Page History
...
Figure 10 contains a pie chart for the dataset whose shrinkage plot is displayed in Figure 4. Because of a small sample size (two groups with four observations each) we see that, overall, shrinkage is beneficial: for an "average" feature, Akaike weight for feature-specific Lognormal is 25%, whereas Lognormal with shrinkage weighs 75%.
| Numbered figure captions | ||||
|---|---|---|---|---|
| ||||
At the same time, if we look at ERCC-00046 specifically (Figure 11) we see that Lognormal with shrinkage fits so bad that its Akaike weight is virtually zero, despite having fewer parameters than feature-specific Lognormal.
...
Overview
Content Tools