Data is transforming health care, just as it’s transformed nearly every other field of endeavor. However, data is a resource whose value is realized only after it’s been processed and analyzed. Biostatisticians play key roles in unlocking the potential of data to revolutionize the health care industry and enhance the health and well-being of individuals and communities.
Biostatistics applies statistical theory and mathematical principles to biological and health data to help identify the causes of disease, devise effective treatments and implement preventive measures. The growing importance of biostatistics is evident in the wide variety of biostatistics careers available to people who possess the skills and experience to convert the ever-expanding quantity of medical and health data into insights that support the decisions that policymakers and health care professionals make.
These are just three examples of the roles biostatistics can play in improving health systems and individual outcomes:
- The Helmholtz Center for Infection Research applies biostatistics techniques to forecast the potential of health systems to be overwhelmed by COVID-19 patients.
- Biostatistics measured the effectiveness of public health interventions in Mozambique to address sanitary conditions and improve patient outcomes.
- Statistical models identified characteristics associated with short- and long-term survival rates for people diagnosed with colorectal cancer.
What Is Biostatistics?
The short answer to the question, “What is biostatistics?” is that it’s the field of medicine focused on the application of statistical methods and principles to the study of biology. The terms “biostatistics” and “biometry” are often used interchangeably, although biometry’s broader definition encompasses all the biological sciences, while biostatistics is typically limited to medical applications.
The International Biometric Society defines biometry as the science concerned with the development and use of statistical and mathematical methods to solve problems in biology via data analytics. Biostatistics encompasses such health-related fields as genetics, genomics, neuroscience, environmental health and pharmaceuticals. However, the work of biostatisticians touches every aspect of medicine and health care: from pharmaceutical research seeking new treatments to clinical research measuring the effectiveness of cutting-edge therapies for combating cancer, heart disease and other maladies.
Converting Medical and Health Data into Insights
At its most fundamental level, biostatistics is the field that converts data related to disease, medicine and public health into insights that help health care professionals and health policymakers address the challenges related to the health of individuals and communities. However, for the data to be useful and trustworthy, it must be validated:
- Complete: The degree to which all required data is known.
- Clean: Data errors are corrected or removed, irrelevant data is excluded and duplicate data is excised.
- Contextualized: Data values are confirmed to be appropriate for their context.
- Normalized: Data looks and reads the same across all records in the data set.
Primary sources of data for biostatistics applications include electronic medical record (EMR) and electronic health record (EHR) systems. Accessing useful data for creating statistical models and using other analytics tools requires open systems and consistent data formats across health care organizations. New cloud-based data analytics platforms hold promise for overcoming obstacles related to file formats, timely data sharing and securing patients’ private information.
How Biostatistics Contributes to Medical Research and Treatment
Biostatisticians contribute to researchers developing more effective treatments for cancer and infectious diseases, as well as those working in environmental health and behavioral sciences. Among the ways that biostatistics supports cutting-edge medical research are:
- Clinical trials: Help design studies, optimize sample sizes, choose data collection methods and clean data.
- Public health programs: Assist health officials in government, nonprofit organizations and hospitals in understanding the significance of public health research.
- Epidemiological studies: Contribute to research by public health professionals into the factors that influence the causes, behavior and distribution of disease outbreaks, such as COVID-19.
- Meta-analysis and evidence-based medicine: Perform systematic reviews of medical research on specific topics to integrate results and identify potential outcomes that can be applied to develop evidence-based health care.
- Genome sequencing: Cut through the complexity of the massive amounts of data generated by genome sequencing to distinguish genetic traits and variants that may cause disease.
How Advanced Statistical Methods Benefit Medicine and Health Sciences
Generating valid and reliable results requires choosing the correct statistical methods and approaches for the unique characteristics of each research study. Other researchers must also be able to reproduce the research results. Among the techniques that biostatisticians employ are:
- Multiple testing problem (multiplicity): Biostatisticians must account for the damage that an error in the data has caused that could result in a false positive being inflated when a set of hypotheses is tested simultaneously within a single study.
- Bayesian analysis: Bayesian analysis is a statistical technique that uses probability statements to answer questions about unknown parameters.
- Model averaging: In model averaging, several models run simultaneously, either to make predictions or infer parameters.
