Abstract
The general Gauss–Markov model, Y = Xβ + e, E(e) = 0, Cov(e) = σ 2 V, has been intensively studied and widely used. Most studies consider covariance matrices V that are nonsingular but we focus on the most difficult case wherein C(X), the column space of X, is not contained in C(V). This forces V to be singular. Under this condition there exist nontrivial linear functions of Q′Xβ that are known with probability 1 (perfectly) where \({C(Q)=C(V)^\perp}\). To treat \({C(X) \not \subset C(V)}\), much of the existing literature obtains estimates and tests by replacing V with a pseudo-covariance matrix T = V + XUX′ for some nonnegative definite U such that \({C(X) \subset C(T)}\), see Christensen (Plane answers to complex questions: the theory of linear models, 2002, Chap. 10). We find it more intuitive to first eliminate what is known about Xβ and then to adjust X while keeping V unchanged. We show that we can decompose β into the sum of two orthogonal parts, β = β 0 + β 1, where β 0 is known. We also show that the unknown component of X β is \({X\beta_1 \equiv \tilde{X} \gamma}\), where \({C(\tilde{X})=C(X)\cap C(V)}\). We replace the original model with \({Y-X\beta_0=\tilde{X}\gamma+e}\), E(e) = 0, \({Cov(e)=\sigma^2V}\) and perform estimation and tests under this new model for which the simplifying assumption \({C(\tilde{X}) \subset C(V)}\) holds. This allows us to focus on the part of that parameters that are not known perfectly. We show that this method provides the usual estimates and tests.
Similar content being viewed by others
References
Christensen R (1990) Comment on Puntanen and Styan (1989). Am Stat 44: 191–192
Christensen R (2002) Plane answers to complex questions: the theory of linear models. Springer, New York
Fan J, Huang LS (2001) Goodness-of-fit tests for parametric regression models. J Am Stat Assoc 96: 640–652
Groß J (2004) The general Gauss–Markov model with possibly singular dispersion matrix. Stat Pap 45: 311–336
Harville DA (1981) Unbiased and minimum-variance unbiased estimation of estimable functions for fixed linear models with arbitrary covariance structure. Ann Stat 9: 633–637
Harville DA (1990) Comment on Puntanen and Styan (1989). Am Stat 44: 192
Kempthorne O (1989) Comment on Puntanen and Styan (1989). Am Stat 43: 161–162
Kreijger RG, Neudecker H (1977) Exact linear restrictions on parameters in the general linear model with a singular covariance matrix. J Am Stat Assoc 72: 430–432
Puntanen S, Scott AJ (1996) Some further remarks on the singular linear model. Linear Algebra Appl 237/238: 313–327
Puntanen S, Styan GPH (1989) The equality of the ordinary least squares estimator and the best linear unbiased estimator (with discussion). Am Stat 43: 153–164
Rao CR (1967) Least squares theory using an estimated dispersion matrix and its application to measurement of signals. In: Proceedings of the fifth Berkeley symposium, vol 1. University of California Press, Berkeley, pp 355–372
Rao CR (1968) A note on a previous lemma in the theory of least squares and some further results. Sankhyā A 30: 259–266
Rao CR, Mitra SK (1971) Generalized inverse of matrices and its applications. Wiley, New York
Zyskind G (1967) On canonical forms, non-negative covariance matrices and best and simple least square linear estimators in linear models. Ann Math Stat 38: 1092–1109
Zyskind G, Martin FB (1969) On best linear estimation and general Gauss–Markov theorem in linear models with arbitrary nonegative covariance structure. SIAM J Appl Math 17: 1190–1202
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Christensen, R., Lin, Y. Linear models that allow perfect estimation. Stat Papers 54, 695–708 (2013). https://doi.org/10.1007/s00362-012-0455-0
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00362-012-0455-0