I am performing a systematic review of the literature and the data is stored as a table including the fields:
DISEASE, VIRUS, TISSUE, ASSAY.
I made a random effect model for each of the first three fields (that is: test the OR for disease x upon infection with virus y on z tissue). But further stratification by assay would be (a) cumbersome (too many groups) and (b) diluting (too few articles into each group).
Is there a statistical way to account for possible bias due to the assay?
I do not understand what your research question is. State it in PICO format if at all possible.
This article "Issues relating to confounding and meta-analysis when including non-randomized studies in systematic reviews on the effects of interventions" maybe useful to explore
https://pubmed.ncbi.nlm.nih.gov/26053537/
the question is: is an infection associated with disease in a given tissue? the problem is: does the type of assay introduce a bias?
Determining, from the questions available within the item bank, the best set of questions to use for studies with specific design features and subject topics requires sufficient epidemiological expertise to classify study designs, experience conducting systematic reviews, and familiarity with risk of bias rating. I think this the best way to reduce the confunding variables
Is confounding factors meaning contributory factors? I am doing a systematic review on occupational health issues. Have you completed your draft to submit?
- Badges
- Science topic
- Similar topics
- Microbiology
- Assays