- Causal inferences: Causal inference is a form of inductive reasoning that concludes that some entity is or isn’t likely to be the cause of something else.
- Estimation in disease state changes: Morbidity measures the incidence (number of persons who become ill) and prevalence (number who are ill at a given time) of a disease, injury or disability. Estimation is used to calculate incidence proportion (risk) for new diseases or injuries.
What Does a Biostatistician Do?
The primary role of biostatisticians is to apply mathematical and statistical techniques to determine the causes of diseases, injuries and other health issues. More specifically, what a biostatistician does is work as part of a team of researchers and health care providers to discover more effective approaches to the treatment and prevention of common illnesses, including the following:
- Devising more effective solutions to health problems
- Developing faster and more affordable treatment options
- Discovering new ways to apply data analytics tools to help solve problems related to individual health care and public health
Duties and Responsibilities of Biostatisticians
The roles of biostatisticians frequently overlap with those of medical informaticians, bioinformaticians and epidemiologists. The four broad categories of biostatistician tasks and responsibilities are clinical trials, interventional studies, statistical genetics, and systematic reviews and meta-analyses.
- Biostatisticians participate in the design of clinical trials as well as in the analysis of the data that they generate. This includes determining the protocol, preparing case report forms, and writing interim and final reports.
- For observational studies, biostatisticians apply mathematical equations to explain the relationships between variables, whether via multiple measures of the same subject over time or studies of multiple patients interacting with different departments in a health care facility.
- When working on projects related to statistical genetics, biostatisticians integrate findings from mathematics, statistics, genetics, epidemiology and bioinformatics. This requires a background that encompasses a range of disciplines and familiarity with various modeling techniques.
- Determining the level of evidence present in medical research studies requires systematic reviews and meta-analysis that biostatisticians conduct to identify the value of the research results to other researchers and health care professionals.
The education and training required to become a biostatistician begins with earning a master’s degree in biostatistics or public health with concentrations in biostatistics and epidemiology. The most common skills of biostatisticians include mathematics and statistical analysis, problem-solving, critical thinking, communication and teamwork. Among the technical skills that may be required to qualify for a position as a biostatistician are:
- SAS, R and other statistical programming languages
- Relational and nonrelational databases
- Ruby, Python and other general programming languages
Biostatisticians rely on various tools in their work, which includes designing statistical studies and applying advanced analysis techniques to extract intelligence from massive health care datasets. Here are 10 popular statistical tools that biostatisticians use, according to Kolabtree: Stata, R, GraphPad Prism, SAS, IBM SPSS, MATLAB, JMP, Minitab, Statista and Microsoft Excel.
Typical Workday of a Biostatistician
Biostatisticians usually work a standard 40-hour week, although they may work overtime to meet deadlines for specific projects. While biostatisticians do much of their work on computers, their job requires interacting with team members, writing reports, and other communication and interpersonal duties. The profession allows people to contribute to improving the health of people in their communities without participating directly in their treatment.
- Typical data sources for medical and health statistics include surveys, administrative and medical records, claims data, vital statistics from government agencies, surveillance, disease registries and peer-reviewed literature.
- Among the statistical analysis tools that biostatisticians use are the IBM Statistical Package for the Social Sciences (SPSS), MATLAB, GraphPad Prism and Microsoft Excel.
- Collaboration with other researchers, health care professionals and public officials is a vital part of the work that biostatisticians do and the focus of much of their training.
Common Biostatistician Projects and Work Environments
Biostatisticians are employed by private companies, research foundations, educational institutions and government agencies. They spend much of their time working on computers in offices and research facilities as part of a team of researchers, scientists and other professionals in public health and health-related fields. In addition to projects involving the use of SAS, R and other statistics and data analytics tools, biostatisticians participate in these research tasks:
- Study design and protocol development
- Quantitative and qualitative research projects
- Data analysis and interpretation for clinical trials
- Data administration and management
- Public health modeling of disease outbreaks
- Survival analysis for new drugs and treatment approaches
- Institutional review boards (IRBs) to vet the ethics of research procedures
- Research on the effectiveness of cancer treatments
Resources on the Roles and Responsibilities of Biostatisticians
- Pubrica Academy, Role of Biostatistics and Responsibilities of Biostatisticians in Clinical Medical Research — A description of biostatistics applications and the contributions of biostatisticians to medical research projects.
