Dr. Kristian Kleinke
Kristian Kleinke

Kristian Kleinke

senior lecturer for psychological methods (tenured)

University of Siegen

Biography

I am a psychologist and licensed psychotherapist (behavior therapy) employed with the University of Siegen, Germany, and also the guy responsible for teaching statics in our BSc and MSc psychology programs. I happend upon missing data when I embarked on my diploma thesis in 2006 (well, who didn’t?) and got ensnarled in this fascinating topic ever since. My methodological research interests today (still) include missing data and multiple imputation, as well as robust multiple imputation procedures that can be applied, when parametric assumptions of standard imputation models are violated. I am furthermore interested in structural equation models for longitudinal data (mainly in latent growth curve models).

My non-methods related research focusses on – well it doesn’t really focus. I am interested in many different fields including criminology and various subdomains of clinical psychology. For an overview, see my publications. MI-related publications are listed here.

short CV

Interests
  • missing data and multiple imputation
  • juvenile delinquency and effects of criminal victimization
  • long-term effects of traumata
Education
  • licensed psychotherapist (behavior therapy), 2021

    Landesamt für Soziales, Jugend und Versorgung, Rheinland-Pfalz, Germany

  • Dr. rer. nat., 2014

    Bielefeld University, Germany

  • Diplom in Psychology, 2008

    University of Erlangen-Nürnberg, Germany

  • BSocSc(Hons), 2008

    University of Waikato, New Zealand

My Missing Data Software

package countimp: Multiple imputation of incomplete count data

Description

Count data require special analysis and imputation techniques. countimp provides addon-functions to the popular multiple imputation package mice, and extends mice’s functionality. Imputation models include:

  • the standard Poisson model,
  • the quasi-poisson, and negative binomial model for overdispersed count data,
  • zero-inflation and hurdle models for count data with an excess of zero counts
  • multilevel versions of these models.

Download / Installation

  • countimp version 2 is available from github under the GPL-3 licence.
  • The latest version can be installed from GitHub using function install_git from package devtools:
# install.packages('remotes')
remotes::install_github('kkleinke/countimp')
  • If you find any bugs, please let me know.
  • countimp version 2 is described in detail (+ tutorials, examples) in Chapter 6 of our book.
  • The user’s guide with some applications and Monte Carlo Simulations is available from https://countimp.kleinke.io.

Previous versions

  • For more information about the old countimp 1, see this technical report. Note that countimp version 1 only works with mice version 2.35 or older.

Recent Publications

Workshops

I give one- to three-day workshops on missing data, multiple imputation, and SEM either at your institution or online. To inquire about a workshop, please contact me via Email

Examples

  • Applied multiple imputation. Half day workshop, Heidelberg University Hospital, Heidelberg, Germany (2023)
  • Applied multiple imputation. 3-day workshop, GESIS, Mannheim, Germany (2022)
  • An introduction to structural equation modelling with lavaan in , 2-day workshop, German Centre for Higher Education Research and Science Studies (DZHW), Hannover (2019)
  • An introduction to structural equation modelling in , half-day short course, Hochschule Darmstadt (2019)
  • Missing data imputation in , 3.5-day workshop, Doctorates psychology, University of Zürich (2017)
  • Multiple Imputation, one-day workshop, University of Giessen, Peer mentoring group ‘empirical social research’ (2015).

Consulting

I offer paid statistical consulting for external researchers and for organizations. To inquire about a consulting session, please contact me via Email.

Contact