Nancy Flournoy
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Nancy Flournoy has a total of 63 co-authors. Here are the top co-authors by number of shared publications:
- Sergey Tarima
Institute for Health & Equity, Division of Biostatistics, Medical College of Wisconsin, Milwaukee, Wisconsin, USA
13 shared publications - Kelly Van Lancker
Department of Mathematics, Computer Science and Statistics, Ghent University
4 shared publications - James L. Rosenberger
National Institute of Statistical Sciences, and Department of Statistics, Penn State University, University Park, PA 16802-2111 U.S.A.
3 shared publications Madeline Bauer
Division of Infectious Diseases, Keck School of Medicine, University of Southern California (ret), Los Angeles, CA
3 shared publications- Sarah Zohar
Inserm, Inria, Université Paris Cité UMRS 1346, HeKA Paris France
3 shared publications - Anastasia Ivanova
University of North Carolina at Chapel Hill
2 shared publications
Latest Publications
- Open Access
- 10 June 2025
- Published by Springer Nature in Statistical Papers
- Vol. 66 (5) , 1-28
Maximum likelihood estimation under the Emax model: existence, geometry and efficiency
This study focuses on the estimation of the Emax dose–response model, a widely utilized framework in clinical trials, experiments in pharmacology, agriculture, environmental science, and more. Existing challenges in obtaining maximum likelihood estimates (MLE) for model parameters are often ascribed to computational issues but, in reality, stem from the absence of a MLE. Our contribution provides new understanding and control of all the experimental situations that practitioners might face, guiding them in the estimation process. We derive the exact MLE for a three-point experimental design and identify the two scenarios where the MLE fails to exist. To address these challenges, we propose utilizing Firth’s modified score, which we express analytically as a function of the experimental design. Through a simulation study, we demonstrate that the Firth modification yields a finite estimate in one of the problematic scenarios. For the remaining case, we introduce a design-augmentation strategy akin to a hypothesis test.
- 10 June 2025
- Published by Springer Nature in Statistical Papers
- Vol. 66 (5) , 1-28
Open AccessMaximum likelihood estimation under the Emax model: existence, geometry and efficiency
This study focuses on the estimation of the Emax dose–response model, a widely utilized framework in clinical trials, experiments in pharmacology, agriculture, environmental science, and more. Existing challenges in obtaining maximum likelihood estimates (MLE) for model parameters are often ascribed to computational issues but, in reality, stem from the absence of a MLE. Our contribution provides new understanding and control of all the experimental situations that practitioners might face, guiding them in the estimation process. We derive the exact MLE for a three-point experimental design and identify the two scenarios where the MLE fails to exist. To address these challenges, we propose utilizing Firth’s modified score, which we express analytically as a function of the experimental design. Through a simulation study, we demonstrate that the Firth modification yields a finite estimate in one of the problematic scenarios. For the remaining case, we introduce a design-augmentation strategy akin to a hypothesis test.
- Open Access
- 17 December 2024
- Published by New England Statistical Society in The New England Journal of Statistics in Data Science
- p. 222-233
Up-and-Down: The Most Popular, Most Reliable, and Most Overlooked Dose-Finding Design
Up-and-Down designs (UDDs) are ubiquitous for dose-finding in a wide variety of scientific, engineering, and clinical fields. They are defined by a few simple rules that generate a random walk around the target percentile. UDDs’ combination of robust, tractable behavior, straightforward usage, and good dose-finding performance, has won the trust of practitioners and their consulting analysts across fields and continents. In contrast, in recent decades the statistical dose-finding design field has turned a cold shoulder towards UDDs, and it is quite possible that many younger dose-finding methods researchers are not even aware of this design approach. We present a concise overview of UDDs and their current state-of-the-art methodology, with references for further inquiry. We also revisit the performance comparison between UDDs and novel, more complicated design approaches such as the Continual Reassessment Method and the Bayesian Optimal Interval design, which we group under the term “Aim-for-Target” designs. UDDs fare very well in the comparison, particularly in terms of robustness to sources of variability.
- 17 December 2024
- Published by New England Statistical Society in The New England Journal of Statistics in Data Science
- p. 222-233
Open AccessUp-and-Down: The Most Popular, Most Reliable, and Most Overlooked Dose-Finding Design
Up-and-Down designs (UDDs) are ubiquitous for dose-finding in a wide variety of scientific, engineering, and clinical fields. They are defined by a few simple rules that generate a random walk around the target percentile. UDDs’ combination of robust, tractable behavior, straightforward usage, and good dose-finding performance, has won the trust of practitioners and their consulting analysts across fields and continents. In contrast, in recent decades the statistical dose-finding design field has turned a cold shoulder towards UDDs, and it is quite possible that many younger dose-finding methods researchers are not even aware of this design approach. We present a concise overview of UDDs and their current state-of-the-art methodology, with references for further inquiry. We also revisit the performance comparison between UDDs and novel, more complicated design approaches such as the Continual Reassessment Method and the Bayesian Optimal Interval design, which we group under the term “Aim-for-Target” designs. UDDs fare very well in the comparison, particularly in terms of robustness to sources of variability.
- 17 September 2024
- Published by Springer Nature in Statistical Papers
- Vol. 65 (9) , 5529-5553
The cost of sequential adaptation and the lower bound for mean squared error
- 17 September 2024
- Published by Springer Nature in Statistical Papers
- Vol. 65 (9) , 5529-5553
The cost of sequential adaptation and the lower bound for mean squared error
- Open Access
- 19 March 2024
- Published by Taylor & Francis in Statistics in Biopharmaceutical Research
- Vol. 16 (4) , 383-402
Bayesian and Frequentist Approaches to Rescuing Disrupted Trials: A Report from the NISS Ingram Olkin Forum Series on Unplanned Clinical Trial Disruptions
- 19 March 2024
- Published by Taylor & Francis in Statistics in Biopharmaceutical Research
- Vol. 16 (4) , 383-402
Open AccessBayesian and Frequentist Approaches to Rescuing Disrupted Trials: A Report from the NISS Ingram Olkin Forum Series on Unplanned Clinical Trial Disruptions
- Open Access
Estimation of the Emax model
This study focuses on the estimation of the Emax dose-response model, a widely utilized framework in clinical trials, agriculture, and environmental experiments. Existing challenges in obtaining maximum likelihood estimates (MLE) for model parameters are often ascribed to computational issues but, in reality, stem from the absence of MLE. Our contribution provides a new understanding and control of all the experimental situations that pratictioners might face, guiding them in the estimation process. We derive the exact MLE for a three-point experimental design and we identify the two scenarios where the MLE fails. To address these challenges, we propose utilizing Firth's modified score, providing its analytical expression as a function of the experimental design. Through a simulation study, we demonstrate that, in one of the problematic cases, the Firth modification yields a finite estimate. For the remaining case, we introduce a design-correction strategy akin to a hypothesis test.
Open AccessEstimation of the Emax model
This study focuses on the estimation of the Emax dose-response model, a widely utilized framework in clinical trials, agriculture, and environmental experiments. Existing challenges in obtaining maximum likelihood estimates (MLE) for model parameters are often ascribed to computational issues but, in reality, stem from the absence of MLE. Our contribution provides a new understanding and control of all the experimental situations that pratictioners might face, guiding them in the estimation process. We derive the exact MLE for a three-point experimental design and we identify the two scenarios where the MLE fails. To address these challenges, we propose utilizing Firth's modified score, providing its analytical expression as a function of the experimental design. Through a simulation study, we demonstrate that, in one of the problematic cases, the Firth modification yields a finite estimate. For the remaining case, we introduce a design-correction strategy akin to a hypothesis test.
- Open Access
- 1 August 2023
- Published by Springer Nature in Statistical Papers
- Vol. 65 (3) , 1731-1732
Correction to: Posterior alternatives with informative early stopping
- 1 August 2023
- Published by Springer Nature in Statistical Papers
- Vol. 65 (3) , 1731-1732
Open AccessCorrection to: Posterior alternatives with informative early stopping
- 26 June 2023
- Published by Taylor & Francis in Statistics in Biopharmaceutical Research
- Vol. 16 (2) , 141-157
Coping with Information Loss and the Use of Auxiliary Sources of Data: A Report from the NISS Ingram Olkin Forum Series on Unplanned Clinical Trial Disruptions
While the SARS-CoV-2 (COVID-19) pandemic has led to an impressive and unprecedented initiation of clinical research, it has also led to considerable disruption of clinical trials in other disease areas, with around 80% of non-COVID-19 trials stopped or interrupted during the pandemic. In many cases the disrupted trials will not have the planned statistical power necessary to yield interpretable results. This paper describes methods to compensate for the information loss arising from trial disruptions by incorporating additional information available from auxiliary data sources. The methods described include the use of auxiliary data on baseline and early outcome data available from the trial itself and frequentist and Bayesian approaches for the incorporation of information from external data sources. The methods are illustrated by application to the analysis of artificial data based on the Primary care pediatrics Learning Activity Nutrition (PLAN) study, a clinical trial assessing a diet and exercise intervention for overweight children, that was affected by the COVID-19 pandemic. We show how all of the methods proposed lead to an increase in precision relative to use of complete case data only.
- 26 June 2023
- Published by Taylor & Francis in Statistics in Biopharmaceutical Research
- Vol. 16 (2) , 141-157
Coping with Information Loss and the Use of Auxiliary Sources of Data: A Report from the NISS Ingram Olkin Forum Series on Unplanned Clinical Trial Disruptions
While the SARS-CoV-2 (COVID-19) pandemic has led to an impressive and unprecedented initiation of clinical research, it has also led to considerable disruption of clinical trials in other disease areas, with around 80% of non-COVID-19 trials stopped or interrupted during the pandemic. In many cases the disrupted trials will not have the planned statistical power necessary to yield interpretable results. This paper describes methods to compensate for the information loss arising from trial disruptions by incorporating additional information available from auxiliary data sources. The methods described include the use of auxiliary data on baseline and early outcome data available from the trial itself and frequentist and Bayesian approaches for the incorporation of information from external data sources. The methods are illustrated by application to the analysis of artificial data based on the Primary care pediatrics Learning Activity Nutrition (PLAN) study, a clinical trial assessing a diet and exercise intervention for overweight children, that was affected by the COVID-19 pandemic. We show how all of the methods proposed lead to an increase in precision relative to use of complete case data only.
- 15 April 2023
- Published by Springer Nature in Statistical Papers
- Vol. 64 (4) , 1329-1341
Posterior alternatives with informative early stopping
- 15 April 2023
- Published by Springer Nature in Statistical Papers
- Vol. 64 (4) , 1329-1341
Posterior alternatives with informative early stopping
- 31 March 2023
- Published by Springer Nature in Statistical Papers
- Vol. 64 (4) , 1361-1372
Group sequential tests: beyond exponential family models
- 31 March 2023
- Published by Springer Nature in Statistical Papers
- Vol. 64 (4) , 1361-1372
Group sequential tests: beyond exponential family models
- 20 January 2023
- Published by Taylor & Francis in Stochastic Analysis and Applications
- Vol. 42 (1) , 45-63
On dose-response modeling for evaluation of drugs combinations
We introduce a framework of dose-response modeling for the evaluation of drug combinations. We focus on adaptive techniques in dose-finding studies when several endpoints can be observed simultaneously on each subject. This framework may fit well for clinical trials and we discuss its algorithmization. The generalized bivariate probit model is discussed in particular. Necessary conditions for plausible behavior of drug combinations are given from the theoretical stochastic perspective.
- 20 January 2023
- Published by Taylor & Francis in Stochastic Analysis and Applications
- Vol. 42 (1) , 45-63
On dose-response modeling for evaluation of drugs combinations
We introduce a framework of dose-response modeling for the evaluation of drug combinations. We focus on adaptive techniques in dose-finding studies when several endpoints can be observed simultaneously on each subject. This framework may fit well for clinical trials and we discuss its algorithmization. The generalized bivariate probit model is discussed in particular. Necessary conditions for plausible behavior of drug combinations are given from the theoretical stochastic perspective.