Polymyxin B is used as a last treatment resort for multidrug-resistant Gram-negative bacterial infections. The objectives of this study were to examine the population pharmacokinetics of polymyxin B and investigate factor(s) influencing pharmacokinetic variability. Four serial blood samples each were collected from 35 adult patients at steady state. The concentrations of individual polymyxin B components were analyzed using a validated liquid chromatography / tandem mass spectrometry assay and combined to derive total concentrations. A maximum likelihood expectation maximization approach was used to fit the data. Various demographic variables were investigated as potential covariates for clearance and volume of distribution (Vd) using linear regression analysis. A one-compartment model fit to the data satisfactorily (r2 = 0.96). The best-fit mean ± SD for clearance and Vd were 2.5 ± 1.1 L/h and 34.3 ± 16.4 L, respectively. Creatinine clearance was found to be a statistically significant covariate of clearance, but the magnitude was deemed clinically insignificant.