David Izard
Sunday, May 31, 2026, 8:00 AM – 12:00 PM

The US FDA introduced binding guidance in 2014 establishing requirements for the provision of clinical and non-clinical data and related assets in support of drug & biologic filings seeking marketing approval. PMDA (Japanese regulator) and NMPA (Chinese regulator) followed suit shortly afterwards, establishing similar expectations.

This seminar will engage Programmers, Statisticians, Data Managers and others as they directly or indirectly support the generation of these regulated deliverables by:

• Reviewing the foundations of FDA, PMDA and NMPA submission data requirements and how they have evolved over time.
• Participating in a detailed walk-through of regulatory guidance, highlighting the specific requirements for each deliverable as dictated by documents such as the US FDA Study Data Technical Conformance Guide, the PMDA Technical Conformance Guide on Electronic Study Data Submissions and the NMPA Guidelines for the Submission of Clinical Trial Data for Drugs.
• Focusing on work practices that will support meeting immediate study execution needs while simultaneously preserving assets for future use in regulatory submissions.

We will wrap up with a focus on what is likely to come – imminent acceptance of machine-readable data by EMA, other regulators worldwide that consume machine readable data in alternative ways, and expansion of US FDA Technical Rejection Criteria, among other topics.

Phil Bowsher
Sunday, May 31, 2026, 8:00 AM – 12:00 PM

AI innovation for programming is changing quickly. This workshop will explore various areas of AI for statistical programming, including IDEs, packages, Shiny, and AI orchestration/architecture. This session will have something for everyone—whether you’re a statistical programmer looking to learn R, a seasoned R programmer looking to learn AI, or an AI sage looking to create and drive agents. We will explore the new IDE, Positron, while also highlighting tricks for RStudio users. Finally, we will cover how to integrate AI with Shiny in both R and Python. Posit/RStudio will be presenting an overview of AI in Positron and RStudio for the open-source user community at PharmaSUG.

This session will provide an opportunity to use AI in Positron and see how it can empower statistical programmers using R and the Pharmaverse. This workshop will explore and discuss areas such as ADaM data and TLG creation, while providing examples for getting started in your own environment after the session. You will gain hands-on insights using R for clinical workflows and discover how these emerging technologies can enhance your approach to pharmaceutical data science. This deep dive ensures you remain at the forefront of innovation within the rapidly shifting landscape of open source pharmaceutical AI.

Ryan Lafler
Sunday, May 31, 2026, 8:00 AM – 12:00 PM

This hands-on training seminar delivers a clear, comparative, and applied foundation in statistical hypothesis testing and modeling across the R, Python, and SAS® programming languages. Designed for analysts, data scientists, researchers, and professionals in clinical, healthcare, pharmaceutical, and other data-driven industries, the workshop emphasizes practical programming applications for model selection, checking assumptions, running diagnostics, and interpreting results.

Registered attendees will learn when to apply parametric vs. non-parametric tests, how to distinguish statistical significance from practical or clinical significance, and how to conduct power analyses to determine the minimum sample size needed for effective study design. Through guided exercises, participants will perform exploratory data analysis (EDA), describe and visualize datasets, build statistical models, and interpret results using:

• R (RStudio by Posit)
• Python (Jupyter Notebook)
• SAS® 9.4 (free-to-use SAS® OnDemand for Academics)

This training seminar is structured to highlight cross-language similarities and differences, giving attendees a practical roadmap for statistical analysis using Python, R, or SAS® 9.4.

Key topics include:

• Understanding statistical significance, effect size, and practical significance in experiments
• Exploratory data analysis (EDA), summarization, and visualization across R, Python, and SAS®
• Comparing two groups: 2-sample t-test (Welch’s) and Mann-Whitney U test
• Comparing multiple groups: One-way ANOVA models and Kruskal-Wallis test
• Modeling factorial ANOVA and evaluating interaction effects
• Checking model assumptions and conducting diagnostic tests for reliability
• Statistical power, sample size determination, and study design considerations.

All registered attendees will receive the non-redistributable PDF slides, fully documented R, Python, and SAS® code examples, and the complete workshop dataset to continue practicing and enhancing their skills after the seminar.

Bart Jablonski
Sunday, May 31, 2026, 8:00 AM – 12:00 PM

Unusual, for a “good old SAS language”, syntax of hash tables objects can be uncomfortable, hard to accept or to “get used to” for some programmers. The aim of the workshop is to convince those people that advantages growing up out of the hash tables facility overgrow that vague disadvantages by three orders of magnitude.

