Iris Eekhout, PhD

Statistician & Senior Scientist

TNO

Biography

Iris Eekhout holds a double master in clinical psychology and methodology and statistics of psychology (Leiden University). She obtained her PhD at the Department of Epidemiology and Biostatistics of the VU University medical centre in Amsterdam. Her dissertation work resulted in novel ways of dealing with missing data in questionnaire items and total scores. Currently, Iris teaches a course on missing data analysis in the epidemiology masters program at VU University medical centre. At TNO, Iris works on a variety of projects as a methodologist and statistical analyst related to child health, e.g., measuring child development (D-score) and adaptive screenings for psycho-social problems (psycat). Her main interests and expertise are missing data methods (multiple imputation), longitudinal (multilevel) modeling, R programming, developing shiny applications, interactive visualizations, psychometrics and measurement.

Interests

Missing data methods (multiple imputation)
Longitudinal (Multilevel) modelling
R programming/shiny apps
Psychometrics and measurement

Education

PhD in Epidemiology & Biostatistics, 2015
VU University, Amsterdam
MSc in Methodology and Statistics, 2010
Leiden University
MSc in Clinical Psychology, 2010
Leiden University
BSc in Psychology, 2008
Leiden University

Posts

From Fixed-Age Screening to Flexible Developmental Assessment

A new interactive tool makes it possible to use the Dutch Developmental Instrument more flexibly in preventive Youth Health Care. By combining the D-score model, Dutch reference data and an accessible Shiny application, the tool helps professionals identify developmental milestones that match a child’s current developmental level. The application supports personalized assessment, strengthens conversations with parents and provides a practical foundation for future adaptive developmental testing.

Iris Eekhout

Last updated on Aug 27, 2026 14 min read

Enhancing Comparability with the D-score

Excited to announce the publication of our latest paper in the prestigious International Journal of Behavioral Development! This study proposes a new unit for child development for children up to 3 years and explores ways to convert existing data into this D-score, offering fresh insights into the field of child development. A heartfelt thanks to all co-authors for their support. Check out the full paper here: https://journals.sagepub.com/doi/10.1177/01650254241294033.

Iris Eekhout & Stef van Buuren

Last updated on Jan 28, 2025 2 min read

Enhancing Comparability with the D-score

Child Development with the D-score

Our blog introduces the revolutionary book Child Development with the D-score, unveiling a pioneering framework that harmonizes childrens diverse milestones onto a single scale. It promises unparalleled comparisons across populations and individuals. The book explores the significance of the D-score, from its construction to computation, catering not only to child development professionals but also policymakers and data scientists. Its an empowering guide to understand and enhance child development. Readers are encouraged to grab this transformative book and embark on an enlightening journey into the world of the D-score!

Edited by Stef van Buuren & Iris Eekhout

Last updated on Jan 9, 2024 2 min read

Missing data mechanisms

In research, missing data occur when a data value is unavailable. Many empirical studies encounter missing data. Missing data can occur in many stages of research due to many different causes in many different forms. Each type of missing data may have different reasons, and also different implication for the methods to deal with the missing data.The underlying reasons for missing data can be described as missing data mechanisms.

Last updated on Jan 9, 2024 15 min read

Missing value analysis

Missing observations are defined as NA in R. Missing data can have different implications for data summaries, analyses and conclusions based on the data with missing values. In this post, different types of missing data are reviewed and explored in data examples.

Last updated on Jan 9, 2024 7 min read

See all posts

Projects

Don’t Miss Out!

Missing data occurs in many empirical studies. It is vital for study results to handle the missing data correctly. The best solution to deal with missing data depends on the reasons for the occurrence of missing data and on the analysis that is planned. In the project a guide was developed to find the best way to deal with missing data in multi-item questionnaires. The website www.missingdata.nl also provides a lot of information about missing data and methodology.

D-score

Children learn to walk, speak, and think at an astonishing pace. The D-score captures this process as a one-number summary. Application of the D-score enables comparisons in child development across populations, groups and individuals.

