ADVANTAGES/ WEAKNESSES OF PLS

ADVANTAGES

• Flexibility of algorithm
  • Size dimensions do not matter e.g. there can be more variables than observations;
  • Some versions of the algorithm can accept missing data.
• Can fit data with fewer components than other modelling approaches.

WEAKNESSES

• Distributional properties of estimates not known

• Sometimes difficult to interpret loadings.

Partial Least Squares Regression 27.2.96 Page : 12 of 16