During the tutorial:

1. general overview and analogies with SAS arrays,
2. syntax of the hash object,
3. and a bunch of use cases

will be presented.

Mario Widel & Veronica Gonzalez
Sunday, June 1, 1:00 PM – 5:00 PM

ADaM datasets must be designed with the fundamental principles in mind as well as following the rules. Most of the time, analysis requirements lead to a specific and unambiguous ADaM approach. Statistical analyses involving change from baseline should be done in ADaM BDS, similarly analyses that involve counts under hierarchies should be done in ADaM OCCDS.

However, there are circumstances where analysis requirements do not lead to an obvious optimum approach. This seminar will present analysis situations where the best approach may be debatable. Exposure analyses where you can use ADEX and/or ADEXSUM, how do you know which to use? Or protocol deviations where BDS or OCCDS could be used, which one should you pick? Or cases like time-to-event where the analysis is supported by a BDS, are there benefits to including an intermediate analysis dataset? Cases such as these will be explored in depth illustrating varying approaches, covering their advantages and disadvantages, while highlighting the preservation of the ADaM fundamental principles and ADaM rules, as feasible.

Recommended pre-reading:

• ADaM Fundamental Principles vs. Rules: Which to Follow, When, and Why? — Sandra Minjoe, & Mario Widel, PharmaSUG 2025
• Which ADaM Data Structure Is Most Appropriate? Gray Areas in BDS and OCCDS. – Veronica Gonzalez, PharmaSUG 2025

Outline:

• Brief covering of fundamental principles & rules
• Example
• Clear cases
  • Change from baseline
  • Counts of AEs
  • Time to event
• Debatable cases
  • Exposure ADEX and/or ADEXSUM
  • Protocol deviations
  • TTE & intermediate analysis dataset(s)
• Exercises

Kevin Lee & Nathan Lee
Sunday, May 31, 2026, 1:00 PM – 5:00 PM

Artificial Intelligence is rapidly evolving beyond simple chatbots into a new era of AI Agents, Agentic Workflows, and Vibe-Coding where machines can reason, act, and collaborate like digital teammates.

In this hands-on seminar, we’ll explore how Generative AI (Gen AI) tools such as ChatGPT, Copilot, Gemini, and Claude are transforming the Biometrics field – from automating data analysis and code generation to driving intelligent workflows and decision support.

You’ll learn how to harness these technologies to:

• Build powerful prompt using Prompt Engineering (e.g. Zero Shot, Few Shot, Chain of Thought
• Enhance document generation, data exploration, visualization, and interpretation
• Develop SAS, R, and Python programming using Gen AI and Vibe-coding
• Translate legacy code across languages effortlessly
• Build data-aware AI assistants that can query and explain datasets
• Develop applications powered by Gen AI APIs, LangChain, and RAG
• Design AI Agents that think and act autonomously within your workflow
• Implement Agentic Workflows that connect tools, data, and reasoning chain
• Explore Vibe-Coding, the next evolution of collaborative human-AI coding

We’ll also discuss risk management, data privacy, and ethical AI practices, ensuring your implementation is both powerful and compliant.

Troy Martin Hughes
Sunday, May 31, 2026, 1:00 PM – 5:00 PM

Attend and receive a FREE copy of the instructor’s 400+ page book, PROC FCMP User-Defined Functions: An Introduction to the SAS® Function Compiler, Second Edition, hot off the presses in Spring 2026! Students will receive the physical book at the training. This hands-on course provides a gentle introduction to SAS user-defined functions, which enable SAS practitioners to build reusable chunks of code that can be shared among coworkers and teams, and which improve the efficiency and quality of SAS software development. All examples demonstrate real-world application in clinical, pharmaceutical, and life science environments. No prior knowledge of PROC FCMP is required.

Instruction includes:

• Gentle introduction to PROC FCMP syntax and the construction of user-defined functions and subroutines (with the FUNCTION and SUBROUTINE statements, respectively)
• Use of the OUTARGS option to modify multiple arguments (to pass arguments “by reference” not “by value”)
• Passing character and/or numeric data types to functions
• Passing arrays to functions, and declaring and using arrays inside functions
• Declaring, initializing, and referencing hash objects within functions
• Calling functions and subroutines from the DATA step, and from %SYSFUNC and %SYSCALL
• Calling user-defined functions from PROC FORMAT user-defined formats or informats
• Multiple examples demonstrating the superiority of user-defined functions to user-defined macros in solving programming challenges

The course is taught in lecture format, so students are not expected to run the exercises in real-time. However, all SAS code will be provided to students prior to the start of the course, so students have the option to run all examples in real-time during the course, or to peruse the code at their leisure after conclusion of the course.