- CROS NT, How Well Do You Understand the Role of Biostatisticians in Medical Research? — An explanation of biostatisticians’ work for nonstatisticians who are members of clinical research teams.
Is Biostatistics a Good Career?
The American Statistical Association (ASA) predicted that 2021 would be “a year of opportunity for statisticians” because of growing demand for advanced data analytics skills in pharmaceutical manufacturing, government and other large sectors of the economy.
- Statistician is rated the sixth best career in S. News & World Report’s listing of the 100 best jobs of 2021. It’s also rated the fifth best science, technology, engineering and math (STEM) job and the second best business job.
- The U.S. Bureau of Labor Statistics (BLS) identifies statistician as the fourth fastest growing career on its list of the 20 fastest growing occupations between 2019 and 2029; the number of jobs is forecast to increase by 35% in that period.
- BioSpace estimates that employment opportunities for biostatisticians will increase by 31% in the U.S. between 2019 and 2028.
Career Options for Biostatisticians
Entry-level positions in biostatistics are available in all areas of medicine and scientific research, including medical assistant, research fellow, software engineer, laboratory technician and instructor. The employment site Zippia describes the 10 best jobs for people entering the field of biostatistics:
- Data analyst
- Biostatistician
- Data scientist
- Statistician
- Analyst
- Software engineer
- Research analyst
- Research internship
- Bioinformatics analyst
- Bioinformatics scientist
Careers in biostatistics involve working in one or more of four areas: clinical trials, public health programs, genome sequencing research and epidemiological studies.
Participating in Clinical Trials
Clinical trials evaluate the effectiveness of medical, surgical and behavioral interventions on patients recruited specifically for the studies. The trials also help determine whether specific treatments have more or less harmful side effects than existing approaches. Some trials attempt to identify diseases before symptoms arise or to prevent diseases entirely; they may also study the role of caregivers and support groups in treating and preventing illnesses.
Contributing to Public Health Programs
The goal of public health programs is to ensure conditions in which people can be healthy. Biostatistics plays a pivotal role in these programs by addressing all three core public health functions:
- Assessment identifies problems that threaten a population’s health and the extent and seriousness of that threat.
- Policy development prioritizes the problems, determines possible intervention and prevention measures, implements policies and regulations to address the problems, and predicts the effects of the policies on the at-risk population.
- Assurance puts in place the services necessary to achieve the goals of the policies and regulations and monitors the community’s compliance with the policies.
Conducting Genome Sequencing Research
Biostatistics is central to the work that medical researchers do to create The Cancer Genome Atlas (TCGA) and the International Cancer Genome Consortium (ICGC) to support cancer genomics:
- To produce somatic variant call sets from exome (TCGA)
- To create whole genome-level models (ICGC)
The two programs rely on “scientific crowdsourcing” to aggregate whole genome sequencing data from 2,658 cancers representing 38 tumor types. The result was 746 samples that serve as benchmarks for comparing exome and genome somatic variant detection techniques.
Performing Epidemiological Studies
A timely example of biostatistics applied to determine the causes and effects of diseases is the work that medical researchers have done to measure the effectiveness of vaccines that prevent COVID-19. Statistical techniques were used to estimate the effects of the vaccines in case-control and test-negative frameworks while accounting for bias in the results.
The research findings serve as guideposts for public health agencies and health care providers investigating the most effective strategies for measuring the impact and effect of COVID-19 vaccinations on specific populations, including asymptomatic individuals.
Industries in Which Biostatisticians Are Employed
Biostatisticians are qualified to work in any setting that relies on calculating risk and predicting outcomes.
Most careers in biostatistics focus on one of four specific fields of medicine: epidemiology, public health, pharmaceuticals and genetics:
- Among the biostatistics specialties within epidemiology are environmental, genetic, social and nutritional statisticians. Typical activities include determining the rates of infectious and chronic diseases and tracking outbreaks of disease.
- The goals of public health statisticians are to prevent disease and promote long, healthy lives. They work on ways to improve sanitation, prevent infectious diseases, and educate the public on health and hygiene topics.
- Pharmacology statisticians support drug discovery activities, as well as drug development, approval and marketing. They participate in clinical trials, preclinical research and other aspects of drug development.
