A CHANCE-CONSTRAINED APPROACH TO STOCK SELECTION IN HONG-KONG

To deal with the uncertainty of models a stochastic programming techni que, chance-constrained programming, developed in 1959 by Charnes and Cooper, is employed to modify, the classical model of Markowitz so tha t it is more realistic. Chance-constrained programming does not requir e that a constraint should always hold but only be satisfied with a gi ven probability. In this paper the Markowitz model is first modified w ith the chance-constrained programming technique by determining the ra ndomness that exists in the average rates of return of stocks. This mo dification requires the assumption of the normal distribution of retur n rates to find an estimator of the variance of the portfolio. Then th e modified model is run for four satisfaction levels: 99, 95, 90 and 8 5%, together with the classical one, at different required rates of re turn.