Summary
The comparison of different (linear) models, representing different geodetic/geophysic hypotheses, on the light of observational data leads to a testing procedure based on residuals between data and manifolds in general different positions. This topic has already been mentioned in statistical literature as comparison of non-nested linear models. The problem is here defined and completely solved by a Bayesian approach.
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
Backus G.L. (1971). Inference from inadequate and inaccurate data, Lectures in Applied Mathematics n. 14, pp. 1–105.
Betti B., Crespi M. and Sansó F. (1993). A geometric illustration of ambiguity resolution in GPS theory and a Bayesian approach Manuscripta Geodaetica 18, n. 6, pp. 317–330.
Cox D.R., Hinkley D. K. (1978). Theoretical Statistics. Chapman and Hall, London.
Efron B. (1984). Comparing non-nested linear models. Journal of the American Statistical Association 78, n. 38b, pp. 791–803.
Jackson D.D. and Matsu’ura M. (1985). A Bayesian approach to non linear inversion. Journal of Geophysical Research 90, n. Bl, pp. 581–591.
Koch K.R. (1988). Parameter estimation and hypotheses testing in linear models. Springer, Berlin Heidelberg New York Tokyo.
Tarantola A. (1987). Inverse problem theory. Elsevier, New York.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Betti, B., Crespi, M., Sansó, F., Sguerso, D. (1995). Discriminant Analysis to Test Non-Nested Hypotheses. In: Sansò, F. (eds) Geodetic Theory Today. International Association of Geodesy Symposia, vol 114. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-79824-5_34
Download citation
DOI: https://doi.org/10.1007/978-3-642-79824-5_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-59421-5
Online ISBN: 978-3-642-79824-5
eBook Packages: Springer Book Archive