We’re launching a new leadership course next year and in this episode, we go into some key questions about statisticians and leadership.

We cover the following topics:

  • What is a good definition for leadership?
  • Why should technical statisticians worry about developing leadership skills?
  • What happens, if you have limitations in the leadership skills?
  • What should the mindset of a statistical leader be?
  • When should statisticians start thinking about developing their leadership skills?

Gary Sullivan

I worked in and around the field of statistical science in both technical (13 years) and management roles (15 years) for Eli Lilly and Company, a major pharmaceutical manufacturer in Indianapolis, Indiana.

Couple this experience with my leadership study – almost 10 years creating, implementing and instructing leadership programs. The result is a perspective from all sides: the employee, the manager and the leadership expert.

This allows me to understand what will be helpful and insightful to any person or group seeking to improve their leadership.


Why should statisticians care about leadership and developing their leadership skills? Interview with Gary Sullivan

You are listening to the Effective Statistician episode number 35. Why should statisticians care about leadership and developing their leadership skills? An interview with Gary Sullivan. Welcome to another episode of the Effective Statistician with Alexander Schacht and Benjamin Piske. The weekly podcast for statisticians in the health sector designed to improve your leadership skills and today is really about that.

widen your business acumen and enhance your efficiency. We are creating an online course for improving your leadership skills and this episode serves as kind of a first intro into this.

and you can develop your leadership skills business course as a statistician even if you have no direct reports. So register your interest for such a course on the homepage of the Effective Statistician at thee slash course.

So in today’s episode we’ll chat about actually what is leadership and why should technical statisticians worry about their leadership skills and developing their leadership skills. So if you’re not really sure about why and what then keep on this episode. Also we will talk about…

different dimensions of leadership, mindset of a leadership, and how you can develop your leadership skills.

This podcast is created in association with PSI, a global member organization dedicated to leading and promoting best practice and industry initiatives. Join PSI today to further develop your statistical capabilities with access to special interest groups, the video on demand content library, free registration to all PSI webinars and much much more.

come a PSI member today.

Hello, this is another episode of the Effective Statistician. Today we are talking about leadership and this will be actually the first episode in a series of episodes about leadership. And for the series, I have a special guest with me that has done a lot about leadership in terms of statistics.

and has great, great expertise here. And so I welcome Gary Sullivan. Hi, Gary, how are you doing? Hi, Alexander, I’m doing great. It’s great to be with you. Always enjoy talking about leadership. Yep, very, very good. So as we are recording this, it’s actually summer and here in Germany where I’m located, it’s just started to rain, which is really great because it’s completely dry here.

but maybe you hear a little bit of rain in the background. That shouldn’t kind of distort us from speaking about leadership today. So, Gary, you have been in statistics for quite some time. Can you speak a little bit how you first got in touch with statistics and what has been your career within statistics that far? Sure.

Took up an interest in statistics way back when I was in high school and decided to go on and get my bachelor’s degree in statistics and went on to receive my master’s and PhD from Iowa State University in 1989. After graduating from Iowa State, I joined Eli Lilland Company and I worked there for a little over 28 years.

I feel like I had the best of both worlds there because I spent about half of that time working as a practicing consulting statistician, supporting different roles in product development and discovery research, and then moved on into management roles within the statistics function. I came to understand leadership a little bit later in my career.

So in terms of your management roles, what kind of areas have you managed there? So in the pharmaceutical industry, I managed on what we call the non-clinical side. So I had a responsibility for statisticians in discovery research, in product development, and in manufacturing.

I had responsibility for all the statisticians in those three areas as well as biomarker research. So, a very, very broad range of statistics where people interact with lots of different areas. So, from, you know…

Very different to, let’s say, the usual phase three setting where you have a much more homogeneous group of statisticians, yeah? Yes, yes. I mean, statisticians that interacted with discovery chemists and biologists who are trying to identify the next molecule in the pipeline all the way through to manufacturing

technical associates and operations to make sure that our products are being manufactured and distributed with consistency and reliability. Okay. So how did you came into touch with this leaderships topic for statistics? Yeah, that’s a really good story.

Back, I think it was in 2009, I was invited to attend a leadership program, a corporate leadership program at Eli Lilly. And right before I attended that program, our new vice president in statistics, we developed a new statistics strategy with some different pillars to that strategy. And one of the pillars was leadership. And I was asked to…

develop a leadership program with another senior technical statistician within the company. And I went to the leadership class and I came back and we just sort of started from scratch and developed a couple different programs for our statisticians at Eli Lilly. So that was kind of the start of it and from there I went on to teach

and facilitate different programs. And those first few years, I just became really interested and fascinated by leadership. And I guess I became what I now call a true student of leadership and that I view many things through a leadership lens and find lessons in leadership and a lot of different things I observe in my work life and in my social life.

in the community, everywhere. Interesting. So as we are talking about leadership, maybe it’s due to actually start with a definition of leadership. So like in every good statistics or math book, everything starts with a definition. So what’s your definition of leadership here in this statistics setting?

Yeah, actually, when we started our leadership program, that was actually the first thing we did was to come up with a definition because we felt that we had to keep people focused on the same thing. Because when you hear leadership, people think of many different things. So I’ll give you a most recent definition that we used in teaching a class at the Joint Statistical Meetings last week. And that definition is to consistently…

deliver value to an organization or cause by inspiring people to take a specific direction when they truly have the freedom or choice to do otherwise. And I’m not reading that. That’s kind of etched in my memory, again, because like I said, I’ve thought about that definition a lot and thought about leadership a lot. Okay. So there’s a couple of…

interesting words and it’s the first kind of thing comes into this. It’s about inspiring and it’s about that people follow when they have the true choice to do something different. What do you mean by the second one? Can you give an example of what would then not be leadership?

to get into a discussion about when I provide training on leadership is the difference between leadership and management. And if again, if that’s something you haven’t thought about, I think it’s something worth considering. If you think about management, typically it’s about managing resources, coordinating activities.

there’s even some things I’ve read where they use the word controlling. And when you think about leadership, if you ask people to talk about leadership, they’ll talk about words like influence and courage and strategic thinking and vision. And so the two are very different. So, so in management, when you talk about someone that has authority, in a sense,

the people beneath them maybe feel obliged to simply follow their direction. And over time… As a leader, you need to actually convince people rather than tell people. Yes. Whether you have authority over them or not, we can get into some different aspects of leadership.

sort of sticking with the leadership management thing. So in a management role, you do have the authority sometimes to tell people maybe what to do, when to do it. But in the 21st century employee, especially those in statistical roles or in other technical type roles, they’re gonna be motivated by wanting to be creative, wanting to be challenged.

wanting to master certain things, wanting to contribute at a high level. And you need to meet those needs as well. Otherwise, if you’re just simply telling them what to do, they lose interest. They become demotivated. They become less productive. So I think there is in being a leader at something beyond being a manager that you do have to, in addition to having authority over them, you need to find ways to inspire them so that

they can both meet the goals and objectives of the organization that they’re working for, but also that they themselves are motivated and feel challenged and feel like they’re advancing technically, that they’re impacting the organization. So I think that’s why the inspire part and is an important part of being a leader, whether you have authority or whether you don’t have authority. Okay.

And so it’s a lot about inspiring and influencing others. So, and if you think about, you know, a statistician in day-to-day work.

Who is he inspiring? Who is he leading?

Yeah, so I guess there’s a couple different types of statisticians. When we think of leadership, we probably immediately think of people in roles where they have responsibilities over people. So in the last half of my career, I was leading other statisticians and trying to inspire them. And not in a day-to-day type of sense, but trying to identify the things that…

that keep them motivated and challenged. Now, on the other hand, most statisticians, they’re working as technical contributors. They may have supervisor responsibilities or they may not. And so they need to inspire those around them. Maybe they would be colleagues, scientific colleagues.

people they’re working with on teams, project management type folks, or decision makers. And they’re inspiring them perhaps to adopt a certain approach toward a statistical design or buy into a certain type of analysis. So in those ways, they have to inspire.

fellow team members, colleagues, collaborators, to make those certain choices that they have the freedom to make or not. So in that way, both types of roles, whether you’re in a management type role or whether you’re in a technical contributor type role, both roles have to inspire those around them in order to deliver value. Okay, so it’s really…

topic for everybody, for every statistician, because we all work not in isolation just for ourselves. We all work in teams, cross-functional teams. There’s always something where our expertise is needed to set a direction to help make a decision. Maybe it’s a team decision, maybe it’s a management decision, but there’s always some…

um, some things that we need to help, uh, so that, you know, others can actually achieve something. That’s right. I was going to say, um, uh, several years ago, I think Bob Rodriguez, when he was the president for the ASA, um, was quoted as saying a statisticians, our job is to get people to act on our ideas and adopt our, uh,

methods, whatever the appropriate method might be. And in order to do that, that requires influence and influences a large part of leadership.

If you think of a statistician that wouldn’t have these kind of leadership skills, the influencing, how would you call such a statistician?

Well, I think a statistician can still certainly feel challenged and add value without leadership. I think of a consulting statistician in the purest sense where, and this is probably, I had experiences like this earlier in my career, would someone come and ask me if I could design an experiment for them or analyze some data.

And you can do that and you can help provide them with what they need and help advance a cause. But in order to, if you think about things from a standpoint of wanting to advance whatever fields you’re working in, whether it’s advancing the science or advancing the production in an area or

advancing just the flow of information or insights. The field of statistics is constantly changing. There are constantly new methods, new ideas, new ways of doing things that are brought about through, again, advances in science, advances in technology. And so as a statistician, in a sense, by trying to convince people to use the best appropriate methods,

It requires leadership, it requires influence. And there’s more to it than that, but I guess that’s sort of a simple way of describing maybe the passive statistician who just provides what they’re asked to do, and the active statistician or the statistical leader who maybe provides what they’re asked to do, but then looks for wanting to understand the bigger question.

and maybe how they could do it better or what they might be able to contribute to do it more efficiently. Okay, so an example would be a colleague from another function comes to you with data and says, okay, could you please analyze this data here for me and I need a p-value based on a Q square test here.

just do it and the passive statistician would just run the software, give him the p-value, job done. Whereas the more leadership person would take it, try to understand the data and maybe come up with a different solution, a more powerful solution to come to the answer and would then…

try to convince the other person that that is actually a better approach than just a very simple test that maybe that person is coming up with. Yeah. It could be that or it might even be the person, when they come to them with a data set, sort of digging a little deeper and saying, okay, what problem are you trying to solve or what question is someone asking you and what bigger question are they trying to answer?

maybe inserting yourself a little bit more to gain a deeper understanding of the bigger problem or the bigger picture. And then you may find that, well, yeah, this data set is good, but maybe we can leverage other data, or maybe you’re not asking the right question, or maybe we need to go about this in a different type of way. So I think those are some of the qualities, or at least the beginnings, of a statistical

to want to dig deeper and understand the question beyond the question. Okay. So that already points us into a little bit kind of the benefits of the statistician of developing leadership skills. Could you expand a little bit more on this topic? So why should a technical statistician at the beginning come out of this?

maybe passive mode and develop more of these leadership skills.

Yeah, that’s a really good question. Because I think some statisticians may look at it as, well, this is how I was trained. This is the job. This is what I’m asked to do. I think in any industry, or any sector, whether it’s industry, government, research, independent consulting, even academia, I mean, there’s

There’s always sort of a, I mean, you’re working for an organization that has a mission or a vision is trying to achieve goals. And as a member of that organization, you want to do the best that you can to help the organization achieve those goals. So at the highest level, you wanna look for ways to more efficiently

deliver on those goals, to deliver value, to be more efficient, to be more productive. And so I think there’s a notion of always want to think about a better way to do things, a way to bring greater value to the cause that you’re a part of. And if you want to do that, then that’s about wanting to innovate, wanting to identify.

new methods, wanting to come up with new ideas and constantly improve upon the way that things are being done, or at least think about improving upon the way that things are done. So any opportunity to influence or any situation where you need to influence or you need to create change requires leadership skills.

And I think that’s the reason that many statisticians are pursuing more leadership skills. And for those that aren’t, why they should think about doing it. Yeah. I think this change is a very, very kind of fundamental term here. Because if you don’t want to change things, there’s no kind of need to…

convince somebody or there’s no need to put a lot of effort into something because the ball will just roll further and further and further. But if you really want to change something being it on any aspect of the business, then you always need these leadership skills.

You mentioned just that in terms of training, people come from this perspective that they’re trained at university, how to do certain tests, statistical methodology, all these different things.

technical knowledge of the statisticians.

When is actually then a good time to start with this leadership development?

Yeah, that’s another really good question. I’ve gone, I think, back and forth on that. And I think there’s probably no time that’s too early. And I think it depends on how much. The question is how much time to spend on it. I think my thinking these days is that even in graduate school or in universities, statisticians should be at least

provided some understanding of what leadership is and why it’s important. So they should never sort of lose sight of it. Now, I think when someone first starts in a professional role, yeah, they should spend the majority of their time just learning what their responsibilities are and figuring out how to do their job and just to deliver.

value in a way that they’re expected to. But I think after a few years and once that starts to become understood by the statistician that then they need to think about, start investing in their leadership. Because ultimately as you said, they’re gonna think of, or they’re gonna be presented with opportunities where they can do things.

faster, do things cheaper, do things in a way that will deliver greater quality, and they need to, they’re going to want to do that. And in order to do that, they’re going to need to convince other people that they need to do things differently. So I think the answer to your question is it’s never too early.

I think as someone’s professional career goes on, they maybe need to invest more and more in their leadership development. And I’ll say on the flip side, I don’t think it’s ever too late either. I think sometimes people, you know, in mid-career may run into a bit of a wall or feel like they’re at a crossroads or feel like, okay, I’ve done all the things that I expected I could do. And maybe they’re…

starting to feel bored or not challenged, then I think the question is, well, what more can you do? And in order to perhaps maybe take on a different role or re-energize themselves, they can think about ways where they can create change for the better for their organization. And that’s again where leadership would come in. So I think even

whether it’s as early as graduate school or as late as 15 to 20 years into their career or places in between that people can and should invest in their leadership. Yeah, I think when I look across the different people, the different colleagues, also just beyond my company.

I see that those people where I have the feeling they have very good leadership skills, they just get things done much, much easier because they can work much better with other people. They can get things across much easier. If you have all these influencing skills and…

These things that are the foundations of good leadership, which we’ll talk about in future episodes, if you have all these, everything will be much easier for you. So you can get much more done in fewer time with less problems. So I think all these leadership skills are kind of, they put a kind of supercharge your

your day-to-day life. Whereas if you don’t have them, you run into barriers again and again and again. And as you say, maybe at a certain point, your career might plateau and you might even get bored because there’s no change anymore and you don’t see any kind of further possibility to grow.

Yeah, I agree, maybe except with the part of it becomes easier for people. I think people that are strong leaders, strong statistical leaders, they may disagree and say that, well, it’s never easy, but it’s challenging. Then they certainly have the tools and the skills to create change.

Whereas in some situations, some people may not even have those tools or not even see those opportunities and may not even want to engage in trying to create a change. I don’t know that it’s ever easy, but I think it makes it challenging and interesting and more rewarding. And those are probably the things that motivate most statisticians to want to keep, not just developing their technical skills, but developing their leadership skills so they can…

continue to impart change and create impact and grow as a, not just a statistician, but a business professional, a scientist, a researcher, whatever field they’re in. Yeah. Okay, very good. That was a great kind of introduction into leadership and what it means. We talked about, you know,

why leadership is important, what leadership is. Gary, you gave a really nice definition about what leadership is, that it’s inspiring and it is about influencing others so that they take action when they have the freedom to do something different. We talked about kind of what it is, why it’s important for every statistician early in their career or late in their career.

And if you don’t have these kind of skills, how that kind of impacts your day-to-day life as a statistician. And yeah, I think on the flip side, that also explains where the benefits are. So, Gary, thanks so much for this first episode. And stay tuned for the next episodes with Gary on…

where we go further into other aspects of this discussion.

Thanks a lot. Thank you.

So don’t forget to register your interest in the Leadership Program at thee slash course. This show was created in association with PSI. Thanks for listening. Please visit thee to find the show notes and learn more about our podcast to boost your career as a statistician in the health sector, especially now with respect to leadership.

Join The Effective Statistician LinkedIn group

I want to help the community of statisticians, data scientists, programmers and other quantitative scientists to be more influential, innovative, and effective. I believe that as a community we can help our research, our regulatory and payer systems, and ultimately physicians and patients take better decisions based on better evidence.

I work to achieve a future in which everyone can access the right evidence in the right format at the right time to make sound decisions.

When my kids are sick, I want to have good evidence to discuss with the physician about the different therapy choices.

When my mother is sick, I want her to understand the evidence and being able to understand it.

When I get sick, I want to find evidence that I can trust and that helps me to have meaningful discussions with my healthcare professionals.

I want to live in a world, where the media reports correctly about medical evidence and in which society distinguishes between fake evidence and real evidence.

Let’s work together to achieve this.