The 2023 program 

Click here to view/download the 2023 program.

Note: On Wednesday afternoon (directly after the conference), a tour of the J&J museum will be made available to conference participants (including non-J&J members). It is not normally open to the public, so this is a rare opportunity. Sign ups will take place during the conference.

ASA Presidential Speaker:  Dr. Madhumita (Bonnie) Ghosh Dastidar, Head, RAND Statistics Group
Talk title:  Statistics Is a Core Competency for Creating Effective Public Policy

Abstract: The ASA vision imagines a world that relies on data and statistical thinking to drive discovery and inform decisions. Policy makers and stakeholders are responsible for establishing regulations, formulating a plan, and setting a course of action in important arenas such as reducing drug overdose mortality, improving nutrition and health, increasing school attendance rates, ensuring equitable application of regulations, supporting essential technology development. The gold standard for public policy is evidence-based decision making—deliberate and strategic application of real facts and research-supported principles that yields objective evidence.

Statistical science is the foundation for evidence-based decision making. As an interdisciplinary science, it has applications to every field imaginable, making statisticians uniquely qualified to lend their expertise in multiple policy domains. Effectively informing policy requires becoming involved early in the design phase; understanding the nature of the issue; and knowing how to communicate, educate, and explain. In this talk, I will provide multiple examples from health policy to highlight both valuable contributions made by statistical scientists and lessons learned. Extrapolating from these successes, I will suggest areas for future contributions in which the stakes are very high and involving statistics will be essential for crafting effective policy approaches. Finally, I will highlight the ASA’s role, major initiatives and contributions to public policy making.

Keynote Speaker
:  Dr. Ajaz S. Hussain

Talk title:  Statistical Thinking and Pharmaceutical Professional development for 21st-century
Pharmaceutical Quality

Abstract: Observations and experience suggest that statistical science, as applied in pharmaceutical development and manufacturing, can often be fraught with psychological and technical difficulties. This talk’s subject is the observations supporting this assertion and how to improve the quality of statistical applications and inferences. Furthermore, it is argued that far less attention has been given to cognitive problems in pharmaceutical statistics than technical issues. A path forward to address the core problems in pharmaceutical development and manufacturing, such as BAD-I breaches in the assurance of data integrity, will be explored. This discussion will be in the context of the FD&C Act stipulation of “scientific training and experience” to make “effectiveness” decisions “fairly and responsibly,” as relevant to professional development, organization management system maturity, and the increasing chaos in our social environment.

Short courses:
Conference attendees may attend one of the following short courses.

Course #1

    • Title: Bayesian Methods for Nonclincial Statisticians
    • Instructor: Dr. Luwis Diya (Janssen) and Dr. Will Landau (Eli Lilly)

    Description: Bayesian methods have several advantages in the nonclincial space. Relative to the traditional frequentist paradigm, Bayesian models are more capable of nuanced inference, straightforward interpretation, quantification of prior evidence, and borrowing information across the features of a dataset. In this short course, we will introduce the Bayesian paradigm and motivate use cases in CMC, safety, and pharmacology. In addition, we will introduce Bayesian computation with JAGS and Stan so participants can begin implementing their first Bayesian analyses.

    Course #2

    • Title: Statistical Tolerance Intervals and Regions
    • Instructors: Dr. Thomas Mathew, UMBC

    Description: Statistical intervals and regions, computed based on a random sample, have wide applicability. Confidence intervals and regions, and prediction intervals regions are well-known examples. The topic of the short course is on another type of intervals and regions, namely tolerance intervals and tolerance regions.

    A tolerance interval for a univariate population, computed using a random sample, is an interval that will include a certain proportion or more of the population distribution, with a given confidence level. In particular, an upper tolerance limit for a univariate population is such that with a given confidence level, a specified proportion or more of the population distribution will fall below the limit. This proportion is referred to as the content of a tolerance interval. Furthermore, the confidence level associated with the tolerance interval captures the sampling variability. A lower tolerance limit, or a tolerance interval having both lower and upper limits, satisfy similar conditions. For multivariate populations, we analogously have tolerance regions. The theory of statistical tolerance intervals and tolerance regions has undergone vigorous development, starting with the early works of Wilks (1941, 1942) and Wald (1943). A significant amount of recent and very recent literature is also available on the topic, motivated by specific applications and computational considerations. Applications of tolerance intervals and tolerance regions are varied and extensive. They include clinical and industrial applications: quality control, environmental monitoring, the assessment of agreement between two methods or devices, occupational exposure monitoring, the computation of reference intervals and regions in laboratory medicine, and a host of other applications. Starting with the simplest case of a univariate normal distribution, the short course will introduce the participants to the methodological developments and applications of tolerance intervals and regions under various scenarios: regression models, random effects models, multivariate normal models (including multivariate regression models), and non-parametric tolerance intervals and regions. In the multivariate case, the computation of both ellipsoidal and rectangular tolerance regions will be discussed, the latter being motivated by applications in laboratory medicine. Numerous applications will be presented, and computational issues will be briefly addressed.

    Some of the material to be presented will be taken from the book Statistical Tolerance Intervals and Regions: Theory, Applications and Computations by Krishnamoorthy and Mathew (2009, Wiley). However, a significant part of the course will include more recent developments on the topic.

    Contributed Abstracts:

    Members of the nonclinical statistics and academic communities are encouraged to submit abstracts for contributed talks and posters.  See abstract submission page.

    Graduate Students:
    Click here for our page for graduate students and young professionals.
    Student registration is $50. We encourage full-time students to present posters. The best student poster will be awarded a prize of $250.  The second-place award is $150.  Contact Wei Zhao for more details. Poster submission is open.  Special panel discussions, round-table discussions, and sessions on career advice are planned for graduate students and young statisticians.

    For the 2021 program, click on the virtual platform link (get the pdf version with times given in CDT) and also download the program booklet.  The keynote speaker, invited speakers, and short courses are shown below.

    Past Programs:
    2023 2021 2019  2017  2015