Style breaks in return-based style analysis
Faculty of Applied Economics
Antwerp :UA, 2002
Research paper / Faculty of Applied Economics UFSIA-RUCA ; 2002:019
University of Antwerp
Despite the wide acceptance of return-based style analysis, the method has several limitations. One important drawback is the underlying assumption that the style exposures do not vary over time. In general, little attention was devoted to examining whether this hypothesis is acceptable, although a number of studies have documented that time variation in style exposure does occur. We apply results on break tests established in Andrews and Ploberger (1994), Hansen (1997) and Bai and Perron (1998, 2001) to examine profoundly the possibility of style breaks. We find strong evidence against the hypothesis of constant time exposures in time in daily return data of European equity funds. All funds exhibit at least one break, while 60% of the funds exhibit even more than one break. The style breaks may be induced by economic motives or may be related to other factors such as changes in management structure. A comparison of the number of breaks in the standard style analysis and an extended model where one additional variable capturing an economic motive is added, reveals that the most promising pursuit for explaining (the majority of) style breaks is to be found in economic motives.