January 2011
Intermediate to advanced
420 pages
12h 32m
English
Content preview from Practical Applications of Data Mining
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
Start your free trial
3.4 divide-and-Conquer approaCh 121
Pre-Presbyopic : N = 1, f = 0, q = z
2
/(N + z
2
) = 0.476/(1 + 0.476)
= 0.322
Presbyopic : N = 1, f = 0, q = z
2
/(N + z
2
) = 0.476/(1 + 0.476)
= 0.322
The weighted average is q = (1/3) × 0.322 + (1/3) × 0.322 + (1/3) × 0.322
= 0.322. Since the internal error rate of the node age is bigger than those of its
children, we keep the node age. Now the next node to examine is the internal
node prescription:
N = 6, f = 2/6 = 0.667, q
= ( f + z
2
/2N + z
fN fNzN///−+
222
4
)/
(1 + z
2
/N) = (0.333 + 0.040 + 0.139)/1.079 = 0.474
Normal
YesNo
Tear Production Rate
Reduced
MyopeHypermetropic
Young Pre-Presbyopic ...