Defining the estimand of interest in a clinical trial is crucial to align its planning, design, conduct, analysis, and interpretation. The need for more precise specifications of estimands is highlighted in the draft addendum ICH E9(R1) which was published for public consultation in August 2017. Although not explicitly mentioned in ICH E9(R1), the addendum brings causal reasoning – besides randomization and ITT – into our world of pharmaceutical statistics. In this webinar, we will discuss the link between the ICH E9(R1) and causal inference. Furthermore, per protocol analyses will be discussed from a causal inference perspective and a case study where a principal strata estimand was investigated will be presented.
For more information please click here.
Baldur Magnusson
Novartis Pharma AG
Using principal stratification to address post-randomization events: A case study
In a randomized controlled trial, occurrence of post-randomization events associated with treatment and the primary endpoint may complicate the interpretation of the overall treatment effect. In this presentation, we discuss how these events may be accounted for at the estimand and the estimator level in the context of a recent case study. We define a principal stratification estimand derived from the scientific question of interest. Consideration is given to identifying assumptions, model-based derivation of an estimator, handling of covariates and missing data. We also discuss the role of sensitivity analyses.
Daniel Scharfstein Professor of Biostatistics, Johns Hopkins Bloomberg School of Public Health
Estimands and Causal Inference
Recently, the ICH proposed an addendum to the E9 Guidance: Statistical Principles for Clinical Trials. This addendum is focused on estimands and sensitivity analysis for randomized trials with intercurrent events. In this webinar, I will discuss the potential outcomes framework for causal inference and use it to formally define estimands that address different types of intercurrent events. I will then discuss the assumptions required to identify these estimands from the observable data and discuss the important role of sensitivity analysis.
Estimating Causal Effects in Clinical Endpoint Bioequivalence Studies in the Presence of Treatment Noncompliance and Missing Data
In clinical endpoint bioequivalence (BE) studies, the primary analysis for assessing equivalence between a generic and an innovator product is usually based on the observed per-protocol (PP) population (i.e., completers and compliers in general). The FDA Missing Data Working Group and the ICH E9 Revision 1 Working Group recommended using “causal estimands of primary interest.” The analysis based on the PP population, however, is not generally causal because PP is determined post-treatment, hence conditioning on it may introduce selection bias. To date, no causal inference has been proposed to assess to equivalence. In this paper, we propose a causal framework and co-primary causal estimands to test equivalence by applying Frangakis and Rubin (2002)’s principal stratification in causal inference. We identify three conditions when the current PP estimator is unbiased for one of the proposed co-primary causal estimands – the“Survivor Average Causal Effect” (SACE) estimand. Simulation was used to demonstrate the bias, type 1 error, and power associated with the PP estimator when these three conditions are not met. We also propose a tipping point sensitivity analysis to evaluate the robustness of the current PP estimator (primary analysis) in testing equivalence when the underlying sensitivity parameters vary across a clinically meaningful range. Data from a clinical endpoint BE study is used to illustrate the proposed co-primary causal estimands and sensitivity analysis method. Our work starts causal evaluation of equivalence assessment in clinical endpoint BE studies with non-compliance and missing data, and can be applied to clinical biosimilar and non-inferiority studies.
*The views expressed in this article represent the opinions of the authors, and do not represent the views and/or policies of the U.S. Food and Drug Administration.
Defining the estimand of interest in a clinical trial is crucial to align its planning, design, conduct, analysis, and interpretation. The need for more precise specifications of estimands is highlighted in the draft addendum ICH E9(R1) which was published for public consultation in August 2017. Although not explicitly mentioned in ICH E9(R1), the addendum brings causal reasoning – besides randomization and ITT – into our world of pharmaceutical statistics. In this webinar, we will discuss the link between the ICH E9(R1) and causal inference. Furthermore, per protocol analyses will be discussed from a causal inference perspective and a case study where a principal strata estimand was investigated will be presented.
For more information please click here.
Baldur Magnusson
Novartis Pharma AG
Using principal stratification to address post-randomization events: A case study
In a randomized controlled trial, occurrence of post-randomization events associated with treatment and the primary endpoint may complicate the interpretation of the overall treatment effect. In this presentation, we discuss how these events may be accounted for at the estimand and the estimator level in the context of a recent case study. We define a principal stratification estimand derived from the scientific question of interest. Consideration is given to identifying assumptions, model-based derivation of an estimator, handling of covariates and missing data. We also discuss the role of sensitivity analyses.
