Answers are grounded in this paper and cite their sources.
It is shown that the kurtosis parameter K for a continuous p-variate elliptical distribution with real positive-definite covariance matrix Ω must be strictly greater than −2/(p+2).
No takes yet. Share an insight, caveat, or question.
Bentler et al. (1986) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: