The model of quadratic regression is studied by means of the projection pursuit method. This method leads to a decomposition of the matrix of quadratic regression, which can be used for an estimation of this matrix from the data observed.
@article{104303, author = {Franti\v sek \v Stulajter}, title = {Projection pursuit quadratic regression - the normal case}, journal = {Applications of Mathematics}, volume = {33}, year = {1988}, pages = {204-212}, zbl = {0659.62062}, mrnumber = {0944784}, language = {en}, url = {http://dml.mathdoc.fr/item/104303} }
Štulajter, František. Projection pursuit quadratic regression - the normal case. Applications of Mathematics, Tome 33 (1988) pp. 204-212. http://gdmltest.u-ga.fr/item/104303/
Projection pursuit regression, J. Amer. Stat. Assoc. 76 (1981) 817-823. (1981) | Article | MR 0650892
Projection pursuit, Ann. Statist. 13 (1985), 435-475. (1985) | Article | MR 0790553 | Zbl 0595.62059
Quadratic estimation of variance components, Biometrika 29 (1973), 311-330. (1973) | MR 0329142
Estimation of variance and covariance components - MINQUE theory, J. Mult. Analysis 1, 1971, 445-456. (1971) | Article | MR 0301870 | Zbl 0223.62086
Gaussian random processes, (Russian). Nauka, Moskva 1970. (1970) | MR 0544843
RKHS approach to nonlinear estimation of random variables, Trans. VIII-th Prague Conf. Volume B (1978), 239-246. (1978) | MR 0536821