The x-calculated values are linear combinations of the x-scores; contain the variance in the predictors explained by the PLS model. Observations with relatively small x-calculated values are outliers in the x-space and are not well explained by the model.
The x-calculated matrix, similar to the original x-matrix, is an n × p matrix, where n equals the number of observations and p equals the number of predictors. The x-calculated values are on the same scale as the predictors.
The x-calculated matrix is initialized to the zero matrix. After calculating the m th component and obtaining the x-score vector and the x-loading vector, Minitab calculates the x-calculated values. If the number of components equals the number of predictors, then the x-calculated value equals the original x-value.
Minitab then calculates the unstandardized x-calculated values by multiplying the standardized x-calculated values by the standard deviation of the predictor values and adding the mean.
|n||the number of observations|
|p||the number of predictors|
|i||the number of observations from 1 to n|
|j||the number of predictors from 1 to p|
| t || the x-scores|
| l || the x-loadings|