Please enable JavaScript.
Coggle requires JavaScript to display documents.
Chapter 7: Decision Analytic Thinking Douglas Beighle (expected value…
Chapter 7: Decision Analytic Thinking
Douglas Beighle
Accuracy= # of correct decisions made/ total number of decisions made
Class confusion
confusion matrix
N x N matrix
positive/negative
class distribution break down causes less accuracy in the data
classification accuracy makes no distinction between false positives and false negatives
false positive
telling a patient that they have cancer when they do not
false negative
telling someone they do not have cancer when they do
expected value
the structure of the problem
what can be extracted
the elements of analysis that need to be pulled from other sources
formula : p(01)
v(01)+p(02)
v(02)+p(02) *v(02)...
a weighted average of the different possible values
figure 7-3 cost benefit matrix
true positive
you tell a patient that they have cancer and they do have cancer
true negative: tell a patient that they do not have cancer and they do not have cancer
Error Rates
errors/total
mathematically there is no distinction between a cost and a benefit.
Costs are negative #s
benefits are positive #s