An improved saddlepoint approximation.

Given a set of third- or higher-order moments, not only is the saddlepoint approximation the only realistic 'family-free' technique available for constructing an associated probability distribution, but it is 'optimal' in the sense that it is based on the highly efficient numerical method of steepest descents. However, it suffers from the problem of not always yielding full support, and whilst [S. Wang, General saddlepoint approximations in the bootstrap, Prob. Stat. Lett. 27 (1992) 61.] neat scaling approach provides a solution to this hurdle, it leads to potentially inaccurate and aberrant results. We therefore propose several new ways of surmounting such difficulties, including: extending the inversion of the cumulant generating function to second-order; selecting an appropriate probability structure for higher-order cumulants (the standard moment closure procedure takes them to be zero); and, making subtle changes to the target cumulants and then optimising via the simplex algorithm.

[1]  K. Hopcraft,et al.  Distinguishing population processes by external monitoring , 2003, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[2]  Eric Renshaw.  Saddlepoint approximations for stochastic processes with truncated cumulant generating functions , 1998 .

[3]  G. R. Hext,et al.  Sequential Application of Simplex Designs in Optimisation and Evolutionary Operation , 1962 .

[4]  Elvezio Ronchetti,et al.  Small Sample Asymptotics , 1990 .

[5]  I. Good.  THE MULTIVARIATE SADDLEPOINT METHOD AND CHI-SQUARED FOR THE MULTINOMIAL DISTRIBUTION , 1961 .

[6]  George Casella,et al.  Explaining the Saddlepoint Approximation , 1999 .

[7]  Eric Renshaw,et al.  The M / M /1 queue with mass exodus and mass arrivals when empty , 1997 .

[8]  Jane L. Harvill,et al.  Saddlepoint Approximations for the Difference of Order Statistics and Studentized Sample Quantiles , 1999 .

[9]  E. Ronchetti,et al.  General Saddlepoint Approximations with Applications to L Statistics , 1986 .

[10]  Eric Renshaw,et al.  A simple saddlepoint approximation for the equilibrium distribution of the stochastic logistic model of population growth , 2003 .

[11]  Saddlepoint Approximations of Marginal Densities and Confidence Intervals in the Logistic Regression Measurement Error Model , 1996 .

[12]  Eric Renshaw,et al.  Birth-death processes with mass annihilation and state-dependent immigration , 1997 .

[13]  H. Daniels.  Saddlepoint Approximations in Statistics , 1954 .

[14]  James H. Matis,et al.  ON APPROXIMATING THE MOMENTS OF THE EQUILIBRIUM DISTRIBUTION OF A STOCHASTIC LOGISTIC MODEL , 1996 .

[15]  John A. Nelder,et al.  A Simplex Method for Function Minimization , 1965, Comput. J..

[16]  Offer Lieberman.  The Effect of Nonnormality , 1997, Econometric Theory.

[17]  Rob Hengeveld,et al.  Dynamics of Biological Invasions , 1989 .

[18]  Eric Renshaw,et al.  The evolution of a batch-immigration death process subject to counts , 2005, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[19]  E. Renshaw,et al.  Applying the saddlepoint approximation to bivariate stochastic processes. , 2000, Mathematical biosciences.

[20]  W. Tan,et al.  Some stochastic models of AIDS spread. , 1989, Statistics in medicine.

[21]  Shih-Yu Wang.  General saddlepoint approximations in the bootstrap , 1992 .

[22]  Eric Renshaw.  Modelling biological populations in space and time , 1990 .

[23]  Generation and monitoring of discrete stable random processes using multiple immigration population models , 2003 .