×

zbMATH — the first resource for mathematics

Changes in the general linear model: A unified approach. (English) Zbl 0933.62060
Summary: Analysis of the general linear model with possibly rank-deficient design and dispersion matrices has sometimes generated some confusion and controversy, prompting some researchers to discuss it as quite distinct from the case of full-rank matrices. We show that linear zero functions, i.e., linear functions in observations which have zero expectations for all parameter values, provide an intuitive way of developing all the important results in connection with the general linear model, thus bridging this imaginary gap. We show that the effect of addition or deletion of a set of observations in this model can be clearly understood in statistical terms if viewed through such linear zero functions. The effect of adding or dropping a group of parameters is also explained well in this manner.
Several sets of update equations were derived by a host of previous researchers in various special cases of the above set-up. The results derived here bring out the common underlying principles of these formulae and indeed help simplify most of them. These results also provide further insights into recursive residuals, design of experiments, deletion diagnostics and selection of subset models.

MSC:
62J05 Linear regression; mixed models
62J20 Diagnostics, and linear inference and regression
PDF BibTeX XML Cite
Full Text: DOI
References:
[1] Basu, D., The family of ancillary statistics, Sankhyā ser. A, 21, 247-256, (1959) · Zbl 0091.14803
[2] Bhimasankaram, P.; Jammalamadaka, S.R., Updates of statistics in a general linear model: A statistical interpretation, applications, Communication in statistics, ser. B, 23, 789-801, (1994) · Zbl 0825.62062
[3] Bhimasankaram, P.; Sengupta, D.; Ramanathan, S., Recursive inference in a general linear model, Sankhyĉ ser. A, 57, 227-255, (1995) · Zbl 0857.62067
[4] Bhimasankaram, P.; Sengupta, D., The linear zero functions approach to linear models, (), Submitted. Also · Zbl 0744.62084
[5] Bich, W., Variances, covariances, restraints in mass metrology, Metrologia, 27, 111-116, (1990)
[6] Brown, R.L.; Durbin, J.; Evans, J.M., Techniques for testing the constancy of regression relationships over time, Journal of the royal statistical society ser. B, 37, 149-163, (1975) · Zbl 0321.62063
[7] Chib, S.; Jammalamadaka, S.R.; Tiwari, R.C., Another look at some results on the recursive estimation in the general linear model, American Statistician, 41, 56-58, (1987)
[8] Christensen, R., Plane answers to complex questions: the theory of linear models, (1987), Springer Berlin · Zbl 0645.62076
[9] Farebrother, R.W., Linear least squares computations, (1988), Marcel Dekker New York · Zbl 0715.65027
[10] Feuerverger, A.; Fraser, D.A.S., Categorical information, the singular linear model, Canadian journal of statistics, 8, 41-45, (1980) · Zbl 0464.62060
[11] Gragg, W.B.; LeVeque, R.J.; Trangenstein, J.A., Numerically stable methods for updating regressions, Journal of the American statistical association, 74, 161-168, (1979) · Zbl 0398.62058
[12] Harville, D.A., Unbiased, minimum-variance unbiased estimation of estimable functions for fixed linear models with arbitrary covariance structure, Annals of statistics, 9, 633-637, (1981) · Zbl 0477.62053
[13] Haslett, S., Recursive estimation of the general linear model with dependent errors, multiple additional observations, Australian journal of statistics, 27, 183-188, (1985) · Zbl 0568.62064
[14] Kianifard, F.; Swallow, W.H., A review of the development, application of recursive residuals in linear models, Journal of the American statistical association, 91, 391-400, (1996) · Zbl 0873.62070
[15] Kempthorne, O., The design, analysis of experiments, (), 137-138
[16] McGilchrist, C.A.; Sandland, R.L., Recursive estimation of the general linear model with dependent errors, Journal of the royal statistical society, ser. B, 41, 65-68, (1979) · Zbl 0398.62059
[17] Mitra, S.K.; Bhimasankaram, P., Generalized inverses of partitioned matrices, recalculation of least squares estimators for data or model changes, Sankhyā ser. A, 33, 396-410, (1971) · Zbl 0236.62049
[18] Plackett, R.L., Some theorems in least squares, Biometrika, 37, 149-157, (1950) · Zbl 0041.46803
[19] Rao, C.R., A note on a previous lemma in the theory of least squares, some further results, Sankhyā ser. A, 30, 259-266, (1968) · Zbl 0197.15802
[20] Rao, C.R., Linear statistical inference, its applications, (1973), Wiley New York · Zbl 0169.21302
[21] Rao, C.R., Least squares theory for possibly singular models, Canadian journal of statistics, 6, 19-23, (1978) · Zbl 0401.62052
[22] Rowley, J.C.R., Singularities in econometric models of wage determination based on time series data, (), 616-621
[23] Scheffe´, H., The analysis of variance, (), 299-301
[24] Searle, S.R., Extending some results, proofs for the singular linear model, Linear algebra and applications, 210, 139-151, (1994) · Zbl 0815.62044
[25] Sengupta, D., Optimal choice of a new observation in a linear model, Sankhyā ser. A, 57, 137-153, (1995) · Zbl 0857.62075
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. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.