Mutual funds classifications, often made by rating agencies, are very common and sometimes criticized. In this work, a three-steps pure statistical procedure for mutual funds classification is proposed. In the first two steps time series funds are characterized in terms of their degree of return and riskiness. In particular, the risk is defined starting from a particular kind of Threshold-GARCH aimed to describe minimum, normal and turmoil risk. In the second step, a clustering analysis, based on return and risk levels, is performed in order to obtain classes of homogeneous funds. An application to 75 European funds belonging to 5 different categories is given.
Clustering mutual funds by return and risk levels
LISI, FRANCESCO;
2009
Abstract
Mutual funds classifications, often made by rating agencies, are very common and sometimes criticized. In this work, a three-steps pure statistical procedure for mutual funds classification is proposed. In the first two steps time series funds are characterized in terms of their degree of return and riskiness. In particular, the risk is defined starting from a particular kind of Threshold-GARCH aimed to describe minimum, normal and turmoil risk. In the second step, a clustering analysis, based on return and risk levels, is performed in order to obtain classes of homogeneous funds. An application to 75 European funds belonging to 5 different categories is given.
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
