We interviewed a handful of statistical consultants to find out who inspired them, why they became consultants, and what skills they think consultants need to succeed.

Andrew D. Althouse
Assistant Professor of Medicine, University of Pittsburgh

 

What or who inspired you to be a statistician/data scientist?

I liked the class! Seriously, it was my favorite class as a freshman in college, and I just went with it. Over time, I began to develop more specific interests (statistical applications in medicine), but it all started with college freshman-year statistics.

Why did you become a consultant?

Because I like to collaborate! For me, the most fun part of this job is working with a physician or medical professional who has a question. We can help them define and refine it, figure out the right data source and study design to answer their question, create an analytic plan, and execute that plan!

Name a few specific skills you need to be a consultant.

Communication is critical. You can have all the technical and programming knowledge in the world, but if you cannot communicate (both listening and speaking), it is very difficult to be an effective consultant.

What is the most exciting part of consulting?

Seeing the results come to fruition! You put so much work into these projects. The rewarding part is seeing the finished product in a journal and, hopefully, seeing that it has a meaningful impact on clinical practice.

What is the best piece of advice you received from a mentor regarding statistics or consulting?

As much as possible, try to work with good collaborators. The work experience of many statisticians is dictated by the environment and people you work with, so you’ll be best suited to find a place where you have some say in the people you work with.

What advice would you give to statisticians just beginning their careers?

Learning the field and practice of statistics is an ongoing process. Don’t expect to know it all on your first day as a staff member or faculty. There are always more models, tests, programming tricks to learn. Keep an open mind, and don’t be afraid to engage or ask questions when you aren’t sure of something.

What do you enjoy doing in your spare time?

Lifting weights!

Name one or two favorite blogs or books you have read and would recommend to others.

Four Days to Glory, about two high-school wrestlers in pursuit of their fourth state championship. An inspiring story about the importance of hard work and determination.

 

Robyn L. Ball
Statistical Consultant, Stanford University Center for Artificial Intelligence in Medicine & Imaging (AIMI)

 

What or who inspired you to be a statistician/data scientist?

When working on my BS and MS in mathematics, I thought I wanted to be a theoretical mathematician and philosopher. While a master’s student, I took a statistics class from Blair Sterba-Boatwright, who elegantly explained the fundamentals of statistical concepts. Then, for my master’s thesis, I developed a machine learning algorithm with Philippe Tissot and Beate Zimmer used for many years by the Texas Parks & Wildlife Department to preserve wildlife. I was so excited that what I built could actually be used—and used for good—that I decided to pursue statistics.

Plus, options. When I was in high school, someone gave me the best advice: “Make the choice that gives you the most options—you can always turn something down if you decide you don’t want to do it.” Statistics gives me options; I can work in just about any field.

Why did you become a consultant?

Mainly, it’s fun! I love getting to learn all the time, and I enjoy the creative process of understanding what the investigator/collaborator wants to know, why they want to know it, how they plan to use it, and then translating that into a statistical framework that provides a pathway to a trustworthy result.

Name a few specific skills you need to be a consultant.

I think it’s more qualities, rather than skills, though skills will grow over time. In my opinion, the personal qualities needed for success are the following:

• A natural curiosity to learn and a willingness to ask questions
• Perseverance and integrity (relationships—and trust—take time and persistence). Be true to your word.
• Enjoyment of the creative process of finding the right statistical framework for the problem at hand

What is the most exciting part of consulting?

For me, I get excited when the investigator/collaborator lights up and says, “Yes, that’s it!” Sometimes, they don’t know the question they truly want to ask, and getting there is half the fun. Also, finding a way to get the data back into the hands of the expert is powerful. They know what to look for, and so providing a means for them to interrogate their data—perhaps in an interactive way—has led to insightful discoveries. As Mary Ann Handel put it, “I don’t have to send you an email at 2 a.m. when I have an idea and a question about a gene’s expression; I can just log in and look for myself!”

What is the best piece of advice you received from a mentor regarding statistics or consulting?

I’m not sure who told me this, but it has stood the test of time: “You may have the most brilliant idea, but if you can’t express it or if it’s so complicated that no one understands it, no one will want to use it. Learn to communicate and choose the simplest, most straightforward approach first.”

What advice would you give to statisticians just beginning their careers?

It’s the same advice I give everyone. Spend some time with yourself. Write down what is most important to you in every area of your life: where you live; relationships; community; your work; etc. Don’t consider any barriers. Just take the time to write down what you want because you are either moving toward your goal or you are moving away from it; there is no standing still. Then, every decision becomes clearer.

