Vovk, Vladimir (2005) Non-asymptotic calibration and resolution.
Full text access: Open
We analyze a new algorithm for probability forecasting of binary observations on the basis of the available data, without making any assumptions about the way the observations are generated. The algorithm is shown to be well calibrated and to have good resolution for long enough sequences of observations and for a suitable choice of its parameter, a kernel on the Cartesian product of the forecast space [0,1] and the data space. Our main results are non-asymptotic: we establish explicit inequalities, shown to be tight, for the performance of the algorithm.
This is a Submitted version This version's date is: 1/6/2005 This item is not peer reviewed
https://repository.royalholloway.ac.uk/items/ba0829e0-514e-a228-ff8d-d8c98ff1f10e/8/
Deposited by Research Information System (atira) on 18-Nov-2014 in Royal Holloway Research Online.Last modified on 18-Nov-2014
20 pages