- Biostatistics is applied in genetics research to automate the process of identifying sequences that may indicate abnormalities causing birth defects and other health problems.
Biostatisticians work in offices, laboratories and in the field conducting a range of tasks, from designing research studies to analyzing and reporting on their results. In addition to technical and statistical skills, Indeed reports that biostatisticians require several personal and professional skills: written and oral communication, problem-solving, critical thinking, ability to work autonomously and adaptability.
Importance of Keeping Current on Biostatistics Tools and Techniques
Machine learning and other areas of artificial intelligence (AI) will continue to impact the way medical and health data is analyzed. The techniques will also facilitate gathering and processing the large quantities of data that will be generated in the future. Increased automation will enhance the use of seven different types of statistical analysis.
- Descriptive statistical analysis is a straightforward summary of the data and its characteristics, with no attempt to infer anything from the analysis.
- Inferential statistical analysis derives inferences from the data to suggest from the sample data what the population at large may think or how they may act, for example.
- Predictive statistical analysis applies statistics and mathematical models to current and past data to predict what will occur or how something will perform.
- Prescriptive statistical analysis goes beyond prediction to recommend specific actions based on its analysis of current and past data. The actions suggested may be in the short or long term.
- Exploratory data analysis performs a cursory analysis of the data prior to the full-scale investigation as a way to check assumptions, identify potential errors and spot patterns.
- Causal analysis attempts to explain why health-threatening events, such as COVID-19, occur and spread through a population.
- Mechanistic analysis examines the precise biological mechanisms that caused actions, as well as the various responses to those actions, as a way to discover how to reduce adverse reactions.
Resources on Careers in Biostatistics
- American Statistical Association, Career Resources — The professional association provides links to salary information, fellowships and grants, funding, ethics, and job opportunities.
- The Balance Careers, “How to Become a Biostatistician” — Among the topics covered are typical work hours, qualifications and related careers.
Biostatistics vs. Bioinformatics
While much overlap exists between biostatistics vs. bioinformatics, the two fields are distinct primarily in the scope of the projects they’re applied to.
- Bioinformatics uses computational technology to organize and analyze the huge data sets that studies in molecular biology are generating, including gene sequencing; gene expression studies; and pharmacogenomics, which studies how genes impact the way a person responds to drugs.
- Biostatistics has a much broader scope, covering the use of statistics and mathematical modeling to analyze and evaluate research relating to public health, medicine, biology and environmental health.
Biostatistics vs. Bioinformatics: Education and Skills
Most biostatisticians earn a master’s degree in biostatistics or public health with concentrations in biostatistics and epidemiology. The educational background required to qualify for positions in biostatistics is weighted heavily toward statistics, mathematics, programming, life sciences and physical sciences. The profession also calls for strong communication and interpersonal skills because much of the work entails collaborating with team members from diverse backgrounds.
For careers in bioinformatics, the educational requirements include a strong background in molecular biology and genetics as well as several bioscience specialties within those categories:
- Cell biology
- Comparative genomics
- Genetic mutations
- Chromosomes and gene expressions
- Molecular cloning
- Immunogenetics
- Gene mapping
- Gene sequencing
- Protein synthesis
- DNA and RNA
Bioinformaticists must be familiar with many different software tools, including the Genome Analysis Toolkit (GATK); the Blast and Bowtie sequence alignment systems; and Partek and other programs for sequencing, microarray and data analysis. Bioinformaticists and biostatisticians both rely on statistical analysis tools, such as SAS and IBM SPSS, as well as programming and machine learning skills.
Biostatistics vs. Bioinformatics: Roles and Responsibilities
Bioinformatics focuses on the collection and analysis of genetic codes and other complex biological data. Conversely, biostatistics emphasizes the design, implementation, analysis and interpretation of studies designed to improve medical treatments and public health in general.
- Bioinformaticists typically work on large databases of omics data: a subset of biotechnology that studies the functions and characteristics of specific biological processes. These include genomics for genes, proteomics for proteins and metabolomics for metabolic functions. The Human Genome Project is an example of the size and scope of such projects.
- Biostatisticians generally are involved in a broader range of topics related to medical and clinical research. They contribute to the design of studies, the protocols to be followed, and monitoring of ongoing research to ensure safety and efficacy.
