I would like to do bootstrap aggregation of a model (currently fit
with glm()) so that:
1) Data observations are replicated as N bootstrap samples.
2) The specified model is fit to each sample.
3) Error is calculated on out of bag samples.
4) Have an easy way of making model predictions.
5) + all
visualisation/data
analysis/reporting software that uses Rserve to connect to R.
Best regards,
Alex
--
* Alex Fun * Resident Scientist
* Email: * a...@glasshat.com
* Website: * www.glasshat.com
* Address: * Level 9, 70 Pitt Street Sydney NSW 2000 * Office: * 02 9114
9515
* Personal: * 02
/Batteries O.O#. #.O#. with
>> /Software/Embedded Controllers) .OO#. .OO#.
>> rocks...1k
>>
>> ---
>>
>>
> __
3 matches
Mail list logo