A new method has been developed to describe the quantitative relationship between the octanol-air partition coefficients and molecular connectivity indexes of semivolatile organic compounds such as polychlorinated dibenzo-p-dioxins and dibenzofurans (PCDD/Fs), polychlorinated naphthalenes (PCNs), polycyclic aromatic hydrocarbons (PAHs), chlorobenzenes (CBs), polybrominated diphenyl ethers (PBDEs). The stepwise multiple linear regression was used to derive six equations with correlation coefficients greater than 0.99 except for PBDEs' (0.96). The largest relative error is 4.6%, and the standard deviation is less than 1.83 log units. Compared with the data obtained from the relevant experiments, the results of prediction are very accurate.