| [1]Efron B. Defining the curvature of a statistical problem (with application to second ord er efficiency).Ann Statist, 1975,3(6):1189-1242
[2]Bates D M, Watts D G. Relative curvature measures of nonlinearity. J Roy Statist Soc B,1980,42(1): 1-25
[3]Hamilton D C, Bates D M, Watts D G. Accounting for intrinsic nonlinearity in nonlinear regression parameter inferen ceregions.Ann Statist, 1982,10(2): 386-393
[4]Wei B C. Exponential Family Nonlinear Models. Singapore:SpringerVerl ag, 1998
[5]Tsay R S. Regression models with time series errors. J Amer Statist Assoc, 1984, 79(385): 118-124
[6]Puterman M L. Leverge and influence in autocorrelated regression model s. Appl Statist, 1988, 37(1): 76-865
[7]Hossain A. Detection of influential observations in regression model wit h autocorrelated errors.Comm Statist Theory Methods, 1990,19(5):1047-1060
[8]Tsay R S. Time series model specification in the presence of outliers.J Amer Statist Assoc, 1986, 81(393):132-141
[9]Ledolter J. Outlier diagnostics in time series analysis. J Time Ser, 1988, 11(2): 317-324
[10]Seber G A F, Wild C J. Nonlinear Regression. New York: John Wiley, 1989
[11]Amari S. Differential geometry of curved exponential family curvatur es and information loss.Ann Statist, 1982, 10(2): 375-385
[12]Kass R E. The geometry of asymptotic inference. Statist Sci, 1989, 4(2):188-219
[13]Wei B C. Some second order asymptotics in nonlinear regression. Aust J statist, 1991, 33(1): 75-84
[14]Wei B C. Some asymptotic properties in multinomial nonlinear models (A geometric appoach).Appl Math J Chin Univs Ser B, 1996, 11(2): 273-284
[15]Efron B, Hinkley D V.Assessing the accuracy of the maximum likeliho od estimator:Observed versus expected fisher information. Biometrika, 1978,65(2): 457-487 |