Rater agreement & reliability

In studies where more than one rater gives a judgement on a certain characteristic, the agreement between the judgements is of interest. Historically, mostly a kappa statistic is used to assess the agreement. However, the kappa statistic is a reliability measure instead of an agreement measure. It is more informative to use the percentage of absolute agreement instead. The reliability of ratings can also be obtained via different methods. The choice between the ICC oneway, ICC consistency and ICC agreement depends on the study design and goals.

Publications

Katharina Preuhs, Iris Eekhout, Rosa Andree, Hilde {van Keulen}, Pepijn {van Empelen} (2026). Effective Behavior Change Techniques for Successful Weight Loss and Weight Loss Maintenance Among Adults With Overweight and Obesity: A Systematic Review and Meta-Analysis. Obesity Reviews, pp. e70195.

Stef van Buuren, Iris Eekhout, Gareth McCray, Jonathan Seiden, Dana C McCoy, Melissa Gladstone, Vanessa Cavallera, Tarun Dua, Maureen M Black, GSED Team (2026). GSED Core Model: A Unified D-score Scale for Early Child Development From Seven Sites. International Journal of Behavioral Development, pp. 01650254261451140.

Iris Eekhout, Yvonne Schonbeck (2026). Interactive Tool for Flexible Developmental Assessment in Youth Health Care. Studies in Health Technology and Informatics, (336), pp. 62–66.

Lisanne Vonk, Paula {van Dommelen}, Iris Eekhout, Noelle N Uilenburg, Paul H Verkerk, Catharina (Kitty) PB {van der Ploeg} (2026). Optimal timing for neonatal hearing screening in Well-Babies. International journal of neonatal screening, (12), pp. 7.

Iris Eekhout, Zeena Harakeh, Minne Fekkes, Jeroen Pronk (2026). Teachers as Informant for Students’ Bullying Involvement: The Impact of Teacher Training on Agreement between Teacher vs. Self-and Peer Reports. International Journal of Bullying Prevention, pp. 1–11.

Iris Eekhout, Renate {van Zoonen}, Sylvia {van der Pal}, Paul H Verkerk, Yvonne Schonbeck (2026). Van Wiechen Continu: het ontwikkelingsonderzoek in de JGZ 0-4 op elk moment, voor elk kind. JGZ Tijdschrift voor jeugdgezondheidszorg.

Stef van Buuren, Iris Eekhout, Gareth McCray, Gillian A Lancaster, Marcus R Waldman, Dana C McCoy, Melissa Gladstone, Vanessa Cavallera, Tarun Dua, Maureen M Black, {others} (2025). Enhancing comparability in early child development assessment with the D-score. International Journal of Behavioral Development, (49), pp. 348–364.

Caren Lanting, Ellian Lebbink, Ernest {de Vroome}, Iris Eekhout (2025). Proportion of cancer attributable to modifiable factors in the Netherlands in 2019: a secondary data analysis. BMJ Public Health, (3).

Lidwine B Mokkink, Iris Eekhout (2025). The measurement properties reliability and measurement error explained--a COSMIN perspective. Journal of clinical epidemiology, pp. 112058.

Meinou HC Theunissen, Marianne S de Wolff, Iris Eekhout, Coryke {van Vulpen}, Sijmen A Reijneveld (2024). A study on the applicability of the Strengths and Difficulties Questionnaire among low-and higher-educated adolescents. Frontiers in psychology, (15), pp. 1289158.

See all publications

Contact

R Packages & shiny

The projects highlighted on the website have R packages attached. The D-score project has multiple R packages available and several shiny application that demonstrate functionalities. The agreement project evolves around one R package and one shiny application.

Reliability and Agreement

Agree: An R package with functions to compute the Reliability and Agreement between multiple raters.
ICC power: A shiny application that can assist sample size decisions for studies on reliability.

Child development with the D-score

dscore
dcalculator: A shiny application to calculate the D-score with your data

Missing data

Missing data mechanism