Abstract
The performance of Maximum Likelihood (ML) and Maximum a posteriori (MAP) estimates in nonlinear problems at low data SNR is not well predicted by the Cramér-Rao or other lower bounds on variance. In order to better characterize the distribution of ML and MAP estimates under these conditions, we derive an approximate density for the conditional distribution of such estimates. In one example, this approximate distribution captures the essential features of the distribution of ML and MAP estimates in the presence of Gaussian-distributed noise.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
SP Müller, MF Kijewski, SC Moore, and BL Holman. “Maximum-Likelihood Estimation: A Mathematical Model for Quantitation in Nuclear Medicine,” J Nucl Med 1990; 31:1693–1701.
HH Barrett. “Objective assessment of image quality: Effects of quantum noise and object variability,” J Opt Soc Am A 1990; 7:1266–1278.
SP Müller, MF Kijewski, and SC Moore. “The efficiency of ML-estimation at low SNR can be inferred from the probability distribution of the estimates,” J Nucl Med 1995; 36:119P.
SP Müller, MF Kijewski, Christian Kappeler, and SC Moore. “Estimation performance at low SNR: Predictions of the Barankin Bound,” in Medical Imaging 1995: Physics of Medical Imaging, Richard van Meter, Jacob Beutel, Editors. Proc. SPIE 2432:157–166.
JA Fessler and AR Hero. “Cramér-Rao lower bounds for biased image reconstruction,” in Proc. Midwest Symposium on Circuits and Systems, 1993, vol. 1, pp. 253–256.
JA Fessler. “Mean and Variance of Implicitly defined Biased Estimators (such as Penalized Maximum Likelihood): Applications to Tomography,” IEEE Trans Image Proc, EDICS 2.3, 1995.
HL Van Trees. Detection, Estimation and Modulation Theory, (Wiley, New York, 1968).
HH Barrett and W Swindell. Radiological Imaging: Theory of Image Formation, Detection, and Processing (Academic, New York, 1981), Vol. I.
S Geman and D Geman. “Stochastic Relaxation, Gibbs Distributions and the Bayesian Restoration of Images,” IEEE Trans. on Pattern Analysis and Machine intelligence, 1984 PAMI-6(6), pp 721–741.
KV Mardia, JT Kent, and JM Bibby. Multivariate analysis, (Academic, San Diego, Calif., 1979).
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Abbey, C.K., Clarkson, E., Barrett, H.H., Müller, S.P., Rybicki, F.J. (1997). Approximate distributions for Maximum Likelihood and maximum a posteriori estimates under a Gaussian noise model. In: Duncan, J., Gindi, G. (eds) Information Processing in Medical Imaging. IPMI 1997. Lecture Notes in Computer Science, vol 1230. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63046-5_13
Download citation
DOI: https://doi.org/10.1007/3-540-63046-5_13
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63046-3
Online ISBN: 978-3-540-69070-2
eBook Packages: Springer Book Archive