Sequential Outlier Identification for Model-Based Clustering
Fit a Gaussian mixture model to the backtrack solution.
Fit a linear cluster-weighted model to the backtrack solution.
Move backwards from the minimum to a more conservative solution.
Compute the dissimilarity for a Gaussian mixture model and identify th...
Compute the dissimilarity for a single component of a Linear CWM.
Compute the dissimilarity for a linear cluster-weighted model and iden...
Compute the dissimilarity for a single multivariate Gaussian distribut...
Compute the response dissimilarity for a single component of a Linear ...
Find gross outliers.
Obtain an initial clustering as a component assignment matrix.
Constructor for "outliermbc_gmm" S3 class.
Constructor for "outliermbc_lcwm" S3 object.
Sequentially identify outliers while fitting a Gaussian mixture model.
Sequentially identify outliers while fitting a linear cluster-weighted...
outlierMBC: Sequential Outlier Identification for Model-Based Clusteri...
Plot the dissimilarity curve showing the backtrack solution.
Plot multiple dissimilarity curves.
Plot multiple dissimilarity curves.
Plot the dissimilarity curve.
Plot dissimilarity values for multiple solutions.
plot method for "outliermbc_gmm" S3 class.
plot method for "outliermbc_lcwm" S3 class.
print method for "outliermbc_gmm" S3 class.
print method for "outliermbc_lcwm" S3 class.
Simulate data from a Gaussian mixture model with outliers.
Simulate data from a linear cluster-weighted model with outliers.
Check if a new sample satisfies the outlier criteria.
Run mixture::gpcm and try alternative covariance structures or initi...
Produce a single sample that passes the outlier checks.
Sample a potential outlier.
Obtain the span of the observations for each component.
Validator for "outliermbc_gmm" S3 class.
Validator for "outliermbc_lcwm" S3 class.
Sequential outlier identification for Gaussian mixture models using the distribution of Mahalanobis distances. The optimal number of outliers is chosen based on the dissimilarity between the theoretical and observed distributions of the scaled squared sample Mahalanobis distances. Also includes an extension for Gaussian linear cluster-weighted models using the distribution of studentized residuals. Doherty, McNicholas, and White (2025) <doi:10.48550/arXiv.2505.11668>.