Abstract Number:
807
Submission Type:
Topic-Contributed Paper Session
Participants:
Pamela Shaw (1), Malka Gorfine (2), Pamela Shaw (1), Carsten Oliver Schmidt (3), Michael Wallace (4), Marc Henrion (5), Nicholas Bakewell (4)
Institutions:
(1) Kaiser Permanente Washington Health Research Institute, N/A, (2) Tel Aviv University, N/A, (3) University Medicine Greifswald, Germany, (4) N/A, N/A, (5) Malawi Liverpool Wellcome Trust Clinical Research Programme, Malawi
Chair:
Session Organizer:
Pamela Shaw
Kaiser Permanente Washington Health Research Institute
Speaker(s):
Pamela Shaw
Kaiser Permanente Washington Health Research Institute
Marc Henrion
Malawi Liverpool Wellcome Trust Clinical Research Programme
Session Description:
The validity and practical utility of observational medical research depends critically on good study design, excellent data quality, appropriate statistical methods and accurate interpretation of results. Statistical methodology has seen substantial advances in recent decades. Unfortunately, many of these methodological developments are underutilized or ignored in practice, often due to the lack of practical guidance for implementation. These observations motivated the founding of The Strengthening Analytical Thinking in Observational Studies (STRATOS) Initiative in 2011. The objective of STRATOS is to provide accessible and accurate guidance in the design and analysis of observational studies. There are several working groups focused on issues that arise commonly in observational studies, including missing data, initial data analysis, model selection, measurement error, study design, causal inference, survival analysis, and high dimensional data. The developed guidance is intended for applied statisticians and other data analysts with varying levels of statistical education, experience and interests. In this session we will present an overview of the STRATOS Initiative and present some of its recent work.
The first speaker in this session will present an overview of the STRATOS initiative, including its organization, topic areas of focus and accomplishments in the last 13+ years related to educational outreach, publications and novel work to address identified shortcomings in the literature. The 2nd speaker discusses structured implementation of initial data analysis (IDA), which aims to gain insights into the properties and quality of the targeted data. This talk will provide guidance for the role of IDA in statistical analysis plans and the responsible use of IDA results. The 3rd speaker will outline recent contributions of STRATOS Topic Group 4, which focuses on the challenge of measurement error. This includes work addressing the categorization of mismeasured (continuous) variables, addressing uncertainty in post-prediction inference, and recent outreach activities through short, accessible videos. Speaker 4 will provide an overview of the work of STRATOS Topic Group 2 , which considers variable and functional form selection in multivariable analysis. As a concrete example of the group's work, this speaker will present results from a recent review of modeling approaches, with a specific focus on variable and functional form selection, from predictive models developed during the Covid-19 pandemic. Finally, The fifth speaker offers guidance on the use of real-world data (RWD) to assess the effects of long-term drug exposures. This talk will (1) address key study design aspects that focus on the interplay between etiologic pharmacology and principles of pharmacoepidemiology, and (2) present a case example on antidiabetic medications to demonstrate how to appropriately consider key study design aspects.
Talks:
1. Pamela Shaw: Overview of the STRATOS Initiative
2. Carsten Oliver Schmidt: Gaining insights into the properties and quality of the targeted data is the primary goal of Initial Data Analysis (IDA).
3. Michael Wallace: Recent Advances in Measurement Error Within the STRATOS Initiative
4. Marc Y. R. Henrion: STRATOS Topic Group 2 and results from a recent review of Covid-19 predictive models
5. Nicholas Bakewell: Guidance for the design of observational studies to estimate the effects of long-term drug exposure
Sponsors:
ENAR 1
Section on Statistics in Epidemiology 2
WNAR 3
Theme:
Statistics, Data Science, and AI Enriching Society
Yes
Applied
Yes
Estimated Audience Size
Medium (80-150)
I have read and understand that JSM participants must abide by the Participant Guidelines.
Yes
I understand and have communicated to my proposed speakers that JSM participants must register and pay the appropriate registration fee by June 3, 2025. The registration fee is nonrefundable.
I understand