Premium
Optimal Portfolio Selection and Cutoff Rates of Security Performance: A Multi‐Index Case *
Author(s) -
Kwan Clarence C. Y.
Publication year - 1988
Publication title -
decision sciences
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.238
H-Index - 108
eISSN - 1540-5915
pISSN - 0011-7315
DOI - 10.1111/j.1540-5915.1988.tb00294.x
Subject(s) - portfolio , cutoff , portfolio optimization , normality , computer science , mathematical optimization , robustness (evolution) , modern portfolio theory , selection (genetic algorithm) , property (philosophy) , index (typography) , variance (accounting) , econometrics , mathematical economics , mathematics , economics , statistics , finance , artificial intelligence , physics , chemistry , philosophy , accounting , quantum mechanics , world wide web , biochemistry , epistemology , gene
ABSTRACT The present study performs portfolio analysis using a multi‐index model in the diagonal form. In a mean‐variance framework, an alternative solution to a portfolio optimization problem is derived, providing analytical and computational improvements. This leads to a proof of a crucial functional property of cutoff rates of security performance in the solution, thus providing formal justification for a nonranking procedure of optimal portfolio selection. The robustness of the above functional property, and hence the nonranking procedure, is demonstrated numerically when the underlying normality assumption of security returns is replaced by a more general assumption of stable Paretian distributions.