What a statistician really does
You decide which method fits the question, clean the data, run the analysis, and tell researchers what their results really mean, even when they hoped for something else.
FieldScience and engineering
Preparation (O*NET Job Zone)Extensive preparation needed
What the work involves
What fills a typical week for statisticians, built from O*NET occupation data.
- Clean and check new datasets for errors, missing values and impossible entries
- Pick the right method for a research question and write it into an analysis plan
- Write and run code in R, SAS or Python to fit models and make tables and charts
- Review analyses other people did and judge whether the method was valid
- Meet with researchers or clients to explain results and limits
- Plan sample sizes and sampling methods for new studies
What the days are like
What people in the job know
- Exactness is the job. A small coding or method error can overturn a conclusion. Importance of being exact or accurate: 67% extremely important; Consequence of error: 35% serious (O*NET Work Context)
- Judging methods matters as much as running them. The top tasks are about whether an analysis is valid. Task 2 (importance 92): Evaluate statistical methods and procedures for validity; Task 4 (importance 88): Determine whether statistical methods suit user needs (O*NET)
- Data cleaning and weighting is a core, high importance part of the work, not a chore you hand off. Task 5 (importance 87): Prepare data for processing by organizing it, checking for errors, and adjusting and weighting raw data (O*NET)
- It is a focused, seated job with steady hours for most people. Spend time sitting: 71% continually or almost continually; Duration of typical work week: 52% 40 hours; Work schedules: 85% regular (O*NET Work Context)
- Deadlines come in monthly waves rather than every day. Time pressure: 62% once a month or more but not every week (O*NET Work Context)
How people get into it
O*NET places this in Job Zone 5. Of surveyed workers, 62% say a master's degree is required, 14% a bachelor's degree and 10% a doctoral degree; statistics or biostatistics are the usual fields. Many start as statistical analysts or programmers in government, healthcare research, pharma or industry.
The Firstday trial, easy to hard
Three simulated tasks at Brookhaven Health Research Institute, Biostatistics Core, a fictional company, with AI coworkers who message you, react to your work and coach with questions. Nobody scores you.
What the trial can't show: This trial does not cover writing large analysis programs from scratch, working with very large databases, deep mathematical theory, or the full cycle of a study from design to publication. Code is scaffolded so non programmers can take part.
Reading about it is one thing.
Find out how the work feels to you before you spend on a degree, course or job change. Your first trial is free.
Other careers you can try
Job details on this page are built from O*NET OnLine, 15-2041.00. This page includes information from the O*NET 31.0 Database by the U.S. Department of Labor, Employment and Training Administration (USDOL/ETA). Used under the CC BY 4.0 license. O*NET® is a trademark of USDOL/ETA.