Skip to main content

Multivariate analysis based on partial least squares regression

Multivariate analysis (MVA) is based on the statistical principle of multivariate statistics, which involves observation and analysis of more than one statistical outcome variable at a time.

Partial least squares regression (PLS regression) is a particular type of MVA. PLS provides quantitative multivariate modelling methods, with inferential possibilities similar to multiple regression, t-tests and ANOVA. It reduces the predictors to a smaller set of uncorrelated components and performs least squares regression on these components.

Regress and analyze

  • Open a table
  • Run from the top menu: ML | Analyze | Multivariate Analysis...
  • Select a table that contains features
  • Select feature columns
  • Select column with sample names
  • Select prediction column
  • Select the number of extracted PLS components
  • Press OK

add-to-workspace

Outputs

Loadings

The loadings plot shows correlations between variables. Comparing the correlation loadings to the scores shows how the variables relate to the observations.

loadings.png

Reference vs. predicted

A scatter plot and a regression line indicate how the model fits and predicts.

reference-vs-predicted.png

Scores

The scores plot shows object similarities and dissimilarities.

scores.png

Regression coefficients

A bar chart illustrates features influence on the predicted value.

regression-coefficients.png

See also: