Week 12 Flashcards

1
Q

Clustering method: partitioning

A

Arbitrarily choose k objects, reassign based on mean of clusters and update until no change.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Problems of partitioning clustering

A

Sensitive to outliers

Takes time

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Problems of hierarchical clustering

A

Join unrelated objects
Rigid
Hard to define clusters

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Data structure based internal measures for number of clusters

A

maximise inter-distance

minimise intra-distance

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Stability-based metrics for number of clusters

A

remove part of information and regenerate until there is no change in clustering results

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Integrating known biological information for number of clusters

A

Use a knowledge base

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Meta-analysis

A

combine results of published data, check for overall effects

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Problems with meta-analysis

A

Publication bias

“Comparing apples to oranges”

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Benefits of meta-analysis

A

Generalisation to broad population possible
Precision and accuracy improve
Differentiate between real and sampling variation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly