I am just taking a guess but Experimental investigations allow you to isolate variables (making most variables constant, allowing only the independent variable to have an impact on the dependent variable). With other scientific investigations, if they don't isolate the variables it is very possible that an unknown third variable could be skewing the results (which will result in correlation but not causation).
Experimental investigations are the best type of scientific investigation to demonstrate cause-and-effect relationships because they allow the investigator to actively manipulate variables and control conditions. The independent variable can be isolated and manipulated, producing a change (or no change) in the dependent variable. This change can be measured to gather evidence to support or refute the cause-and-effect relationship. Experimental investigations also use a control group (a group that does not receive the factor being tested) for comparison.
