Finite Mixture Modeling for Raw and Binned Data
Binning the Raw Data
Bootstrap Likelihood Ratio Test for Finite Mixture Models
The Density of Finite Mixture Models
Initialization of the EM Algorithm
Finite Mixture Modeling for Raw Data and Binned Data
Finite Mixture Modeling for Raw and Binned Data
Plot Bootstrap Likelihood Ratio Test
Plotting the Fitted Mixture Models
Plot Method for Class selectEM
Print Method for Class mixfitEM
Print Method for Class selectEM
Reinstate the Binned Data to the Raw Data
Generating Random Data From A Gamma Mixture Model
Generating Random Data From A Lognormal Mixture Model
Generating Random Data From A Normal Mixture Model
Generating Random Data From A Weibull Mixture Model
Finite Mixture Model Selection by Information Criterion
Parameter Conversion for Weibull Distribution
Parameter Conversion for Gamma Distribution
Parameter Conversion for Lognormal Distribution
Parameter Conversion for Weibull Distribution
Parameter Conversion for Lognormal Distribution
Parameter Conversion for Gamma Distribution
Performs maximum likelihood estimation for finite mixture models for families including Normal, Weibull, Gamma and Lognormal by using EM algorithm, together with Newton-Raphson algorithm or bisection method when necessary. It also conducts mixture model selection by using information criteria or bootstrap likelihood ratio test. The data used for mixture model fitting can be raw data or binned data. The model fitting process is accelerated by using R package 'Rcpp'.