The effect of past successes on the probability of a current success: evidence from a natural experiment
利用国际象棋循环赛的随机配对数据，检验了连胜效应（过去成功增加当前成功概率）是否成立，结果发现该效应完全由选手实力差异解释，过去成功本身并无影响。
Abstract A theoretical prediction for performance in a tournament is that a player’s performance in a round can be affected by their results in previous rounds relative to those of the tournament leader. Such a momentum effect relates to the popular belief that in a competitive environment past successes can increases the probability of a current success. The momentum effect is empirically investigated with data from games of single round-robin chess tournaments. The effect is identified by exploiting that players were randomly assigned a number before the start of the tournament which determined for each round their opponent and colour of the pieces. The findings do not support a momentum effect and, moreover, show that the observed momentum in the data can be explained by differences in players’ strength. Furthermore, no empirical support is found for an effect of the outcome of the previous game on the outcome of a current game. Hence, the empirical evidence suggests that past successes per se do not affect the probability of a current success.