¥There are numerous rules (see Jolliffe, 2002a, Chapter 6)
based on:
1.Size of individual variances (eigenvalues, λk)
2.Cumulative sum of variances
3.Changes in successive variances
4.Physical interpretability
5.More complicated techniques
¥Types 2 & 4 are probably most often used in geoscience, but rules of
type 5 have been suggested and 3 (gaps between
eigenvalues) is also sometimes important (e.g if EOFs are
to be rotated)