Experimental studies that show something is safe or improves outcomes should, by definition, have something to compare the new treatment against. If they don’t, it’s hard to know if the new treatment is a better option or not.
Control groups can come in several varieties:
No Treatment Group – Researchers would compare the outcomes with the group that got the treatment with the group who did not.
Placebo Group – sometimes just the act of taking a pill (or any other treatment) can make people think they’re getting better. Studies with a placebo control group would try to figure out if the differences between groups was the active ingredient, as both groups would experience the effects of just taking a pill each day.
Existing Treatment Group – sometimes, letting a group go untreated is ethically problematic. Say you want to research a new drug for preeclampsia. When you go to test it, you can’t ask study participants who are developing pre-eclampsia to be randomized to either get an untested medication or no treatment. Ethically, you would need to test the new treatment against existing treatments so that no one is asked to go untreated for a very serious condition.
Some studies might have multiple groups acting as a control for each other.