Saddlepoint approximation method

The saddlepoint approximation method is a specific example of the mathematical saddlepoint technique applied to statistics. It provides a highly accurate approximation formula for any PDF or probability mass function of a distribution, based on the moment generating function. There is also a formula for the CDF of the distribution.

Definition

If the moment generating function of a distribution is written as $M(t)$ and the cumulant generating function as $K(t)=\log(M(t))$ then the saddlepoint approximation to the PDF of a distribution is defined as:

${\hat {f}}(x)={\frac {1}{\sqrt {2\pi K''(s)}}}\exp(K({\hat {s}})-{\hat {s}}x)$

and the saddlepoint approximation to the CDF is defined as:

${\hat {F}}(x)={\begin{cases}\Phi ({\hat {w}})+\phi ({\hat {w}})({\frac {1}{\hat {w}}}-{\frac {1}{\hat {u}}})&{\text{for }}x\neq \mu \\{\frac {1}{2}}+{\frac {K'''(0)}{6{\sqrt {2\pi }}K''(0)^{3/2}}}&{\text{for }}x=\mu \end{cases}}$

where ${\hat {s}}$ is the solution to $K'({\hat {s}})=x$, ${\hat {w}}=\operatorname {sgn} {\hat {s}}{\sqrt {2({\hat {s}}x-K({\hat {s}})}}$ and ${\hat {u}}={\hat {s}}{\sqrt {K''({\hat {s}})}}$

References

• Butler, Roland W. (2007), Saddlepoint approximations with applications, Cambridge: Cambridge University Press, ISBN 9780521872508
• Daniels, H. E. (1954), Saddlepoint Approximations in Statistics, The Annals of Mathematical Statistics