summary A new approximation to the distribution of quadratic forms in normal random variables is derived. It is based on the Edgeworth expansion and a bound on the error involved in the approximation is given. The new approximation is compared with others for a particular quadratic form which arises in the estimation of variance in a non‐parametric regression.
No takes yet. Share an insight, caveat, or question.
Buckley et al. (1988) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: