Selected individuals in recurrent selection usually have equal fitness, i.e., they contribute the same number of progenies to the next cycle of selection. Our objective was to determine if varying the fitness of selected individuals increases the response to recurrent selection. We developed and evaluated an optimum method (Unequal Fitness) and a simplified method (Better Half) for determining the appropriate fitness of selected individuals. By computer simulation we found that if the number of selected individuals (N Sel) is constant, the short-term response (cycles 1-5) to phenotypic recurrent selection was generally higher with the Better Half and Unequal Fitness methods than with the Equal Fitness method. In practice, however, breeders would find it easier to change NSel than to manipulate the fitness of selected individuals. Reducing NSel often negated any short-term advantage of the Better Half and Unequal Fitness methods. Likewise, the Better Half and Unequal Fitness methods were not advantageous in marker-assisted recurrent selection, which is a short-term procedure. Across different NSel values, the Better Half and Unequal Fitness methods were superior to the Equal Fitness method for medium- and long-term phenotypic recurrent selection (cycles 6-30). We recommend the Better Half method over the Unequal Fitness method because of its simplicity and because it remained superior to the Equal Fitness method over more cycles of selection. As a rule-of-thumb, we suggest that NSel should be roughly equal to the number of cycles for which selection will be conducted. This rule of thumb leads to NSel values lower than those typically used in selection programs.