Abstract
Several authors have obtained the first order one-step approximation for diagnostic measures when a single observation is deleted from the data in a normal nonlinear regression (Fox, Hinkley and Larntz, 1980) and in generalized linear models (Pregibon, 1981). In this paper, we suggest nonlinearity and skewness measures to assess the adequacy of this first order one-step approximation. If one of these measures is large, compared to its guide values, then we recommend the second order one-step approximation as a better alternative. Furthermore, regression diagnostics such as Cook’s distance, likelihood distance and deviance calculated from the second order one-step approximation provide more accurate results than those calculated from the first order one-step approximation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bartlett, M.S., Approximate Confidence Intervals II. More Than One Unknown Parameter, Biometrika, 40 (1953), pp. 306–317.
Bates, D.M. and Watts, D.G., Nonlinear Regression Analysis and Its Applications, New York: John Wiley (1988).
Bates, D.M. and Watts, D.G., Parameter Transformations for Improved Approximate Confidence Regions in Nonlinear Least Squares, The Annals of Statistics, 9 (1981), pp. 1152–1167.
Bates, D.M. and Watts, D.G., Relative Curvature Measures of Nonlinearity (with discussion), Journal of the Royal Statistical Society, Ser. B., 42 (1980), pp. 1–25.
Belsley, D.A., Kuh, E. and Welsch, R.E., Regression Diagnostics: Identifying Influential Data and Sources of Collinearity, New York: John Wiley (1980).
Carroll, R.J. and Ruppert, D., Transformation and Weighting in Regression, New York: Chapman and Hall (1988).
Chatterjee, S. and Hadi, A., Sensitivity Analysis in Linear Regression, New York: John Wiley (1988).
Cook, R.D., Detection of Influential Observations in Linear Regression, Technometrics, 19 (1977), pp. 15–18.
Cook, R.D. and Weisberg, S., Residuals and Influence in Regression, New York: Chapman and Hall (1982).
Cook, R.D. and Tsai, C.L., Diagnostics for Assessing the Accuracy of Normal Approximations in Exponential Family Nonlinear Models, to appear in Journal of the American Statistical Association (1990).
Cox, D.R., Davison, A.C., Firth, D., Nelder, J.A. and O’Brien, C.M., Generalized Linear Models and Beyond, London: Imperial College (1987).
Draper, N.R. and Smith, H., Applied Regression Analysis, (2nd Ed.) New York: John Wiley (1981).
Duncan, G.T., An Empirical Study of Jackknife-Constructcd Confidence Regions in Nonlinear Regressions, Technometrics, 20 (1978), pp. 123–129.
Finney, D.J., The Estimation From Individual Records of the Relationship Between Dose and Quantal Response, Biometrika, 31 (1947), pp. 320–334.
Fox, t., iiinkley, D. and Larntz, K., Jackknifing in Nonlinear Regression, Technometrics, 22 (1980), pp. 29–33.
Hamilton, D.C., Watts, D.G. and Bates, D.M., Accounting for Intrinsic Nonlinearity in Nonlinear Regression Parameter Inference Regions, The Annals of Statistics, 10 (1982), pp. 386–393.
Jennings, D., Judging Inference Adequacy in Logistic Regression, Journal of the American Statistical Association, 81 (1986), pp. 471–476.
Lawless, J.F., Statistical Model and Methods for Lifetime Data, New York: John Wiley (1982).
Marske, D., Biomedical Oxygen Demand Data Interpretation Using Sum of Squares Surface, M.S. Thesis, University of Wisconsin-Madison (1967).
McCullagh, P. and Nelder, J.A., Generalized Linear Models, (2nd Ed.) London: Chapman and Hall (1989).
Pregibon, D., Logistic Regression Diagnostics, The Annals of Statistics, 9 (1981), pp. 705–724.
Williams, D.A., Generalized Linear Model Diagnostics Using the Deviance and Single Case Deletions, Journal of the Royal Statistical Society, Ser. C., 36 (1987), pp. 181–191.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1991 Springer-Verlag New York, Inc.
About this paper
Cite this paper
Tsai, CL., Wu, X. (1991). Comparisons Between First Order and Second Order Approximations in Regression Diagnostics. In: Directions in Robust Statistics and Diagnostics. The IMA Volumes in Mathematics and its Applications, vol 34. Springer, New York, NY. https://doi.org/10.1007/978-1-4612-4444-8_15
Download citation
DOI: https://doi.org/10.1007/978-1-4612-4444-8_15
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4612-8772-8
Online ISBN: 978-1-4612-4444-8
eBook Packages: Springer Book Archive