University of Cambridge > Talks.cam > Computer Laboratory NetOS Group Talklets > Comparing Predictors

Comparing Predictors

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Henry Robinson.

This talk will involve introducing ‘a tool’ for comparing the performance of two models:

The case often arises when the performance of one predictor is compared to that of another (the performance of a Kalman filter compared to an exponential filter for CPU usage prediction, for example) Typically some form of f-test is applied based on the ratio of sum squared errors from both predictors to show that one is in fact better than the other. However, the underlying assumptions for the f-test are (in reality) always violated as the prediction errors are cross-correlated. This talk will introduce a test based on the difference and sum of prediction errors and an example with some additional details will be given.

This talk is part of the Computer Laboratory NetOS Group Talklets series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity