Eemoutlier

From Eigenvector Research Documentation Wiki
Revision as of 17:30, 10 June 2015 by imported>Scott (Created page with "===Purpose=== Automatically remove outliers in PARAFAC models of EEM data. ===Synopsis=== :result = eemoutlier(X,factors); ===Description=== Provides an automated outlier...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

Purpose

Automatically remove outliers in PARAFAC models of EEM data.

Synopsis

result = eemoutlier(X,factors);

Description

Provides an automated outlier selection procedure for a given dataset and given number of components. Samples with a high leverage or high sum-squared residual are removed one by one until no samples are assessed as outliers. The settings for making decisions are given in the top of the m-file. Outliers can only be removed until there are 8 samples left. Then the algorithm will stop.

Inputs

  • X = multi-way array.
  • factors = number of factors.

Outputs

  • result = structure with following fields:
result.model = parafac model.
result.SMPS = cell of sample sets.

See Also

parafac