We used Poisson regression with robust error variance41 to assess the association between metformin use and severe dengue manifestations, adjusting for potential confounding variables.
This association persisted after controlling for potential confounding variables including severe pre-eclampsia and cesarean delivery (AOR 3.69, 1.13 to 11.99).
We found that exceedingly low concentrations of lead in dust, soil and water were significant predictors of children's BLLs, after adjustment for potential confounding variables.
These associations remained statistically significant after adjustments for potential confounding variables, including age, race, socioeconomic status, health status, and health behavior.
Finally, LISREL analysis was performed to control for potential confounding variables.
There was insufficient power to correct for multiple comparisons or to covary for potential confounding variables.
In addition, binary logistic regression was used to adjust for potential confounding variables.
Food insecurity was also associated with uncontrolled eating (p ≤ 0.05), but the relationship was attenuated when controlled for potential confounding variables.
Comparisons of outcomes for the SIP were adjusted for potential confounding variables of the patient characteristics as well as their specific injuries [4].
A logistic regression model was adjusted for potential confounding variables and fitted to determine factors that were predictive of ICU readmission, prolonged ICU stay, and mortality.
This study evaluated the association of EDS with migraine and headache frequency in a general population, after adjusting for potential confounding variables.
