Metafitting: Weight Optimization for Least-Squares Fitting of PTTI Data

R.J. Douglas, J.S. Boulanger

Abstract:	For precise time intercomparisons between a master frequency standard and a slave time scale, we have found it useful to quantitatively compare different fitting strategies by examining the standard uncertainty in time or average frequency. It is particularly useful when designing procedures which use intermittent intercomparisons, with some parameterized fit used to interpolate or extrapolate from the calibrating intercomparisons. We use the term "metafitting" for the choices that are made before a fitting procedure is operationally adopted. We present methods for calculating the standard uncertainty for general, weighted least-squares fits and a method for optimizing these weights for a general noise model suitable for many PTTI applications. We present the results of the metafitting of procedures for the use of a regular schedule of (hypothetical) high-accuracy frequency calibration of a maser time scale. We have identified a cumulative series of improvemenfs that give a significant reduction of the expected standard uncertainty, compared to the simplest procedure of resetting the maser synthesizer after each calibration. The metafitting improvements presented include the optimum choice of weights for the calibration runs, optimized over a period of a week or 10 days.
Published in:	Proceedings of the 26th Annual Precise Time and Time Interval Systems and Applications Meeting December 6 - 8, 1994 Hyatt Regency Reston Town Center Reston, Virginia
Pages:	347 - 360
Cite this article:	Douglas, R.J., Boulanger, J.S., "Metafitting: Weight Optimization for Least-Squares Fitting of PTTI Data," Proceedings of the 26th Annual Precise Time and Time Interval Systems and Applications Meeting, Reston, Virginia, December 1994, pp. 347-360.
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In