Resources on Biostatistics vs. Bioinformatics
- Yoh, “Bioinformatics vs. Biostatistics: What’s the Difference?” — An explanation of the close links between the two fields as well as their primary distinctions in terms of broad vs. narrow focus of study.
- National Cancer Institute Center for Cancer Research, Bioinformatics Training and Education Program: Resources — Resources including support programs and collaborations, bioinformatics software resources, and sequencing facilities.
Biostatistics Salary
The BLS estimates that the median annual salary for statisticians working in research and development in the physical, engineering and life sciences was $102,370 as of May 2020. For biostatistics salaries in particular, the BLS reports that statisticians in insurance and related fields had a median annual salary of $88,450, and those working in health care and social assistance earned a median annual salary of $79,440.
The salary survey site PayScale reports that annual salaries for biostatisticians range from about $67,000 for people with one year or less of experience to approximately $129,000 for those with 20 years or more of experience. The median annual salary for all biostatisticians was about $77,000 as of July 2021, according to PayScale. For senior biostatisticians, the median annual salary was around $110,000.
Skills That Can Boost a Biostatistician’s Salary
According to figures that PayScale compiled, specific skills can affect biostatisticians’ salaries:
- Machine learning: 60% higher than the average salary
- Bioinformatics: 27% higher
- Research analysis: 8% higher
- Clinical research: 3% higher
Median annual salaries for biostatisticians who possess certain skills include the following (all figures as of July 2021):
- Clinical research: about $79,000
- Statistical analysis: about $79,000
- SAS: about $77,000
- Data analysis: about $76,000
With experience, biostatistician salaries increase at a steady rate:
- With 5 to 9 years of experience: $88,000
- With 10 to 19 years of experience: $98,000
- With 20 or more years of experience: $129,000
Biostatistics Job Outlook
The results of the ASA’s 2020 Work and Salary survey indicated that statisticians were happy with their chosen occupation:
- 55% of statisticians responding to the survey reported being very satisfied with their primary job, and an additional 36% were somewhat satisfied.
- 65% reported being very satisfied with their job security, 41% were very satisfied with their pay and 31% were very satisfied with their opportunities for advancement.
- The two work attributes that the survey respondents rated very important were doing interesting and enjoyable work (83%) and doing work that makes a positive contribution (73%).
This high level of job satisfaction is mirrored in the BLS’s job outlook for the profession: While growth for all statisticians is estimated to be 35% between 2019 and 2029, the health care industry’s and public policymakers’ growing reliance on data analytics will drive much of that increase, according to the BLS.
Data’s Growing Importance to Healthy Populations
The ever-increasing amount of data being collected about health, disease and genetics has the potential to lead to breakthroughs in public health and the health of individuals. This increases the importance of the role of biostatisticians in converting medical and health data into knowledge and intelligence that health care professionals and public health policy decision-makers can use.
The World Bank’s World Development Report 2021: Data for Better Lives identifies three pathways for the use of data to promote the health and well-being of communities and populations.
- The top pathway uses data to monitor the effects of government policies and individuals’ access to health care and other public services.
- The middle pathway uses data to support evidence-based policymaking and to improve the delivery of public services.
- The bottom pathway uses data to drive growth in the private sector’s provision of services.
Biostatistics plays a key role in enhancing the quality and accessibility of health care and promoting disease prevention through scientific and clinical research and the development of consistent and effective public health policies. Achieving these goals will require innovative approaches to repurpose and combine data sources in ways that are open, transparent and able to meet the needs of all stakeholders in public and private health care.
Biostatisticians as Key Contributors to a Healthier Future
The many challenges to public health brought to light as the world joined together to combat the COVID-19 pandemic also point toward solutions that new technologies have driven that can transform data into actionable insight. Making these insights available to decision-makers in health care and public policy depends on the work of biostatisticians. The result of their work is improved patient outcomes; prospering communities; and healthier, happier, more productive individuals. Individuals who are interested in a biostatistician career should consider pursuing a master’s degree in biostatistics or public health to develop the knowledge and skills to excel in the field.
Infographic Sources:
Indeed, “Learn About Being a Biostatistician”
Kolabtree, “Top 10 Statistical Tools Used in Medical Research”