Daniel Scharfstein Professor of Biostatistics, Johns Hopkins Bloomberg School of Public Health
Estimands and Causal Inference
Recently, the ICH proposed an addendum to the E9 Guidance: Statistical Principles for Clinical Trials. This addendum is focused on estimands and sensitivity analysis for randomized trials with intercurrent events. In this webinar, I will discuss the potential outcomes framework for causal inference and use it to formally define estimands that address different types of intercurrent events. I will then discuss the assumptions required to identify these estimands from the observable data and discuss the important role of sensitivity analysis.
Estimating Causal Effects in Clinical Endpoint Bioequivalence Studies in the Presence of Treatment Noncompliance and Missing Data
In clinical endpoint bioequivalence (BE) studies, the primary analysis for assessing equivalence between a generic and an innovator product is usually based on the observed per-protocol (PP) population (i.e., completers and compliers in general). The FDA Missing Data Working Group and the ICH E9 Revision 1 Working Group recommended using “causal estimands of primary interest.” The analysis based on the PP population, however, is not generally causal because PP is determined post-treatment, hence conditioning on it may introduce selection bias. To date, no causal inference has been proposed to assess to equivalence. In this paper, we propose a causal framework and co-primary causal estimands to test equivalence by applying Frangakis and Rubin (2002)’s principal stratification in causal inference. We identify three conditions when the current PP estimator is unbiased for one of the proposed co-primary causal estimands – the“Survivor Average Causal Effect” (SACE) estimand. Simulation was used to demonstrate the bias, type 1 error, and power associated with the PP estimator when these three conditions are not met. We also propose a tipping point sensitivity analysis to evaluate the robustness of the current PP estimator (primary analysis) in testing equivalence when the underlying sensitivity parameters vary across a clinically meaningful range. Data from a clinical endpoint BE study is used to illustrate the proposed co-primary causal estimands and sensitivity analysis method. Our work starts causal evaluation of equivalence assessment in clinical endpoint BE studies with non-compliance and missing data, and can be applied to clinical biosimilar and non-inferiority studies.
*The views expressed in this article represent the opinions of the authors, and do not represent the views and/or policies of the U.S. Food and Drug Administration.
Defining the estimand of interest in a clinical trial is crucial to align its planning, design, conduct, analysis, and interpretation. The need for more precise specifications of estimands is highlighted in the draft addendum ICH E9(R1) which was published for public consultation in August 2017. Although not explicitly mentioned in ICH E9(R1), the addendum brings causal reasoning – besides randomization and ITT – into our world of pharmaceutical statistics. In this webinar, we will discuss the link between the ICH E9(R1) and causal inference. Furthermore, per protocol analyses will be discussed from a causal inference perspective and a case study where a principal strata estimand was investigated will be presented.
For more information please click here.
Baldur Magnusson
Novartis Pharma AG
Using principal stratification to address post-randomization events: A case study
In a randomized controlled trial, occurrence of post-randomization events associated with treatment and the primary endpoint may complicate the interpretation of the overall treatment effect. In this presentation, we discuss how these events may be accounted for at the estimand and the estimator level in the context of a recent case study. We define a principal stratification estimand derived from the scientific question of interest. Consideration is given to identifying assumptions, model-based derivation of an estimator, handling of covariates and missing data. We also discuss the role of sensitivity analyses.
Daniel Scharfstein Professor of Biostatistics, Johns Hopkins Bloomberg School of Public Health
Estimands and Causal Inference
Recently, the ICH proposed an addendum to the E9 Guidance: Statistical Principles for Clinical Trials. This addendum is focused on estimands and sensitivity analysis for randomized trials with intercurrent events. In this webinar, I will discuss the potential outcomes framework for causal inference and use it to formally define estimands that address different types of intercurrent events. I will then discuss the assumptions required to identify these estimands from the observable data and discuss the important role of sensitivity analysis.
Estimating Causal Effects in Clinical Endpoint Bioequivalence Studies in the Presence of Treatment Noncompliance and Missing Data
In clinical endpoint bioequivalence (BE) studies, the primary analysis for assessing equivalence between a generic and an innovator product is usually based on the observed per-protocol (PP) population (i.e., completers and compliers in general). The FDA Missing Data Working Group and the ICH E9 Revision 1 Working Group recommended using “causal estimands of primary interest.” The analysis based on the PP population, however, is not generally causal because PP is determined post-treatment, hence conditioning on it may introduce selection bias. To date, no causal inference has been proposed to assess to equivalence. In this paper, we propose a causal framework and co-primary causal estimands to test equivalence by applying Frangakis and Rubin (2002)’s principal stratification in causal inference. We identify three conditions when the current PP estimator is unbiased for one of the proposed co-primary causal estimands – the“Survivor Average Causal Effect” (SACE) estimand. Simulation was used to demonstrate the bias, type 1 error, and power associated with the PP estimator when these three conditions are not met. We also propose a tipping point sensitivity analysis to evaluate the robustness of the current PP estimator (primary analysis) in testing equivalence when the underlying sensitivity parameters vary across a clinically meaningful range. Data from a clinical endpoint BE study is used to illustrate the proposed co-primary causal estimands and sensitivity analysis method. Our work starts causal evaluation of equivalence assessment in clinical endpoint BE studies with non-compliance and missing data, and can be applied to clinical biosimilar and non-inferiority studies.
*The views expressed in this article represent the opinions of the authors, and do not represent the views and/or policies of the U.S. Food and Drug Administration.
Defining the estimand of interest in a clinical trial is crucial to align its planning, design, conduct, analysis, and interpretation. The need for more precise specifications of estimands is highlighted in the draft addendum ICH E9(R1) which was published for public consultation in August 2017. Although not explicitly mentioned in ICH E9(R1), the addendum brings causal reasoning – besides randomization and ITT – into our world of pharmaceutical statistics. In this webinar, we will discuss the link between the ICH E9(R1) and causal inference. Furthermore, per protocol analyses will be discussed from a causal inference perspective and a case study where a principal strata estimand was investigated will be presented.
For more information please click here.
Baldur Magnusson
Novartis Pharma AG
Using principal stratification to address post-randomization events: A case study
In a randomized controlled trial, occurrence of post-randomization events associated with treatment and the primary endpoint may complicate the interpretation of the overall treatment effect. In this presentation, we discuss how these events may be accounted for at the estimand and the estimator level in the context of a recent case study. We define a principal stratification estimand derived from the scientific question of interest. Consideration is given to identifying assumptions, model-based derivation of an estimator, handling of covariates and missing data. We also discuss the role of sensitivity analyses.
Daniel Scharfstein Professor of Biostatistics, Johns Hopkins Bloomberg School of Public Health
Estimands and Causal Inference
Recently, the ICH proposed an addendum to the E9 Guidance: Statistical Principles for Clinical Trials. This addendum is focused on estimands and sensitivity analysis for randomized trials with intercurrent events. In this webinar, I will discuss the potential outcomes framework for causal inference and use it to formally define estimands that address different types of intercurrent events. I will then discuss the assumptions required to identify these estimands from the observable data and discuss the important role of sensitivity analysis.
Estimating Causal Effects in Clinical Endpoint Bioequivalence Studies in the Presence of Treatment Noncompliance and Missing Data
In clinical endpoint bioequivalence (BE) studies, the primary analysis for assessing equivalence between a generic and an innovator product is usually based on the observed per-protocol (PP) population (i.e., completers and compliers in general). The FDA Missing Data Working Group and the ICH E9 Revision 1 Working Group recommended using “causal estimands of primary interest.” The analysis based on the PP population, however, is not generally causal because PP is determined post-treatment, hence conditioning on it may introduce selection bias. To date, no causal inference has been proposed to assess to equivalence. In this paper, we propose a causal framework and co-primary causal estimands to test equivalence by applying Frangakis and Rubin (2002)’s principal stratification in causal inference. We identify three conditions when the current PP estimator is unbiased for one of the proposed co-primary causal estimands – the“Survivor Average Causal Effect” (SACE) estimand. Simulation was used to demonstrate the bias, type 1 error, and power associated with the PP estimator when these three conditions are not met. We also propose a tipping point sensitivity analysis to evaluate the robustness of the current PP estimator (primary analysis) in testing equivalence when the underlying sensitivity parameters vary across a clinically meaningful range. Data from a clinical endpoint BE study is used to illustrate the proposed co-primary causal estimands and sensitivity analysis method. Our work starts causal evaluation of equivalence assessment in clinical endpoint BE studies with non-compliance and missing data, and can be applied to clinical biosimilar and non-inferiority studies.
*The views expressed in this article represent the opinions of the authors, and do not represent the views and/or policies of the U.S. Food and Drug Administration.
Defining the estimand of interest in a clinical trial is crucial to align its planning, design, conduct, analysis, and interpretation. The need for more precise specifications of estimands is highlighted in the draft addendum ICH E9(R1) which was published for public consultation in August 2017. Although not explicitly mentioned in ICH E9(R1), the addendum brings causal reasoning – besides randomization and ITT – into our world of pharmaceutical statistics. In this webinar, we will discuss the link between the ICH E9(R1) and causal inference. Furthermore, per protocol analyses will be discussed from a causal inference perspective and a case study where a principal strata estimand was investigated will be presented.
For more information please click here.
Baldur Magnusson
Novartis Pharma AG
Using principal stratification to address post-randomization events: A case study
In a randomized controlled trial, occurrence of post-randomization events associated with treatment and the primary endpoint may complicate the interpretation of the overall treatment effect. In this presentation, we discuss how these events may be accounted for at the estimand and the estimator level in the context of a recent case study. We define a principal stratification estimand derived from the scientific question of interest. Consideration is given to identifying assumptions, model-based derivation of an estimator, handling of covariates and missing data. We also discuss the role of sensitivity analyses.
Daniel Scharfstein Professor of Biostatistics, Johns Hopkins Bloomberg School of Public Health
Estimands and Causal Inference
Recently, the ICH proposed an addendum to the E9 Guidance: Statistical Principles for Clinical Trials. This addendum is focused on estimands and sensitivity analysis for randomized trials with intercurrent events. In this webinar, I will discuss the potential outcomes framework for causal inference and use it to formally define estimands that address different types of intercurrent events. I will then discuss the assumptions required to identify these estimands from the observable data and discuss the important role of sensitivity analysis.
Estimating Causal Effects in Clinical Endpoint Bioequivalence Studies in the Presence of Treatment Noncompliance and Missing Data
In clinical endpoint bioequivalence (BE) studies, the primary analysis for assessing equivalence between a generic and an innovator product is usually based on the observed per-protocol (PP) population (i.e., completers and compliers in general). The FDA Missing Data Working Group and the ICH E9 Revision 1 Working Group recommended using “causal estimands of primary interest.” The analysis based on the PP population, however, is not generally causal because PP is determined post-treatment, hence conditioning on it may introduce selection bias. To date, no causal inference has been proposed to assess to equivalence. In this paper, we propose a causal framework and co-primary causal estimands to test equivalence by applying Frangakis and Rubin (2002)’s principal stratification in causal inference. We identify three conditions when the current PP estimator is unbiased for one of the proposed co-primary causal estimands – the“Survivor Average Causal Effect” (SACE) estimand. Simulation was used to demonstrate the bias, type 1 error, and power associated with the PP estimator when these three conditions are not met. We also propose a tipping point sensitivity analysis to evaluate the robustness of the current PP estimator (primary analysis) in testing equivalence when the underlying sensitivity parameters vary across a clinically meaningful range. Data from a clinical endpoint BE study is used to illustrate the proposed co-primary causal estimands and sensitivity analysis method. Our work starts causal evaluation of equivalence assessment in clinical endpoint BE studies with non-compliance and missing data, and can be applied to clinical biosimilar and non-inferiority studies.
*The views expressed in this article represent the opinions of the authors, and do not represent the views and/or policies of the U.S. Food and Drug Administration.
Defining the estimand of interest in a clinical trial is crucial to align its planning, design, conduct, analysis, and interpretation. The need for more precise specifications of estimands is highlighted in the draft addendum ICH E9(R1) which was published for public consultation in August 2017. Although not explicitly mentioned in ICH E9(R1), the addendum brings causal reasoning – besides randomization and ITT – into our world of pharmaceutical statistics. In this webinar, we will discuss the link between the ICH E9(R1) and causal inference. Furthermore, per protocol analyses will be discussed from a causal inference perspective and a case study where a principal strata estimand was investigated will be presented.
For more information please click here.
Baldur Magnusson
Novartis Pharma AG
Using principal stratification to address post-randomization events: A case study
In a randomized controlled trial, occurrence of post-randomization events associated with treatment and the primary endpoint may complicate the interpretation of the overall treatment effect. In this presentation, we discuss how these events may be accounted for at the estimand and the estimator level in the context of a recent case study. We define a principal stratification estimand derived from the scientific question of interest. Consideration is given to identifying assumptions, model-based derivation of an estimator, handling of covariates and missing data. We also discuss the role of sensitivity analyses.
Daniel Scharfstein Professor of Biostatistics, Johns Hopkins Bloomberg School of Public Health
Estimands and Causal Inference
Recently, the ICH proposed an addendum to the E9 Guidance: Statistical Principles for Clinical Trials. This addendum is focused on estimands and sensitivity analysis for randomized trials with intercurrent events. In this webinar, I will discuss the potential outcomes framework for causal inference and use it to formally define estimands that address different types of intercurrent events. I will then discuss the assumptions required to identify these estimands from the observable data and discuss the important role of sensitivity analysis.
