For predicting the standard absolute entropies of gaseous organic compounds, variable molecular connectivity index (m)chi'(k) and Ring parameter H, based on adjacency matrix of molecular graphs, variable atomic valence connectivity index delta'(i), and the numbers of chains (cycles) atomic of molecule n(i)(R), were proposed. The optimal values of parameters c, a, m(i), and y included in the definition of delta'(i), and (m)chi'(k) can be found by optimization method. When c = 0.91, a = 1.3, and y = 0.22, a good four-parameter model can be constructed from H and (m)chi'(k) by using the best subsets regression analysis method for the standard absolute entropies of gaseous organic compounds. The results show that the MLR method can provide an accurate model for the prediction of the standard absolute entropies of gaseous organic compounds. (C) 2011 Elsevier B.V. All rights reserved.