Postdoctoral Researcher in Causal Inference

ZZP36 uurICT
ZZP36 uurICT
Plaats
Leiden, Zuid-Holland
Reageren tot
25 november 2026
Gezien bij de bron
vandaag 12:34
Checkvragen

Kies je bemiddelaar

GreenPepper

ZZP
Maximaal tariefonbekend
Fee10%, gaat van het tarief af (Lage bemiddelingsfee over het uurtarief, per opdracht bepaald; geen percentage gepubliceerd. De fee gaat over het uurtarief, dus de zzp'er draagt hem.)
Reageren totopen tot 25 nov
Transparantie

Omschrijving

About Your Role
You will lead the development of a new sample size framework for nonrandomized studies that adjust for confounding. Such studies are essential when evaluating healthcare interventions that cannot be randomized for ethical or practical reasons. However, suitable methods for determining the required number of participants are currently lacking. Your research will focus on deriving and verifying new statistical methods and testing their usability in real-world studies. Working with clinical collaborators and a panel of end users, you will help ensure these methods meet the needs of researchers.
Your Main Responsibilities Will Include
Derive sample size formulas for different causal effects and methods of confounding adjustment.
Conduct simulation studies to verify the accuracy of the developed formulas.
Validate the framework when designing a prospective non-randomized study and organize meetings with a panel of end users.

Contribute to scientific publications, oversee the development of an open-source R package, and contribute to teaching activities. The position is for 24 months. You will work closely with a software developer who will implement your methods in an open-source R package. Throughout the project, you will have the freedom to shape the methodological approach, with regular input from your supervisors and international collaborators from the STRATOS Initiative's Causal Inference topic group. You will also present your findings at national and international conferences. We support your professional development, providing opportunities to explore your own research ideas and work towards follow-up projects and funding applications.
About Your Workplace
You will work within the Department of Biomedical Data Sciences at the LUMC, which develops, interprets, evaluates and implements advanced statistical methods and data science techniques for (bio)medical research.

Your daily workplace will be the Medical Statistics section, which hosts the largest biostatistics group in the Netherlands. Your project will be embedded in the Caecilia Causal Inference Center, a cross-departmental expertise center for causal inference within the LUMC. You will collaborate closely with clinical partners from the departments of Gynecology at the LUMC and Erasmus MC, who will bring in real-world research questions and data. You will also have access to an international network of causal inference experts through the Causal Inference topic group of the STRATOS Initiative. The project is led by Dr Doranne Thomassen, Dr Nan van Geloven and Prof. Dr Saskia le Cessie, who will supervise you.
About You
Developing statistical methods for causal inference appeals to you, particularly when your quantitative skills can contribute to improving healthcare.

You enjoy exploring complex methodological questions and explaining your findings to others, including clinicians and researchers from different scientific backgrounds. Within an international team of biostatisticians and clinicians, you take initiative, share ideas and collaborate effectively.
In Addition, You Have
A PhD in (Bio)Statistics, Applied Mathematics, Health Data Science or a related field. A track record in developing statistical methodology, preferably in causal inference. Experience deriving theoretical properties of statistical estimators and testing them through simulation studies.
Programming skills, for example in R.
Excellent communication skills in written and spoken English (C1 level or higher).

… lees de volledige omschrijving bij GreenPepper.

Bekijk meer opdrachten

Vergelijkbare opdrachten