Which Studies Produce the Strongest Scientific Evidence

Which Studies Produce the Strongest Scientific Evidence

Studies producing the strongest scientific evidence

Depending on what type of study researchers chose to perform, the strength of the collected evidence varies. This image doesn’t depict every single type of study but it does separate studies that provide the strongest scientific evidence from those producing weaker evidence.

Which Studies Produce the Strongest Scientific Evidence

Double Blind Placebo Controlled

Technically this study belongs to randomized controlled trials (RCTs) but I wanted to highlight this specific one since it’s so common (and good).

In these types of studies people are randomly assigned to either the control group, receiving placebo, or the treatment group. Treatment might be a drug, an intervention or a dietary supplement, just to mention a few examples. The key here is that neither the researcher or patients are aware of what group they’ve been placed. This is done to ensure that no form of conscious or subconscious bias will affect the outcome of the study. Double blind placebo controlled studies provide strong evidence but they can’t always be performed since some treatments can’t be blinded. This is the gold standard of scientific evidence.

Prospective Cohort

In these types of studies researchers follow cohorts, groups of people, from the onset of a study. The aim is to compare two similar group of people who differ in only one or a few aspects to find if this difference is the cause of a disease or condition. One example would be looking at two groups of female nurses, smokers and non-smokers, to see if there’s a link between smoking and lung cancer.

Retrospective Cohort

Still comparing similar groups of people, but here you don’t follow people from the start of the study, instead you study data from a time-period. As an example; you might have data on female nurses between 1976 and 1990 and know both the rate of lung cancer and who of the nurses were smokers, in this type of study you could analyze the data set to find see if there’s a correlation between the cause and effect. The advantage of this type of study is that the data is already collected, the study only takes as long as the analysis of the data.


In this type of study researchers find a group of people with a disease or condition, the cases, and compare them with a similar group of people not affected by the same conditions, the controls. This type of study are relatively inexpensive and might be undertaken to find the cause of a rare disease or condition. Though it might be useful in order to study rare conditions, but the scientific evidence is fairly weak.