Eigenvalues

From Displayr
Jump to: navigation, search

An eigenvalue is a term from linear algebra. It can only be accurately explained with reference to algebra. In general, when statistical methods used in survey research produce eigenvalues, they are interpreted as follows:

  • Eigenvalues can be compared (e.g., if one eigenvalue is twice the size of another it means that it explains around twice us much of the data). For this reason it is common to convert eigenvalues to percentages.
  • Bigger eigenvalues correspond to more variance being explained in data.