Often i have confusion in describing study and can not differentiate between types of studies for example cross-sectional , retrospective study , longitudinal and descriptive study ....... etc.
Which of the is used for diagnostic test evaluation and which for prevalence of certain microorganism or disease.
Could you please help this really matter of confusion.
Dear Ahmed,
The classical classification of epidemiological studies has been done in relation to a causal hypothesis (the relationship between a putative cause "A" and an effect "B") and what kind of design is used for researching phenomena.
These "causal studies" are classified according to the causal temporal direction:
1. Cross-sectional studies: You are not sure about the direction of the relationship between A and B.
2. Looking forward: Cohort studies and intervention trials.
3. Thinking backward: Case-control studies.
Also, they are classified according to the temporal logistics of the study as:
a. Retrospective.
b. Prospective or Longitudinal.
c. Mixed.
The full classification mixes both axes, e.g. Retrospective cohort study.
Please, see:
Grimes, David A., and Kenneth F. Schulz. "An overview of clinical research: the lay of the land." The lancet 359, no. 9300 (2002): 57-61.
Pearce, Neil. "Classification of epidemiological study designs." International journal of epidemiology 41, no. 2 (2012): 393-397.
On the other hand, there are studies about diagnostic and screening tests. The main idea is testing the performance of a test or procedure. There are several study designs, most of them cross-sectional and retrospective, i.e. the researcher already knows the results of the test and the gold standard.
Please see:
Pepe, M.S., 2003. The statistical evaluation of medical tests for classification and prediction. Oxford University Press.
Zhou, Xiao-Hua, Donna K. McClish, and Nancy A. Obuchowski. Statistical methods in diagnostic medicine. Vol. 569. John Wiley & Sons, 2009.
Best regards.
Andrés.
Thanks Andres
I often use ROC curve and its calculation for evaluation of certain test against known gold standard and i think cross-sectional study is more suitable in this case .
I will check the references in your reply
- Badges
- Science topic
- Similar topics
- Biological Science
- Microbiology
- Microorganisms