Biology Reference
In-Depth Information
0.8
0.6
0.4
0.2
0
−0.2
−0.4
−0.6
−0.8
0
0.2
0.4
0.6
0.8
1
1.2
1.4
1.6
1.8
Fig. 2.3.
Data set of Example 2.5
1
1
0.8
0.8
0.6
0.6
0.4
0.4
0.2
0.2
0
0
−0.2
−0.2
−0.4
−0.4
−0.6
−0.6
−0.8
−0.8
−1
−1
−0.5
0
0.5
1
1.5
2
−0.5
0
0.5
1
1.5
2
(a) The PDQ algorithm
(b) The EM method
Fig. 2.4. A comparison of methods for the data of Example 2.5. The EM method returns bad esti-
mates for the left center, and for the weights.
with parameters
µ i , Σ i given in the left column of Table 2.3. A similar example
appears as Fig. 9.6, p. 593, in Tan et al. [14].
As noted in Sec. 2.4.1(d), if the assumptions on the mixing distributions
are justified, the EM Method gives good estimates of the relevant parameters.
Search WWH ::




Custom Search