Dr. Felix Heinzl

Research emphases

• Random effects and mixed models
• Dirichlet processes

Publications

• Heinzl, F. & G. Tutz (2016): Additive mixed models with approximate Dirichlet process mixtures: the EM approach. Statistics and Computing, 26(1), 73-92.
Preliminary version: Technical Report No. 138, Department of Statistics, LMU München.

• Giessing, S., F. Heinzl, B. Kleber & A. Wilke (2014): Geheimhaltung beim Zensus 2011. Wirtschaft und Statistik, November 2014, 641-647.

• Heinzl, F. & G. Tutz (2014): Clustering in linear mixed models with a group fused lasso penalty. Biometrical Journal, 56(1), 44-68.
Preliminary version: Technical Report No. 123, Department of Statistics, LMU München.

• Heinzl, F. & G. Tutz (2013): Clustering in linear mixed models with approximate Dirichlet process mixtures using EM algorithm. Statistical Modelling, 13(1), 41-67.
Preliminary version: Technical Report No. 115, Department of Statistics, LMU München.

• Heinzl, F., L. Fahrmeir & T. Kneib (2012): Additive mixed models with Dirichlet process mixture and P-spline priors. Advances in Statistical Analysis, 96(1), 47-68.
Preliminary version: Technical Report No. 68, Department of Statistics, LMU München.

Talks

• Clustering in linear mixed models with Dirichlet process mixtures using EM algorithm, July 16, 2012,
  IWSM 27 Prague
• Linear mixed models with a penalized normal mixture as random effects distribution, September 12, 2011,
  CEN 2011 Zurich
• EM algorithm for linear mixed models with Dirichlet process mixtures, September 13, 2010,
  16. DStatG-Nachwuchsworkshop Nuremberg
• Additive mixed models with Dirichlet process mixture and P-Spline priors, March 25, 2010,
  DAGStat2010 Dortmund

Dissertation

• Clustering in linear and additive mixed models (January 2013)

Diploma Thesis (in german)

• Nonparametric Bayes inference in additive mixed models (February 2009)

Software

• R-package clustmixed for clustering in linear and additive mixed models
• Contribution to R-package BayesX
• Additive mixed models with Dirichlet process mixture and P-spline priors: amm.dpm.mcmc