Estimating Causal Effects in Clinical Endpoint Bioequivalence Studies in the Presence of Treatment Noncompliance and Missing Data
In clinical endpoint bioequivalence (BE) studies, the primary analysis for assessing equivalence between a generic and an innovator product is usually based on the observed per-protocol (PP) population (i.e., completers and compliers in general). The FDA Missing Data Working Group and the ICH E9 Revision 1 Working Group recommended using “causal estimands of primary interest.” The analysis based on the PP population, however, is not generally causal because PP is determined post-treatment, hence conditioning on it may introduce selection bias. To date, no causal inference has been proposed to assess to equivalence. In this paper, we propose a causal framework and co-primary causal estimands to test equivalence by applying Frangakis and Rubin (2002)’s principal stratification in causal inference. We identify three conditions when the current PP estimator is unbiased for one of the proposed co-primary causal estimands – the“Survivor Average Causal Effect” (SACE) estimand. Simulation was used to demonstrate the bias, type 1 error, and power associated with the PP estimator when these three conditions are not met. We also propose a tipping point sensitivity analysis to evaluate the robustness of the current PP estimator (primary analysis) in testing equivalence when the underlying sensitivity parameters vary across a clinically meaningful range. Data from a clinical endpoint BE study is used to illustrate the proposed co-primary causal estimands and sensitivity analysis method. Our work starts causal evaluation of equivalence assessment in clinical endpoint BE studies with non-compliance and missing data, and can be applied to clinical biosimilar and non-inferiority studies.
*The views expressed in this article represent the opinions of the authors, and do not represent the views and/or policies of the U.S. Food and Drug Administration.
PSI Introduction to Industry Training (ITIT) Course - 2025/2026
An introductory course giving an overview of the pharmaceutical industry and the drug development process as a whole, aimed at those with 1-3 years' experience. It comprises of six 2-day sessions covering a range of topics including Research and Development, Toxicology, Data Management and the Role of a CRO, Clinical Trials, Reimbursement, and Marketing.
Joint PSI/EFSPI Visualisation SIG 'Wonderful Wednesday' Webinars
Our monthly webinar explores examples of innovative data visualisations relevant to our day to day work. Each month a new dataset is provided from a clinical trial or other relevant example, and participants are invited to submit a graphic that communicates interesting and relevant characteristics of the data.
Urgent Meeting: Medical Statistician Apprenticeship Scheme
The UK government have recently announced that level 7 apprenticeships must be fully funded by the employer from January 2026, for any apprentice over the age of 21. With funding for MSc's at an all time low, and universities courses facing closures, the apprenticeship scheme remains as important as ever, as a tool to encourage new statisticians into our industry. In this dedicated meeting, Valerie Millar (chair of the apprenticeship scheme) will provide full updates on the government changes and seek feedback and ideas from employers, universities and apprentices on how to keep this scheme successfully running for many years to come.
PSI Webinar: Methodology and first results of the iRISE (improving Reproducibility In SciencE) consortium
This 1-hour webinar will be an opportunity to hear about the methodology and first results of the iRISE consortium. iRISE is working towards a better understanding of reproducibility and the interventions that work to improve it. At the end of the presentation there will also be the opportunity to ask questions.
One-day Event: Change Management for Moving to R/Open-Source
This one-day event focuses on the comprehensive management of transitioning to R/Open-Source, addressing the challenges and providing actionable insights. Attendees will participate in sessions covering essential topics such as training best practices, creating strategic plans, making the case to senior management, and managing both statistical and programming aspects of the transition.
PSI Book Club - The Art of Explanation: How to Communicate with Clarity and Confidence
Develop your non-technical skills by reading The Art of Explanation by Ros Atkins and joining the Sept-Dec 2025 book club. You will be invited to join facilitated discussions of the concepts and ideas and apply skills from the book in-between sessions.
This course is aimed at biostatisticians with no or some pediatric drug development experience who are interested to further their understanding. We will give you an introduction to the pediatric drug development landscape. This will include identifying the key regulations and processes governing pediatric development, a discussion on the needs and challenges when conducting pediatric research and a focus on the ways to overcome these challenges from a statistical perspective.
This networking event is aimed at statisticians that are new to the pharmaceutical industry who wish to meet colleagues from different companies and backgrounds.
EFSPI/PSI Causal Inference SIG Webinar: Instrumental Variable Methods
The webinar is targeted at statisticians working in the pharmaceutical industry, and the objective is to 1) provide a basic understanding of IV methodology including how it relates to causal inference, and 2) present two inspirational pharma-relevant applications.
This networking event is aimed at statisticians that are new to the pharmaceutical industry who wish to meet colleagues from different companies and backgrounds.
This is an exciting, new opportunity for an experienced Statistician looking to take the next step in their career. Offered as a remote or hybrid position aligned with our site in Harrogate, North Yorkshire.