What rigorous methods are there?
Experimental methods
The most rigorous methods are fully experimental methods, such as randomised controlled trials (RCTs) and these represent the “gold standard” in the field. In RCTs, a project – or even part of a project – is randomly assigned to a group of individuals, schools, communities or others and benefits from the project (“intervention group”). The second group receives access to the project or intervention at a later time or – as is the case with placebos – not at all (control group). The principle of (controlled) random assignment, similar to medical research, ensures the comparability of the two groups: for example, depending on the intervention, they will on be average the same age, in a similar state of health, ambitious, vulnerable or wealthy. This means that all post-intervention differences between the groups can be attributed to the project itself. A well-known example is cash transfers, which are disbursed to households in the target group if their children attend school.
Semi-experimental methods
If a purely experimental (random) assignment is not justifiable or feasible, semi-experimental methods can prove worthwhile. For example, comparison groups can be defined in line with threshold values of certain selection criteria (regression discontinuity design, RDD). Alternatively, a comparison between two similar groups can be made using the difference-in-difference method. Similar to an RCT, a single group then benefits from the project. An estimate is then used to determine the impact of the project based on the comparison.