Above all, trust yourself and be trustworthy. Trusting relationships with friends and colleagues will always see you through. Don’t be afraid of a challenge or a change; walk through the open doors. Importantly though, listen to yourself when it’s time to walk away.

What do you enjoy doing in your spare time?

I love hiking, camping, snowshoeing, staring at mountains, and watching waves crash. Also, I enjoy spending time with family and friends, whether just talking or going on adventures together.

Name one or two favorite blogs or books you have read and would recommend to others.

These aren’t statistics books, I know, but …

On the Road – Jack Kerouac

Together Is Better: A Little Book of Inspiration – Simon Sinek

 

Marlene J. Egger
Professor (tenured), Division of Public Health, Department of Family and Preventive Medicine, University of Utah School of Medicine

 

What or who inspired you to be a statistician/data scientist?

In 1970, I went to Knox College in Illinois. My favorite professors were Rothwell Stephens and Bob Oberg (another ASA member). Rothwell Stephens suggested biostatistics, as I was a double major in math and biology and had done well in his intermediate theory of statistics course. He also wrote a letter of recommendation for me to Stanford. I was further inspired by Ingram Olkin, Brad Efron, Persi Diaconis, Ted Anderson, Alice Whittemore, and others. When it was time to do my dissertation, I did it with Bill (Byron William) Brown in biostatistics, and he assisted me in getting a position at the University of Utah, where I still work today.

Why did you become a consultant?

It just happened. At the University of Utah, there was/is no statistics department nor a department of biostatistics. So, departments knew they needed statistical scientists, though they didn’t call it statistical science back then. In my position in 1979, there were teaching, research, and administrative responsibilities, but “research” really meant statistical collaboration or consultation on biomedical research, as it paid our salaries even in the tenure track. I had the good fortune to work with the Cooperative Systematic Studies of Rheumatic Diseases with John R. Ward, and Bill Brown was on our advisory committee. John Ward turned out to be one of my best mentors. Thus began a collaborative research effort that lasted through the mid-1990s, with side trips in cancer biostatistics, then into health services research, maternal and child public health, and now urogynecology statistics. So, I am an internal consultant, with all the benefits and constraints of internal consulting.

Name a few specific skills you need to be a consultant.

Keeping up with developments in statistics, statistical software, and advances in computing is essential, as that is the capital a statistical consultant brings to the table. The ASA has fine continuing education programs in this regard, though their value was not always as well understood as it is now. Proactiveness and time management are essential. Diplomatic skills with grant writers are essential. Contract writing is not as formal for an internal consultant as an external consultant, but mutual, experience-based trust is essential. For example, it is generally a norm that the statistician who wrote the grant proposal will be the statistician doing the work of the grant. But occasionally, I have been shocked by researchers one might characterize as nouveau-riche, who were more absorbed in their own power than in any sense of collegial norms.

What is the most exciting part of consulting?

My favorite part of statistical consulting is the ability to go into a new substantive area equipped with the skills to make strong analytical contributions. In about 2006, I met another of my favorite colleagues, Ingrid E. Nygaard, who was very interested in a previously untouchable subject: women’s pelvic floor disorders. Earlier in my lifetime, this was far too private to be discussed, and yet 50% of women will have a pelvic floor disorder by age 75. We are still collaborating.

What is the best piece of advice you received from a mentor regarding statistics or consulting?

Well, this is about neither, but rather advice for life. I received it from Gladys Reynolds, the statistician who did pioneering research on STDs and was the first woman to run a Centers for Disease Control and Prevention statistics branch. Gladys helped found the ASA Section on Statistics in Epidemiology. I have known her to stop for a panhandler and ask, “What do you really want?” In one case, she gave a young woman a bus ticket to get off the street and go home. Gladys told me, “It is always time to right a wrong.” When I see the Me Too and Black Lives Matter movements, I think of what my generation encountered, and the generations before me, and what we accomplished or failed to solve. And I am heartened by the courage of a new generation. It is always time to right a wrong.

What advice would you give to statisticians just beginning their careers?

It is such a different world now than in 1979, when there were no cell phones and it took five minutes to run a logistic regression on a good computer! I think the best advice I can give is to continue to learn. Trans-oceanic collaborations have become routine. Bayesian statistics and modern causal methods will be very important in the lifetimes of new statisticians. Big Data and supercomputing will continue to draw on our expertise. Look broadly at what influences statistics and stay current with internet and computer advances, programming languages, databases, and related software.

What do you enjoy doing in your spare time?

