ISCB Course on Bayesian Methods for Missing Covariates in Longitudinal Studies

Czech National Group of the International Society for Clinical Biostatistics, 

in cooperation with the Institute of Computer Science AS CR in Prague, and, 

Faculty of Mathematics and Physics of the Charles University in Prague

are delighted to invite you to attend

 One-day in-person ISCB course on

„Bayesian Methods for Missing Covariates in Longitudinal Studies“

presented by

Nicole S. Erler [1] and Emmanuel M.E.H. Lesaffre [2]

[1]  Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Utrecht University, The Netherlands

[2] L-Biostat, KU Leuven, Belgium

Brief Biography

Prof. Emeritus Emmanuel Lesaffre is the author of the Wiley book Bayesian Biostatistics (2012), and a leading editor of the Chapman and Hall book Bayesian Methods in Pharmaceutical Research. He has taught courses on Bayesian methods in clinical studies on Master level at the University of Hasselt and KU Leuven both in Belgium, Erasmus Medical Center (Rotterdam, the Netherlands) and that for more than 25 years. He has also taught short course on Bayesian methods at various universities abroad and clinical research institutes. In Prague he taught two ISCB courses in the past: "Principles of Biostatistical Reasoning: A Practical Introduction to Statistical Methods in Clinical Research" (2014) and, together with Arnošt Komárek, "Analysis of Interval-Censored Data: Does Interval Censoring Matter?" (2018).

Dr. Nicole Erler is an Assistant Professor at the department of Data Science and Biostatistics at the Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht where her research focuses on (intensive) longitudinal data, joint modelling, and personalised dynamic prediction. Nicole obtained her PhD at the Erasmus Medical Center, Rotterdam, on the topic of Bayesian Imputation of Missing Covariates. She has experience teaching courses on Missing Data in Clinical Research and introductory courses to Biostatistics and R. Nicole is author and maintainer of the R package JointAI that performs fully Bayesian analysis of incomplete data.

WHERE

We are happy to confirm that the course is being scheduled as an in-person course only, virtual attendance will not be possible.

The course will take place on Friday 7 November 2025 at the Institute of Computer Science of the Czech Academy of Sciences, Pod Vodárenskou věží 2, 182 00 Prague 8 - Ládví.

The course material (slides) will be made available to registered course participants approximately 1 week ahead of the course schedule. 

WHEN                                               

7 November 2025 (Friday), 9:00 AM through 5:00 PM Central European Time (CET), i.e. a winter time. In the Czech Republic, the winter time begins (clocks go back) on the last Sunday in October and ends on the last Saturday in March (CET or Universal Coordinate Time (UTC) + 1).

REGISTRATION DEADLINE       

31st October 2025 (Friday), 12:00 CET (noon-time)

Important !!: 

• Before you make a payment, please, make an e-mail inquiry with the Course Secretary, Ms. Lenka Semeráková, for confirmation of your participation (semerakova@cs.cas.cz)

• The number of course participants is limited to 30. Should the course reach its capacity, a notification will be placed here

• The payment has to be received by this date

COURSE ABSTRACT

Missing values often complicate the analysis of observational data. Multiple imputation (MI) is considered to be the “gold standard” for handling incomplete covariates. Developed at the beginning of the Computer Age, it is based on Bayesian ideas, but uses less computationally demanding procedures. In complex settings, e.g. involving non-linear associations or multi-level data, the assumptions underlying commonly used MI algorithms are, however, often violated, leading to possibly biased results.

With the advancements of computational power, a fully Bayesian approach, allowing us to simultaneously estimate parameters of interest and impute missing values, is now feasible. This approach is theoretically valid and superior to MI in complex settings. Highly complex non-standard missing data models can relatively easily be implemented with the help of freely available software such as the R package JointAI.

In this course, we briefly review the essentials of multi-level data, Bayesian concepts and (multiple) imputation. The main focus is on the Bayesian approach to missing values in covariates in multi-level and longitudinal studies, which is motivated and illustrated using examples from clinical and epidemiological studies. In practical sessions, we will show the capabilities of the R package JointAI, starting with simpler standard settings and extending to highly complex joint models for longitudinal and survival data and imputation in non-standard settings.

