Webinars

Sample Size Determination for Counts & Rates

Written by nQuery Team | Mar 6, 2025 1:28:55 PM

Free Webinar
Sample Size determination for Counts & Rates

In this free webinar, Brian Fox, research statistician at nQuery, explore the area of Sample Size determination for Counts and Rates. He will discuss some common challenges faced when designing clinical trials with these endpoints and some of the advanced techniques used to combat these issues.

Learning objective of this webinar:

In this webinar, we will explore various statistical methods for analyzing counts and rates, focusing on practical approaches for different study designs. Additionally, we will provide a comprehensive overview of sample size determination techniques, covering both traditional methods and more advanced, recently developed approaches from the latest research literature.

Four key areas are covered:

1. Sample Size Determination for Counts & Rates

  • Overview of statistical methods for analyzing count and rate data
  • Importance of accurate sample size estimation in clinical trials
  • Traditional approaches vs. recent advancements in methodology
  • Practical applications in various research settings

2. Addressing Overdispersion & Unequal Follow-Up

  • Understanding the impact of overdispersion on count data analysis
  • Methods to handle unequal follow-up periods in clinical trials
  • Application of Poisson models, Negative Binomial regression, and the Anderson-Gill model
  • Practical considerations and case study examples

3. Accommodating Interim Analysis in Count-Based Studies

  • Overview of group sequential design for Negative Binomial rates
  • Interim decision-making strategies for count and rate endpoints
  • Balancing statistical rigor with study efficiency
  • Implementation challenges and solutions

4. Sample Size Re-Estimation (SSR) for Count & Rate Data

  • Importance of adaptive sample size determination
  • Blinded sample size re-estimation (SSR) for Poisson data
  • Practical applications in trial design and real-world scenarios
  • Benefits of SSR in optimizing study power and efficiency

Sample Size determination for Counts & Rates: A Quick Guide for Biostatisticians 

Overcoming issues like Overdispersion, Unequal Followup, Interim Analysis, & SSR

Recurring events are a common outcome in clinical trials in areas such as chronic respiratory diseases such as asthma and COPD. In addition, count data is an important endpoint in contexts such as MRI imaging. 

Well developed methods are available for analysis of recurring events and counts using methods such as Poisson or Negative Binomial regression. However, many studies continue to choose to analyse such data using continuous approximations or time-to-(first) event data. 

One barrier to using count models has been the relatively basic sample size determination methods available. However, recent years have seen significant progress as methods have been developed to determine the sample size in the presence of issues such as overdispersion, unequal follow-up, and using group sequential design.

Overdispersion & Unequal Follow-Up: Addressing Real-World Challenges

Clinical trials frequently face issues such as overdispersion—where variance exceeds the mean—or unequal follow-up periods among participants. These challenges can lead to biased estimates and reduced statistical power if not properly accounted for. Methods such as Negative Binomial regression, Poisson models, and the Anderson-Gill model offer robust solutions, enabling researchers to better analyze count and rate data while maintaining study integrity.

Interim Analysis: Adapting Study Design for Efficiency

Interim analysis is a critical component of adaptive trial design, allowing researchers to assess data at predefined points and make adjustments while maintaining statistical rigor. Group sequential designs for Negative Binomial rates provide a structured approach for incorporating interim analyses in count-based studies. These methods help optimize resource allocation, reduce trial duration, and improve decision-making during the study.

Sample Size Re-Estimation (SSR): Adapting to Emerging Data

Blinded sample size re-estimation (SSR) has emerged as a powerful tool for adjusting study parameters without unblinding treatment effects. This technique is particularly valuable for Poisson data, where initial variance assumptions may change as more data is collected. By implementing SSR, researchers can ensure their study maintains the necessary power and reliability while minimizing the risks of under- or over-recruitment.

Practical Implementation & Future Directions

Recent advancements in statistical software have made it easier to implement sophisticated sample size methods for count and rate data. Case studies demonstrate the real-world impact of these approaches in clinical trial design, offering valuable insights into their practical applications. As computational techniques continue to evolve, hybrid methodologies integrating frequentist and Bayesian approaches are expanding the possibilities for more flexible and adaptive study designs.

Join us for this webinar to gain a deeper understanding of modern sample size determination techniques for count and rate data. Whether you're designing a new study or refining an existing approach, this session will provide actionable insights to improve the efficiency and accuracy of your analyses.

About nQuery
nQuery helps make your clinical trials faster, less costly and more successful.
It is an end-to-end platform covering Frequentist, Bayesian, and Adaptive designs with 1000+ sample size procedures. 

nQuery Solutions
Sample Size & Power Calculations
Calculate for a Variety of frequentist and Bayesian Design

Adaptive Design
Design and Analyze a Wide Range of Adaptive Designs

Milestone Prediction
Predict Interim Analysis Timing or Study Length

Randomization Lists
Generate and Save Lists for your Trial Design