# 2.13.3.5 pls(Pro)

Statistics:Multivariate Analysis:Partial Least Squares

## Brief Information

Perform Partial Least Squares Regression

Minimum Origin Version Required: 9.1 SR0

This feature is for OriginPro only.

## Command Line Usage

 1. pls ix:=1!2[1]:44[20] iy:=1!45[1]:47[20] method:=svd scale:=0 cv:=1 output.stat:=1 output.xw:=1 plot.vip:=1 plot.xload:=1 plot.yload:=1 plot.res:=1; 

## Variables

Display
Name
Variable
Name
I/O
and
Type
Default
Value
Description
Independent Variables ix

Input

Range

<active>

Specify the input data for independent variables. Note that beginning with Origin 2020b, there is a shortened syntax that follows the form [Book]Sheet!(N1:N2), N1 = the beginning column index and N2 being the ending column index in a contiguous range of columns. More complex strings from non-contiguous data of the form [Book]Sheet!([Book]Sheet!N1:N2,[Book]Sheet!N3:N4) are also possible.

Dependent Variables iy

Input

Range

<unassigned>

Specify the input data for dependent variables.

Observation Labels label

Input

Range

<optional>

Specify the input data of label for observation, the labels will be show in the Score Plots and X-Y Scores Plots in result.

Predict Responses predict

Input

int

0

Determine whether to predict response from the established partial least square model.

Independent Variables for Prediction irng

Input

Range

<optional>

This variable can only be accessed when predict is set to 1. It specifies independent variables for prediction.

Method method

Input

int

1

Specify the method to compute the extracted factors:

Option list:

• svd:SVD{0}
• wold:Wold's Iteration{1}

You can refer to the Algorithm for Partial Least Squares Method in Origin Help file.

Scale Variables scale

Input

int

1

Specify whether to divide independent variables by the standard deviation.

Maximum Number of Factors factor

Input

int

0

Specify the maximum number of factors to be in the regression model

Cross Validation cv

Input

int

0

Specify whether to establish the partial least square regression model using the Cross Validation method.

Quantities output

Input

TreeNode

Specify which quantities to compute and output. Set the value for output.subnode to control the settings. Details on each sub nodes can be found in the Origin Help file

Sub nodes are:

• stat:Descriptive Statistics
• coeff:Coefficients
• stdcoeff:Standardized Coefficients
• xpcv:Percent Variance Explained for Each X
• ypcv:Percent Variance Explained for Each Y
• vip:VIP (variable influence on projections statistics)
• score:Scores
• ypred:Predicted Response for Training Data
• res:Residuals
• dist:Distance
• t2:T Square for X Scores
• xw:X Weights
Plots plot

Input

TreeNode

Specify whether to show plots in the PLSn sheet. Set the value for plot.subnode to control the settings. Details on each sub nodes can be found in the Origin Help file

• coeff:Coefficients Plot
• vip:Variance Importance Plot
• xfactor:Component Plot-Factor for X Axis
• yfactor:Component Plot-Factor for Y Axis
• zfactor:Component Plot-Factor for Z Axis
• xscore:Component Plot-X Score Plot
• yscoreComponent Plot-Y Score Plot
• xyscore:Component Plot-X-Y Score Plot
• res:Diagnostics Plot
• dist:Distance Plot
• t2:T Square Plot
Partial Least Squares Report rt

Output

ReportTree

<new>

Specify the output range for the partial least squares report.

Report Data (Fitted Results) rdres

Output

ReportData

<new>

Specify the output range for the options selected in the output tree node.

Output

ReportData

<new>

Specify the output range for the loading values and the X weights.

Report Data (Scores and Residuals) rdscore

Output

ReportData

<new>

Specify the output range for the score values and the residual values.

Plot Data rdplot

Output

ReportData

<new>

Specify the output range to put the data for the plot.

## Description

You can refer to the Origin Help file on this topic for details.

## Algorithm

You can refer to the algorithm for PLS in the Origin Help file.

## References

You can refer to this Origin Help file for the reference.