Prafulla Girase
Sunday, May 31, 2026, 1:00 PM – 5:00 PM

A regulatory submission of clinical study data also needs to be accompanied by various other electronic submission (eSUB) components such as Define-XML, annotated CRF, study data reviewer’s guide, analysis data reviewer’s guide etc. This seminar will take a deep dive into each of these components. It will educate attendees about various requirements, best practices, consistency checks etc. It will also go over key considerations related to preparation of a whole eSUB package for a submission such as folder structure considerations, PDF validation practices, final package checklist, regulatory hand-off etc.

Prerequisite: Very basic knowledge of eSUB components.

Richann Watson
Wednesday, June 3, 2026, 1:00 PM – 5:00 PM

Creating custom graphs has always been a challenge regardless of what software you are using. Most software has tools that can help you create a basic graph such as a simple bar chart, box plot, series plot or scatter plot. These basic graphs use the tools’ default values for things such as background color, line color, marker color and font. Although most of the graphs produced within a procedure or function are adequate for most situations, they sometimes lack those one or two extra features you need to really make your graphs stand out and impress your clients or customers. In this class, we start with the basics and build on to what we know to modify these different aspects to make a graph that is desired. We walk through several examples, showing how to achieve the desired graph using both SAS and R.

Nate Freimark
Wednesday, June 3, 2026, 1:00 PM – 5:00 PM

When submitting data to an approval agency, SDTM and ADaM datasets are provided along with metadata and other files that support the review process. This session will review some best practices and some common issues found when creating defines and reviewer guides and what steps to take to ensure compliance to the SDTM and ADaM standards and consistency between the submitted data and the supportive documentation files.

Bhavin Busa
Wednesday, June 3, 2026, 1:00 PM – 5:00 PM

This seminar will give an overview of the ARS and provide updates on the eTFL Portal. It will also give an overview of the new CDISC Analysis Concepts.

Kirk Paul Lafler
Wednesday, June 3, 2026, 1:00 PM – 5:00 PM

This immersive seminar equips aspiring statistical programming professionals and data scientists with the skills to perform robust statistical analysis using SAS and R. Attendees will learn to clean, transform, visualize, and analyze data, building reproducible workflows for real-world applications. Through instructor-led hands-on exercises, real datasets, and industry-focused examples, attendees will develop the programming expertise needed to derive actionable insights, automate tasks, and present results confidently. Whether you are a business analyst, researcher, or data enthusiast, this seminar’s focus uses an application-oriented approach to statistical understanding and programming, empowering attendees to tackle complex data challenges efficiently.

Seminar Outline:

• Introduction to Statistical Programming
  • Overview of SAS and R environments
  • Data structures: datasets, vectors, matrices, and data frames
  • Importing/exporting data from CSV, Excel, SQL, and other sources
  • Hands-on exercise: Loading and inspecting datasets
• Data Cleaning and Transformation
  • Handling missing data, outliers, and duplicates
  • Data type conversions, recoding, and filtering
  • Combining datasets: merges, joins, and concatenation
  • Hands-on exercise: Cleaning a messy real-world dataset
• Exploratory Data Analysis (EDA)
  • Summary statistics and descriptive measures
  • Data visualization: histograms, boxplots, scatterplots, and bar charts
  • Detecting patterns, trends, and anomalies
  • Hands-on exercise: EDA on a sample survey dataset
• Statistical Analysis
  • Hypothesis testing: t-tests, chi-square, ANOVA
  • Correlation and regression analysis
  • Model diagnostics and interpretation
  • Hands-on exercise: Running a regression analysis
• Advanced Statistical Programming
  • Loops, functions/macros, and automation
  • Advanced modeling: logistic regression, mixed models
  • Using SAS PROC and R packages effectively
  • Hands-on exercise: Automating repetitive tasks in SAS and R
• Reporting and Visualization
  • Creating reports and dashboards in SAS and R
  • Publishing results with R Markdown and ODS in SAS
  • Communicating insights effectively
  • Hands-on exercise: Generate a professional report

Seminar Outcomes:

By the end of this seminar, attendees will be able to:

1. Navigate SAS and R environments confidently.
2. Clean, transform, and prepare datasets for analysis.
3. Conduct exploratory data analysis and generate insights.
4. Perform hypothesis testing and build regression models.
5. Automate repetitive tasks using SAS macros and R functions.
6. Create professional reports and visualizations.
7. Apply statistical programming skills to real-world datasets.