Kubáček, Lubomír Quadratic regression models. (English) Zbl 0848.62033 Math. Slovaca 46, No. 1, 111-126 (1996). Estimation procedures in nonlinear regression models, in comparison with procedures in linear models, are relatively complicated. However, when the effects of nonlinearity are limited up to the second power of differences between the actual values of the parameters and a priori (by a statistician chosen) values, then the estimation procedure can be developed with similar features as the linear procedures have been, e.g., nonrecursive calculation, the explicit formulae for the covariance matrix of the estimator, etc. The aim of the paper is to contribute to a development of such procedures. Cited in 4 Documents MSC: 62J02 General nonlinear regression 62H12 Estimation in multivariate analysis 62F10 Point estimation Keywords:quadratic vector function; approximation of the mean value; explicit formulae; covariance matrices; quadratic approximation; linear estimation PDFBibTeX XMLCite \textit{L. Kubáček}, Math. Slovaca 46, No. 1, 111--126 (1996; Zbl 0848.62033) Full Text: EuDML References: [1] KUBÁČEK. L.: Linear statistical models with constraints revisited. Math. Slovaca 45 (1995), 287-307. · Zbl 0851.62050 [2] KUBÁČEK. L.: On a linearization of regression models. Appl. Math. 40 (1995), 61-78. · Zbl 0819.62054 [3] PÁZMAN A.: Nonlinear Statistical Models. Kluwer Academic Pubhshers; Ister Science Press, Dordrecht-Boston-London; Bratislava, 1993. · Zbl 0808.62058 [4] RAO C. R.: Linear Statistical Inference and Its Application. (2nd Edition). J. Wiley. New York, 1973. [5] RAO, C R.-MITRA S. K.: Generalized Inverse of Matrices and Its Application. J. Wiley, New York, 1971. This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.