setDistanceLimits.pls {mdatools}

Compute and set statistical limits for residual distances.

Description

Computes statisticsl limits for orthogonal and score distances (x-decomposition) and orthogonal distance (y-decomposition) based on calibration set and assign the calculated values as model properties.

Usage

## S3 method for class 'pls'
setDistanceLimits(
  obj,
  lim.type = obj$lim.type,
  alpha = obj$alpha,
  gamma = obj$gamma,
  ...
)

Arguments

obj

object with PLS model

lim.type

type of limits ("jm", "chisq", "ddmoments", "ddrobust")

alpha

significance level for detection of extreme objects

gamma

significance level for detection of outliers (for data driven approach)

...

other arguments

Details

The limits can be accessed as fields of model objects: $Qlim, $T2lim, and $Zlim. Each is a matrix with four rows and ncomp columns. In case of limits for x-decomposition, first row contains critical limits for extremes, second row - for outliers, third row contains mean value for corresponding distances (or its robust estimate in case of lim.type = "ddrobust") and last row contains the degrees of freedom.

Value

Object models with the three fields updated.