Mixture Models: Parametric, Semiparametric, and Robust

[Up] [Top]

Documentation for package ‘MixSemiRob’ version 1.0.0

Help Pages

AFDP AFDP data contains the 11 sensor measures aggregated over one hour (by means of average or sum) from a gas turbine located in Turkey’s north western region for the purpose of studying flue gas emissions Variable description:
backfitglobal Semiparametric Mixtures of Nonparametric Regressions with Global EM-type Algorithm
backfitlocal Semiparametric Mixtures of Nonparametric Regressions with Local EM-type Algorithm
complhfrequency Complete Likelihood Frequency Method for Label Switching
distlatfrequency Euclidean Distance Based Labeling Method for Label Switching
elbow Elbow data This dataset contains elbow dimension measurements on 507 individuals. The 247 men and 260 women were primarily individuals in their twenties and thirties, with a scattering of older men and women, all exercising several hours a week. Variable description: Elbow: elbow diameter, sum of two elbows
EMlogconc Clustering with Mixtures of Log-concave Distributions using EM Algorithm (Univariate)
EMlogconcHD Clustering with mixtures of log-concave distributions using EM Algorithm (Multivariate)
EMnormal Parameter Estimation of Multivariate Normal Mixture Using EM Algorithm
fcdf inverse fcdf
gen_mixreg Semiparametric Mixture Data Generator
gen_mixreg1 Varpop function Data Generator
Hypothesis_test Hypothesis testing for finite mixture models
KDEEM Kernel Density-based EM type algorithm for Semiparametric Mixture Regression with Unspecified Error Distributions
KDEEM.H Kernel Density-based EM type algorithm for Semiparametric Mixture Regression with Unspecified Homogenous Error Distributions
KDEEM.LSE Kernel Density-based EM type algorithm with Least Square Estimation for Semiparametric Mixture Regression with Unspecified Homogenous Error Distributions
mixbino Nonparametric Mixture of Binomial Regression with a Degenerate Component
mixbinosemi Semiparametric Mixture of Binomial Regression with a Degenerate Component
mixbinosemifull Estimation of Semiparametric Mixture of Binomial Regression with a Degenerate Component Using Full Iterative Backfitting Procedure
mixbinosemionestep One-Step Estimation of Semiparametric Mixture of Binomial Regression with a Degenerate Component
mixbspline Mixture of Nonparametric Regressions Using B-spline
mixlin Traditional MLE based mixture regression assuming the normal error density
mixlinrb_bi Robust EM algorithm to fit the mixture of linear regression based on bisquare function
mixlinrb_bione Robust EM algorithm to fit the mixture of linear regression based on bisquare function with one initial value
mixlint Robust Mixture Regression Based on T-distribution
mixlintv Robust Mixture Regression Based on T-distribution mixlintv adaptively estimates the mixture regression parameters robustly assuming the error distribution is t-distribution
mixmnorm Parameter Estimation for Multivariate Normal Mixture
mixnorm Normal Likelihood Based Method for Label Switching
mixonekn Two normal component mixture estimation
mixreg_CWRM Trimmed Cluster Weighted Restricted Model
mixreg_Lap Robust Mixture Regression Based on Laplace Distribution
MixReg_Pvary Estimate Mixture of Regression Models with Varying Mixing Proportions
mixscale Continuous scale mixture approach for parametric mixture model
mphd Minimum profile Hellinger distance estimation for a semiparametric mixture model
NBA NBA data The data set contains four descriptive statistics for all 105 guards for the 1992–1993 season. There are many ways to measure the (statistical) performance of guards in the NBA. Of interest is how the height of the player, minutes per game and free throw percentage affect points per game. Variable description: Height: height of the player MPG: minutes per game FTP: free throw percentage PPM: points per game
paretomix1 Maximum Smoothed Likelihood Estimation for a Class of Semiparametric Pareto Mixture Densities
pfmix Profile Likelihood Method for Normal Mixture with Unequal Variance
RM2_mixreg Robust Mixture Regression with Thresholding-Embedded EM Algorithm for Penalized Estimation
ROE ROE data contains a total of 2,110 Chinese listed companies on their Return on Equity (ROE), meaning the amount of net income returned as a percentage of shareholders equity, which is an important index to measures a corporation’s profitability. It is also a useful indicator for fundamental analysts to price the value of stocks. Variable description: ROE: Return on Equity
root_selection Root Selection Method for Univariate Finite Normal Mixture Models
sim Fully iterative backfitting estimator (FIB) of single index mixture models
simonestep One step estimation of iterative backfitting estimator (FIB) of single index mixture models
sinvreg Dimension Reduction Based on Sliced Inverse Regression
trimmix Trimmed Likelihood Estimator