KEYWORDS

Missing Data, Imputation, Bayesian Methods, Longitudinal Data

REFERENCES

1. Nicole S. Erler, Dimitris Rizopoulos, Emmanuel M.E.H. Lesaffre. JointAI: Joint Analysis and Imputation of Incomplete Data in R. Journal of Statistical Software, 2021, 100, 1907.10867. 

2. Nicole S. Erler, Dimitris Rizopoulos, Vincent W.V. Jaddoe, Oscar H. Franco, Emmanuel M.E.H. Lesaffre. Bayesian imputation of time-varying covariates in linear mixed models. Statistical Methods in Medical Research, 2019, 28 (2), 555–568. 

3. Nicole S. Erler, Dimitris Rizopoulos, Joost van Rosmalen, Vincent W.V. Jaddoe, Oscar H. Franco, Emmanuel M.E.H. Lesaffre. Dealing with missing covariates in epidemiologic studies: A comparison between multiple imputation and a full Bayesian approach. Statistics in Medicine, 2016, 35 (17), 2955 – 2974. 

COURSE SCHEDULE

• REGISTRATION

  • 8:30 - 9:00 Registration of the participants

• LUNCH

  • 12:30 - 13:30 Lunch break

• COFFEE BREAKS

  • 30 minutes between the successive sessions

The course consists of four blocks of approximately 90 minutes each; two in the morning and two in the afternoon

• Morning 1

  • Session 1 (09:00 - 10:30) Introduction & basics of longitudinal data analysis and missing values

• Morning 2

  • Session 2 (11:00 - 12:30) Introduction to the Bayesian framework

• Afternoon 1

  • Session 3 (13:30 - 15:00) (Bayesian) Imputation of missing values in longitudinal settings

• Afternoon 2

  • Session 4 (15:30 - 17:00) Extensions: (Bayesian) Imputation in time-to-event settings, Summary, and Closing

In each session, there will be lectures as well as computer practicals (in R, using the package JointAI).

REGISTRATION RATES

Early Bird (until TUESDAY 30 September 2025)

ISCB student member* 1 500 CZK (60 EUR)

ISCB regular member* 2 000 CZK (80 EUR)

Non-ISCB member – academia 4 000 CZK (160 EUR)

Non-ISCB member – business 10 000 CZK (400 EUR)

Regular (1 October – 31 October 2025)

ISCB student member* 2 000 CZK (80 EUR)

ISCB regular member* 2 500 CZK (100 EUR)

Non-ISCB member – academia 5 250 CZK (210 EUR)

Non-ISCB member – business 13 250 CZK (530 EUR)

(*) Note: ISCB membership is required for 2024 and 2025. For doctoral students, the ISCB membership for 2025 will be sufficient.

Payments by bank transfer ONLY

(All international payments have to be made in EUR)

ACCOUNT INFORMATION

For all domestic (CZK) and international transfers (EUR):

Bank's name and address   Fio banka, a.s., V Celnici 1028/10, 11721 Praha 1, Czech Republic

Account owner                      Mezinárodní společnost pro klinickou biostatistiku v České republice, z.s.

Account number                   2100009829 / 2010  

IBAN                                        CZ3820100000002100009829

BIC code/SWIFT                     FIOBCZPPXXX

• For institutions making payments on behalf of their employees: The payment identification number (variabilní symbol) is 20251107

• Please, remember to state the name of an employee on whose behalf the payment is made in the comment for the payment recipient (poznámka pro příjemce).

CANCELLATION POLICY

Cancellation fees apply as explained below:

• before 1 October 2025: 10 EUR

• 1 October through 15 October 2025: 40 EUR

• after 15 October 2025: full paid amount

COURSE VENUE

Institute of Computer Science of the Czech Academy of Sciences

Lecture Room #318

Pod Vodarenskou vezi 2, 182 00 Prague, Czechia

https://maps.app.goo.gl/QpHXUHVrBixgKsRM7

COURSE SECRETARY

Ms. Lenka Semeráková, Institute of Computer Science, Czech Academy of Sciences, tel. +420 724 021 119, e-mail: semerakova@cs.cas.cz