DOI: https://doi.org/10.31493/tit1921.0302

On calculation of the pseudo-inverse econometric models matrix with a rank deficient observation matrix

Viktor Kutovyi

Abstract


The approach to estimating the parameters of linear econometric dependencies for the case of combining a number of special conditions arising in the modeling process is considered. These conditions concern the most important problems that arise in practice when implementing a number of classes of mathematical models, for the construction of which a matrix of explanatory variables is used. In most cases, the vectors that make up the matrix have a close correlation relationship. That leads to the need to perform calculations using a rank deficient matrix. There are also violations of the conditions of the Gauss-Markov theorem. For any non-degenerate square matrix X , an inverse matrix 1 X  is uniquely defined such that, for random right-hand sideB , the solution of the system XB  is vector 1 Xb  . If X is a degenerate or rectangular matrix, then there is no inverse to it. Moreover, in these cases, the system XB  may be incompatible. Here it is natural to use a generalization of the concept of the inverse transformation, which is formulated in terms of the corresponding problem of minimizing the sum of squared residuals. In the same case, having a QR decomposition, one can use the formula 1 1 X R Q   . In addition, it is recommended for specific calculations. With an incomplete rank, the most convenient form of representation 1 X  follows from the expansion in characteristic numbers. If X U V with non-zero characteristic   
numbers, then X V U   . We propose an alternative X  calculation method, which relies on the decomposition of a rank deficient matrix into the product of two matrices of full rank.

Keywords


econometric model; matrix of incomplete rank; Gauss-Markov conditions; pseudoinverse matrix

References


Johnston J., 1971. Econometric Methods. MeGraw-Hill, 437.

Lawson C.L., Hanson R.J., 1974. Solving Least Squares Problems. Prentice-Hall, Inc., Englewood Cliffs N.J., 340.

Voevodin V.V., 1977. Vychislitel`nye osnovy lineinoi algebry [numerical foundations of linear algebra]. Moscow, Nauka, 303 (in Russian).

Kutovyi V.O., 2001. Pro teoremu HaussaMarkova u vypadku vyrodzhenoi matrytsi sposterezhen. Dopov. Dokl. Akad. Nauk Ukraine, No.5, 19-22 (in Ukrainian).

Kutovyi V.O., 2000. Pro zastosuvania instrumentalnyh zminnyh dlia vyznachenia parametriv zagalnoi liniynoi modeli Modeliuvayia ta informaciyni systey v economici. Kyiv.KNEU, No.64, 168-173 (in Ukrainian).

Kutovyi V.O., Roskach O.S., 1997. Matematyko-statystychne uzagalnenia pokrokovyh metodiv pobudovy predyktornyh prostoriv. Mashynna obrobka informacii, No.59, 140-149 (in Ukrainian).

Kutovyi V.O., Roskach O.S., 1997. Pro zastosyvania na EOM algorytmu FarraraGlaubera.Mashyna obrobka informacii. Kyiv, KNEU, No.61, 142-149 (in Ukrainian).

Kutovyi V.O., 1999. Pro umovy zastosuvania teoremy Gaussa-Markova. Vcheni zapysky Kyiv, KNEU, No.2C, 206-208 (in Ukrainian).

Kutovyi V.O., 2001. Pro efektyvnist zmishenyh ocinok parametriv economichnyh modelei. Kyiv, KNEU, No.3, 324-326 (in Ukrainian).

Aitken A.C., 1993. One Least-squares and Linear Combination of Observations. Proc., Royal Soc., Edinburgh, No.55, 42-46.

Pavies O., 1993. Statistical moments in research and production, New York, 1957.

Plackett R., 1960. Principles of regression analysis. Oxford.

Weatherburn C.E., 1961. A first course in mathematical statistics. University Press, Cambridge, brosch, 18s, 6d, 278.

Hamilton W., 1964. Statistics in physical science. New York, 1964.

Jürgen Grob., 2004. The general Gauss-Markov model with possible singular dispersion matrix. Statistical Paper, No.45, 311-336.

Farrar D.E., Glauber R.R., 1967. Multicollinearity in Regression Analysis: The Problem Revisited. Review of Economics and Statistics, 49(1), 92-107. 17. Yangge Fian, Beisiegel M., Dagenais E., Haines C., 2008. On the natural restrictions in the singular Grauss-Markov model. Statistical Papers, Vol.49, 553-564.

Silvey S.D., 1969. Multicallinearity and Imprecise Estimation. Journal of the Real Statical Society, Series B, No.31, 539-552.

Kutovyi V.O., Katunina O.S., 2017. Projecting predicators for econometric models with matrix of supervisory range obstructions. Моделювання та інформаційні системи в економіці, КНЕУ, No.94, 178-194.

Viktor Kutovyi, Olga Katunina, Oleg Shutovskyi, 2018. Analysis of the multicollinear econometric model parameters with a rank deficient observation matrix. Transfer of Innovative Technologies, Vol.1(1), 75-88. 21. Ахиезер Н.И., Глазман И.И. Теория линейных операторов в Гильбертовом пространстве. Москва, Наука, 543.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.