Valerie Durkalski-Mauldin is a professor of biostatistics in the department of public health sciences at the Medical University of South Carolina and serves as the director of the Data Coordination Unit, a unit that specializes in the design, coordination, and analysis of multicenter clinical trials.

I can’t live without my fellow master’s (MS) statisticians! Their contributions to each project are invaluable. The Data Coordination Unit (DCU) serves as the data coordinating center for several NIH-funded multicenter clinical trials and clinical trial networks. We currently have seven PhD statisticians and six MS statisticians on our team at the DCU, in addition to several project and data managers and computer programmers.

Each of the clinical trials we coordinate involves a statistical team of at least one MS and one PhD statistician to work on the statistical aspects of the trial and collaborate with the study team on the coordination of the trial. Key tasks of the statistical team include study design and statistical analysis plan development, data cleaning, generation of the Data and Safety Monitoring Board (DSMB) reports, conduct of interim and final analyses (including program validation), and creation of public use data sets for submission to the NIH data repository. It is quite a workload for each project, and the contributions of the MS statisticians are invaluable to the team.

Our PhD and MS statisticians work closely with one another and enjoy a mutually beneficial relationship. The PhD statistician often acts as an informal mentor, and the MS statistician has a trusted source of advice and expertise when questions arise.

The DCU MS statisticians are involved before trial initiation, during trial execution, and after trial completion. As several of our trials are NIH-funded, the NIH grant submission process is an excellent opportunity for the statistical team to work together with their clinical colleagues to develop the appropriate trial design to address the important clinical questions of interest.

Our MS statisticians work on literature reviews to support the analysis plan and assist with sample size estimation and program simulation studies required for more complex trial designs when we need to better understand the trial’s operating characteristics. This exposure to the trial-development and grant-writing process is the beginning of the team-building process. All our MS statisticians have enjoyed the exposure to this aspect of trial development, as they often do not receive any formal training while in school in clinical trials or NIH grant writing.

Once a trial is funded, the work scope turns toward daily trial-related tasks, including development of the statistical analysis plan, validation of analysis and report programs, working closely with data managers on case report form development and centralized data monitoring procedures, and report generation. Our MS statisticians are savvy programmers (in SAS and/or R), which is essential for many aspects of their job. For centralized data monitoring, the MS statistician and data manager work together to define the missing data and logic checks to be programmed for each data item. They also outline additional data checks and define which will be performed by the data manager and which will be performed by the statistician. Examples of items within a trial that our statistical team reviews include logic checks for sequences and dates, comparison of data distributions within and across sites, and trends and patterns of data.

Our MS statisticians also have developed graphics for centralized monitoring tasks to facilitate the monitoring of site performance and data quality. After the trial is completed, MS statisticians assist with primary and secondary analyses, manuscript preparation, and the creation of public use data sets. The list goes on for the contributions our MS statisticians bring to each clinical trial study team, and our PhD team members are grateful for their contributions.

In addition to the daily trial-related work tasks, our statistical group (both MS and PhD members) meets bimonthly to discuss statistical topics and challenges they have encountered with various trials. This provides the opportunity for relaxed discussion within our group and is a great learning opportunity for everyone.

Based on the questions, we identify topics of interest that are then presented to the group during a monthly “lunch n’ learn” session. Topics have covered a wide range, including programming graphics in R, review of FDA guidances, randomization techniques, handling of missing data, and multiplicity. There is never a shortage of subjects, and it engages the group to stay in touch with the current methodology research.

We also encourage our MS statisticians to publish methodology research. Having the combined statistical team of PhD and MS members encourages this aspect, as several of our MS statisticians have significant authorship in peer-reviewed journals and present at national and clinical meetings.

All these activities encourage professional development, which is important for any profession. Some MS statisticians may later want to pursue their PhD, while others are already doing what they love. Regardless of the goal or setting, I strongly believe in the collaboration between PhD and MS statisticians.

So, what does it take to be a successful MS statistician working in clinical trials? Let’s ask the experts. Here are a few suggestions from our team.

Lydia Foster earned her Master of Science degree in applied statistics from Kennesaw State University with an undergraduate degree in mathematics. She worked for the Centers for Disease Control and Prevention prior to joining the DCU in 2011. Foster believes strong statistical programming is key. In addition, being able to clean, manipulate, and present data is helpful. This isn’t always the focus of a MS-level program, so a student should consider other resources such as SAS courses and certifications and R tutorials. Collaboration is another important skill. Study teams often consist of several people with different areas of expertise, and the project is most successful when each person can contribute in their area of strength.

Holly Tillman earned her master’s degree in industrial statistics from the University of South Carolina with an undergraduate degree in statistics. She worked for the Office of Research and Statistics in South Carolina before joining the DCU in 2011. Tillman stresses the importance of having attention to detail and accuracy. “Once you graduate and find a position that suits you, continue to be exposed to new projects.” The ability to understand the study protocol/design and relate it to the data analysis plan is a key skill set and best learned by exposure to real projects. Practice using different techniques to achieve the same outcome through programming and analyses so you are able to check yourself for errors. Finally, realize you never stop learning in both statistics and programming, so don’t be afraid to take more courses, tutorials, and webinars whenever possible.

Jyoti Arora earned her master’s degree in statistics from Rashtrasant Tukadoji Maharaj University in India with an undergraduate degree in statistics. She suggests you engage with real-world data as a student. Students should participate in data analysis competitions such as those on DrivenData.org, Kaggle.com, and KDnuggets.com and ask their professors for help if they have any questions. This will offer them an opportunity to work on the unstructured data and develop skills to identify patterns, trends, and relationships within data. Data visualization is a tremendously useful skill to learn and maintain. Students earning a degree in the field of statistics should also focus on developing a broad perspective and understanding of the world by exposing themselves to people, topics, and issues in disciplines such as biology, psychology, public policy, social science, or computer science. This will help in collaborating and communicating with people from other backgrounds.

Angela Pauls earned her master’s degree in statistics from Northern Illinois University with an undergraduate degree in computer science. She highlights the importance of strong programing skills, professional knowledge, and hands-on experience as significant criteria for leading a successful career. Continuous education and good collaboration with PhD-level statisticians can keep you on the top of your game, as well. Pay attention to the detail, as you will be the one who will work with the data and provide analysis results. If you don’t pay attention to the detail and process carefully and patiently, it is easy to make a mistake, which not only reflects poorly on you, but potentially those you work with and, even worse, the trial.