selected, as not every outcome variable is relevant to every program.
Third, select your filters and whether you would like to use fixed or random effects. Currently, our app can handle whether a study was a randomized controlled trial and whether it was blinded. We presently have data on 60 other filters, but adding these will take additional work on the back end. Check back later or get in touch to be notified when more filters are added.
Caution! Be sure to make sure you are selecting your desired filters the first time – don’t go back afterwards and try to change your filters. Read why.
What are fixed or random effects? A meta-analysis makes an assumption about the state of the world, and our app lets you choose which you would prefer to make. Fixed effects are the default choice for if you think that there is one true effect that the program has in different contexts. Random effects are used if you think there is a distribution of effects. Ultimately, your results should not depend too much on which you have selected.
As you make your selections, check how many studies are included in the bottom right. There is a trade-off to be made: the less restrictive your filters, the more studies will remain selected under those filters.
Understanding your results: The output that is displayed shows the point estimate of the meta-analysis (the middle dot) as well as the upper and lower bounds of the 95% confidence interval around that estimate (the vertical ends on the horizontal bar). If you mouseover any of those points, you will see more detail.