EMexample: A model-based clustering

In KrasnitzLab/CNprep: Pre-process DNA Copy Number (CN) Data for Detection of CN Events

A model-based clustering

Description

A model-based clustering based on parameterized finite Gaussian mixture models

Usage

data(EMexample)

Format

an object of class Mclust providing the optimal (according to BIC) mixture model estimation composed of 5 clusters. The details of the output components are as follows:

• call the matched call

• data a matrix, the input data matrix

• modelName a character string denoting the model at which the optimal BIC occurs

• n an integer, the number of observations in the data

• d a double, the dimension of the data

• G an integer, the optimal number of mixture components

• BIC a double, all BIC values

• bic a double, the optimal BIC value

• loglik a double, the log-likelihood corresponding to the optimal BIC

• df a double, the number of estimated parameters

• hypvol NA

• parameters a list with the following components:

  • pro a vector of double whose kth component is the mixing proportion for the kth component of the mixture model

  • mean a matrix of double whose kth column is the mean of the kth component of the mixture model

  • variance a list of variance parameters for the model

• z a matrix of double whose [i,k]th entry is the probability that observation i in the test data belongs to the kth class

• classification an array of double, the classification corresponding to z

• uncertainty a double, the uncertainty associated with the classification

Details

See Mclust for detailed description of the object of class mclust.

Value

an object of class Mclust providing the optimal (according to BIC) mixture model estimation composed of 5 clusters. The details of the output components are as follows:

• call the matched call

• data a matrix, the input data matrix

• modelName a character string denoting the model at which the optimal BIC occurs

• n an integer, the number of observations in the data

• d a double, the dimension of the data

• G an integer, the optimal number of mixture components

• BIC a double, all BIC values

• bic a double, the optimal BIC value

• loglik a double, the log-likelihood corresponding to the optimal BIC

• df a double, the number of estimated parameters

• hypvol NA

• parameters a list with the following components:

  • pro a vector of double whose kth component is the mixing proportion for the kth component of the mixture model

  • mean a matrix of double whose kth column is the mean of the kth component of the mixture model

  • variance a list of variance parameters for the model

• z a matrix of double whose [i,k]th entry is the probability that observation i in the test data belongs to the kth class

• classification an array of double, the classification corresponding to z

• uncertainty a double, the uncertainty associated with the classification

See Also

• CNpreprocessing for pre-process DNA copy number (CN) data for detection of CN events.

Examples

## Loading the demo object of class 'Mclust'
data(EMexample)

## Group clusters that have at least 2% of overlap
## The inital object has 5 clusters while the return object has only 
## 4 clusters
CNprep:::consolidate(EMexample, minover=0.2)

KrasnitzLab/CNprep documentation built on May 28, 2022, 8:32 p.m.