I have had many recreational activities over the years: kayaking; cooking Indian food; poetry; oil painting; and gardening, to name a few. In this modern world, it is important to have your own life, and the analytic mind requires counterbalances. Whitewater kayaking was a blessing to me, as it was physical, nonmathematical, and focused me in the moment. As I begin to look toward retirement, I have a new hobby—amateur astronomy—and I am looking forward to the time when I will be able to allocate my statistical expertise to questions that attract me in this area.

Name one or two favorite blogs or books you have read and would recommend to others.

Statistical or nonstatistical? I think Peter Block’s Flawless Consulting is a classic, as is James Boen and Douglas Zahn’s The Human Side of Statistical Consulting, though I very much like the content of Javier Cabrera and Andrew McDougall’s Statistical Consulting. I read the Women’s Review of Books attentively, as it tells me what young women are thinking.

 

Gregory Csikos
Sole Practitioner (Gregory Csikos, CPA, CFE, GStat)

 

What or who inspired you to be a statistician/data scientist?

I can’t identify anything or anyone specific who inspired me to become a statistician. I was working as an accountant at a CPA firm and realized the growing importance of data analysis, including descriptive and inferential statistics, to answering business questions. At that point, I decided to enter the Master of Applied Statistics program at Penn State.

Why did you become a consultant?

I started my solo practice in 2016, after eight years of working at public accounting firms. I provide tax, financial accounting, and forensic accounting services. My statistical experience is most relevant to the forensic accounting aspect of my practice. 

I decided to start my own practice because self-employment gives me autonomy and long-term security.

Name a few specific skills you need to be a consultant.

Being able to translate what a client wants into services you can provide that will result in the appropriate answers, knowing how to find and retain clients, ensuring you get paid, and dealing with the administrative aspects of being self-employed.

What is the most exciting part of consulting?

I don’t think my work is “exciting,” but it is enjoyable. I get a lot of satisfaction from making order out of chaos and providing an answer to a puzzle faced by a client.

What is the best piece of advice you received from a mentor regarding statistics or consulting?

Not everyone should be your client. It is normal and healthy to not always match with every potential client, whether that’s regarding the client’s professional needs, financial resources, or working style.

What advice would you give to statisticians just beginning their careers?

Know what you’re worth. I’ve noticed statisticians undervalue their skills and seem ignorant of what other highly trained professionals are paid.

What do you enjoy doing in your spare time?

Exploring my adopted city, Philadelphia, and listening to Mary Beard lectures on YouTube.

Name one or two favorite blogs or books you have read and would recommend to others.

Of what I’ve read most recently, I’d recommend 12 Rules for Life: An Antidote to Chaos by Jordan Peterson.

 

Charles Kincaid
Product Owner / Principal Data Scientist, Experis Solutions

 

What or who inspired you to be a statistician/data scientist?

The undergraduate statistics courses taught at Kansas State University were standard courses, but they excited me with what could be done. When I started taking graduate classes, the instructors made it so alive with possibilities that I never looked back.

Why did you become a consultant?

I’ve always been a consultant. Kansas State had a consulting center in which students helped faculty and grad students from other departments. It fits well into my desire to help others.

Name a few specific skills you need to be a consultant.

The ability to listen to others and dig into the questions behind their questions is very important, as well as the ability to build up trust with your client so they become more of a collaborator. The ability to learn other disciplines and grasp the technical aspects quickly is an immense help for doing more than just order taking. And, of course, the many other skills necessary. 🙂

What is the most exciting part of consulting?

The feeling of accomplishment and excitement from helping people solve problems is definitely exciting. We make people’s jobs easier, help them create better products, and even make the world a better place.

What is the best piece of advice you received from a mentor regarding statistics or consulting?

“Clients always lie to you.” This advice from a professor of computer science at Kansas State has been helpful my entire career. They don’t do it intentionally. It’s just that people come to us with problems and questions they’ve filtered through their understanding and experience, which often gives an inadequate representation of what they need.

What advice would you give to statisticians just beginning their careers?

If you want to be a statistician, do statistics. Find opportunities to do, or help with, a wide variety of consulting projects. Learn the skills that cut across disciplines. If you want to specialize, the broad skills and experience will help you more than specializing from the beginning.

What do you enjoy doing in your spare time?

Over the years, I’ve had a lot of hobbies and interests. In this season of my life, I enjoy playing board games, reading theology books, doing tough mudders, playing softball, dancing, watching movies, and playing with my grand kids.

 

LeAnna Stork
Soy Crop Modeling Lead, The Climate Corporation – Bayer Crop Science

 

What or who inspired you to be a statistician/data scientist?

