Overadjustment bias and unnecessary adjustment in epidemiologic studies.
However, mental attitude may alter the time course of disease processes and influence health behaviors directly, so the possibility of
overadjustment exists and we may be adjusting for the effect of intermediate factors in the causal pathway.
There are two types of risk: the infra-adjustment that indicates that the model does not have enough information to predict samples and the
overadjustment that indicates that the model has a lot of information that is not useful.
First, there is
overadjustment when the data have not been prepared well, and there are data with erroneous or poorly conditioned input information.
As a comparison, the Whitehall study adjusted for 3 confounding factors [10] so
overadjustment cannot be ruled out in the current study.
To avoid
overadjustment, the only variables added to the model were those that were significant predictors of a secondary event at an a-level of 0.1 or that changed the parameter estimates for the main variables (galectin-3) by more than 10%.
Therefore, using this line item to offset related party holdings may generate an
overadjustment.
You can never prove cause and effect with observational studies, and it would be a mistake to make meaningful conclusions from this study due to its observational nature and possible
overadjustment of the data.
Finally, the statistical adjustment procedures applied to HIV surveillance data to account for reporting delay are subject to a degree of uncertainty (1), which could result in
overadjustment or underadjustment of the data.