GEOSTATS: Geostats: ABOUT JACKKNIFE
- Dear list readers
I am in an attempt to estimate bias and reduce bias.
I am working to apply jackknife technique to 2D data sets..
I have some thematic map 2d map using data sets..
to estimate bias,
I followed below steps,
(1) by using all layers, I obtain some thematic map(E)
(2) after deleting ith layer, I obtain the possibility map.(E_-i)
(3) calculate pseudo value E(i)(E(i)=n*E-(n-1)*E_-i)
(4) calculate average of pseudo value (=sum(E(i))/n)
I think average of pseudo value is the jackknifed estimate of E..
but jackknife estimate value is larger than E..
the range of E(thematic map) is from -15 to 4.1.
but the range of jackknifed estimate is from -85 to 21.4 ..
when I compare thematic map E with jackknifed estimate,
calculated value is somewhat strange..
I think my procedure may be wrong. or omitted some stage..
If anyone know my problem, please let me know..
sorry for poor writing in english...
*To post a message to the list, send it to ai-geostats@....
*As a general service to list users, please remember to post a summary
of any useful responses to your questions.
*To unsubscribe, send email to majordomo@... with no subject and
"unsubscribe ai-geostats" in the message body.
DO NOT SEND Subscribe/Unsubscribe requests to the list!