My dad. I was good at math in high school but was unsure at the time of what types of careers might be possible. He had a friend who was an actuary (I had never heard of an actuary at the time!) and suggested I take some statistics classes in college. I loved the stats classes so much that I ended up majoring in statistics and pursuing this as my career path.

Why did you become a consultant?

Because I like learning from people about diverse business problems. For me, the most rewarding part of being a consultant is listening to customers’ problems and asking them thought-provoking questions about those problems they may not have even considered.

Name a few specific skills you need to be a consultant.

The ability to ask your client really good questions—not just about their data, but also about the “why.” What is the purpose and objective of their study? What questions will the results of the study answer? How will the results of the analysis be used? Who/what will be affected by the results? What are important assumptions in the collected data?

What is the most exciting part of consulting?

Meeting new people and learning new spaces. Thinking outside the box has really accelerated my career development.

What is the best piece of advice you received from a mentor regarding statistics or consulting?

Put yourself in the researcher’s shoes; they may have spent years planning and conducting the study you are consulting on. Think creatively of the “best” statistical solution that is practical and achievable for the researcher. Sometimes the best solution is the simple one.

What advice would you give to statisticians just beginning their careers?

Walk the hallways and meet with your collaborators; don’t hide out in your cubicle! Visit their laboratories, fields, factories, etc. to see their processes and the data they are collecting. Ask questions about the process so you can truly understand the variability associated with the data you are analyzing. 

What do you enjoy doing in your spare time?

Chasing after my kids, traveling to new places, and tasting wine!

Name one or two favorite blogs or books you have read and would recommend to others.

The Oz Principle: Getting Results Through Individual and Organizational Accountability by Roger Connors, Tom Smith, and Craig Hickman. The concept in this book is simple: Individuals are accountable for results. The authors highlight the “See It. Own It. Solve It. Do It.” concept. I believe most people are good at the first three steps: See It. Own It. Solve It. But to cross the finish line and truly deliver impactful results, those who master “Do It” will achieve greater success. Simply seeing the problem, identifying flaws, and blaming others for failures will not deliver results. People who take accountability for actions, identify solutions, and implement them will achieve great results. I hold myself and my team accountable to this standard.

 

Todd Coffey
Chair and Associate Professor, Department of Research and Biostatistics, Idaho College of Osteopathic Medicine

 

What or who inspired you to be a statistician/data scientist?

I took a course in statistics as a sophomore in college. In one of the first lectures, the professor described how statistical methods could be used to design and analyze a clinical trial to determine if a novel therapy was better than placebo. The recognition that statistics held the key to understanding how to determine which experimental treatments were better, worse, or no different fascinated me. I quickly became hooked on becoming a statistician and never looked back.

Why did you become a consultant?

Two reasons: I was fascinated with the research being done in other fields and I loved the intellectual challenges consulting requires. These challenges include understanding the research question in the collaborator’s language, translating it to a statistical framework, developing a broad methodological background, improving programming skills to implement solutions, retranslating the results into the language of the applicable field, and communicating how the research question has been appropriately answered. The challenges vary across disciplines, so a consultant can move from one to another and continue to find opportunities.

Name a few specific skills you need to be an effective consultant.

Effective consultants I have worked with have a strong and broad methodological background and a solid understanding of statistical theory. The best consultants add to that background with active listening, good questions, excellent written and verbal communication, creative thinking, appropriate lack of fear toward trying something new, analytical thinking to understand advantages and disadvantages of various approaches, and social engagement with the collaborator.

What is the most exciting part of consulting?

When a reluctant collaborator recognizes the power of statistical thinking and transforms into a champion for implementing the methods proposed. This process is the most satisfying when you can convince the collaborator to invest resources into an experimental design or study plan he or she has never considered and then demonstrate results through the analysis that could not have been achieved without statistical methodology. When this happens, the surprise and excitement on the face of the astonished collaborator is priceless.

What is the best piece of advice you received from a mentor regarding statistics or consulting?

On a recruiting trip to a graduate school I ultimately attended, I was taken to see a graduate of the program who was working locally as a statistical consultant. After some small talk, he asked me what I thought was the most important question a statistical consultant needed to ask. Before I could answer, he responded that consultants must understand completely the question the collaborator is asking. It was an impressionable moment, and I learned clearly that all the fancy statistics I would learn in graduate school wouldn’t help the collaborator if I answered the wrong question.

What advice would you give to statisticians just beginning their careers?

Recognize your influence as a statistician will likely be proportional to the professional closeness of the relationships you develop with your collaborators. Becoming a full partner with those you work with is critical. You may have an optimal technical solution to a research question, but if the collaborator does not trust you, you’ll never get the chance to show the power of statistics.