We illustrate empirically the use of return-based style analysis for domestic stock funds. We search the optimal style model according to the tracking errors, investigate the consistency of the fund style for the optimally selected model, and finally investigate the relationship between fund styles and their fund performance. We use weekly fund return data of domestic stock funds from January 2, 2002 to June 30, 2008, and do style analyses based on the various style indices. The major findings are as follows.
Firstly, we find that the style index models with constraint which in practice restricts short sale are better than those with no such constraint. Secondly, we find that the style index model which divides stock market with four categorized indices based on the dimension of size and book-to market and includes the bond market index is the most useful if they are evaluated based on the out-of-sample tracking errors. While adding the Fama-French 3 factors to the selected model does not improve the explanation power, adding the industry sector indexes improves the explanation power. Thirdly, we investigate the consistency of the fund style models and find that the better performing funds are more volatile in the change of the fund style. Fourthly, we find that, contrary to the expectation that the growth-oriented funds perform better than the value-oriented one, the fund performance and style are observed to be mixed. This finding shows that the fund styles are frequently changed according to their performances and market conditions.
