Archives for February 2021

Interview with David Kerr

In today’s episode, we’re talking with a niche part of clinical research many statisticians never get actively involved in: DMCs.

David Kerr comes with a deep knowledge and long experience in this setting. We’ll speak about:

• What is a DMC?
• What is the role of a DMC statistician?
• What are the best skills and traits of the DMC  statistician

Join us while we discuss these questions with David and learn more about the following points:

The knowledge about the bias variance trade off is very important for you as a statistician as it comes across your work – especially exploratory work – all the time. Taking care about it will help you avoid problems of over- or underfitting your models. 

Wikipedia explains the principle very well:

“In statistics and machine learning, the bias–variance tradeoff is the property of a model that the variance of the parameter estimates across samples can be reduced by increasing the bias in the estimated parameters. The bias–variance dilemma or bias–variance problem is the conflict in trying to simultaneously minimize these two sources of error that prevent supervised learning algorithms from generalizing beyond their training set:^[1][2]

• The bias error is an error from erroneous assumptions in the learning algorithm. High bias can cause an algorithm to miss the relevant relations between features and target outputs (underfitting).
• The variance is an error from sensitivity to small fluctuations in the training set. High variance can cause an algorithm to model the random noise in the training data, rather than the intended outputs (overfitting).

This trade-off is universal: It has been shown that a model that is asymptotically unbiased must have unbounded variance”

In this episode, we dive into 3 examples for it:

Interview with Jenny Devenport

Jenny has encountered several highly competent people throughout her career who have admitted that they entered one path or another based on certain assumptions that were not entirely correct. Further, she has talked with interns about their future career interests and she sees them teetering on the edges of some same fallacies. It’s all fun and science until you have to get a job. As you will make this decision at some point, Jenny wants to give you a few key points to consider when evaluating potential statistics / data science careers in drug development and healthcare. 

Join us while Jenny and I talk about these important reflections and answer the important following points:

Interview with Nancy Carpenter

The COVID-19 pandemic has put pharmaceutical research firmly into the spotlight, with the urgent need to develop new therapies, tests, and vaccines. For those outside the industry, hearing announcements in the mainstream media, it is not always easy to understand the intensity of the work and collaboration that fuels game-changing new developments.

However, we know that there are thousands of ‘unsung heroes’ around the world, working in different capacities on different clinical trials to make the breakthrough. It has been a herculean collective effort. Of course, while this is a particularly high stakes situation, seeing an impact on patients’ lives motivates us no matter the therapeutic area. In this podcast, I interview Nancy Carpenter, a Principal Statistician at Veramed who has worked extensively on COVID-19 trials over the last several months. Our wide-ranging discussion covers: