Impact of the New ASA Undergraduate Curriculum Guidelines on the Hiring of Future Undergraduates Robert Vierkant Mayo Clinic, Rochester, MN
Outline Motivation for the topic Overview of statistics at Mayo Clinic – Type of work – Statistical team structure Desirable attributes of new graduates in statistics Review of new recommended ASA guidelines Alignment of guidelines with desired attributes Conclusions
Motivation Previous set of ASA guidelines drafted in 2000 Much has changed since then – Increased adoption of statistics in different disciplines – Advances in technology Ability to collect and store vast amounts of data Ability to analyze data using computationally intensive techniques – Increased demand for individuals with “real world” experience – Increased pace of changes in the field Decision to revamp guidelines based on these changes
Statistics at Mayo Clinic
Division of Biomedical Statistics and Informatics (BSI) – Nearly 200 statisticians at PhD, MS or BS level – Majority of work is consultative/collaborative statistics – Majority of clients are clinicians, researchers and basic scientists specializing in a given field of medicine, biology, genomics or basic science – Applied statistics in fields of medicine and biology
Statistics at Mayo Clinic Primary work units – Lead Statisticians (Faculty, PhD) High level support and oversight, complex analyses Time set aside for methodologic work – MS Statisticians (Master’s Degree trained) Logistical oversight, project management, intermediate and complex analyses – Statistical Programmer Analysts (SPA, Bachelor’s Degree trained) Programming and data management (~70% of work), basic and intermediate analyses – Research Fellows and Research Assistants (PhD) – Support Staff
Statistics at Mayo Clinic Primary work units – Lead Statisticians (Faculty, PhD) High level support and oversight, complex analyses Time set aside for methodologic work – MS Statisticians (Master’s Degree trained) Logistical oversight, project management, intermediate and complex analyses – Statistical Programmer Analysts (SPA, Bachelor’s Degree trained) Programming and data management (~70% of work), basic and intermediate analyses – Research Fellows and Research Assistants (PhD) – Support Staff
Statistics at Mayo Clinic Areas of Concentration – Cancer Clinical Trials – Computational Genomics Individualized Medicine – Health Care Costs, Utilization, Value and Delivery – Clinical Statistics
Typical Mayo Statistical Team Composition Lead MS SPA
Scientific Method Generate Hypothesis Think, reformulate hypothesis Do background research Ask Question Test with an Experiment Analyze results, draw conclusions Report Results Hypothesis is True Hypothesis is False or Partially True
Scientific Method Generate Hypothesis Think, reformulate hypothesis Do background research Ask Question Test with an Experiment Analyze results, draw conclusions Report Results Hypothesis is True Hypothesis is False or Partially True
Scientific Method Generate Hypothesis Think, reformulate hypothesis Do background research Ask Question Test with an Experiment Analyze results, draw conclusions Report Results Hypothesis is True Hypothesis is False or Partially True
Desirable Attributes of New Graduates Data management skills Programming skills Statistical skills Communication skills Problem solving skills Initiative Attention to detail Ability to work in a team environment Inquisitiveness Adaptability Understanding of biology, medicine Understanding of the “big picture” Ability to anticipate next steps Practical experience
Interview Questions for Job Candidates Computer programming Statistical and data management skills Planning, prioritization and goal setting Initiative Quality Respecting diversity Communication and listening Attention to detail Teamwork Coping Tolerance of ambiguity
Necessary Skills Identified in ASA Guidelines Data technologies – Joining data – Formatting and manipulating data – Facile with statistical software – Well-documented and reproducible analyses Statistical fundamentals – Statistical reasoning – EDA – Formal inference Computational fundamentals – Programming language(s) – Ability to think algorithmically – Ability to carry out simulation studies
Necessary Skills Identified in ASA Guidelines Data technologies – Joining data – Formatting and manipulating data – Facile with statistical software – Well-documented and reproducible analyses Statistical fundamentals – Statistical reasoning – EDA – Formal inference Computational fundamentals – Programming language(s) – Ability to think algorithmically – Ability to carry out simulation studies Suggestion: working with messy data
Necessary Skills Identified in Guidelines Mathematical foundations – Probability and theory and how they relate to statistical applications Communication – Write clearly – Speak fluently – Collaboration and teamwork – Communicate complex statistical methods to non- statisticians – Visualize results in accessible manner Interdisciplinary knowledge – Some depth in a substantive area of application
Necessary Skills Identified in Guidelines Mathematical foundations – Probability and theory and how they relate to statistical applications Communication – Write clearly – Speak fluently – Collaboration and teamwork – Communicate complex statistical methods to non- statisticians – Visualize results in accessible manner Interdisciplinary knowledge – Some depth in a substantive area of application Suggestion: emphasize problem-solving skills Suggestion: opportunities for statistical consulting
Alignment of Desirable Attributes with Skills Identified in New Guidelines
Statistical skills Programming skills Data management skills Communication skills Initiative Attention to detail Ability to work in a team environment Statistical fundamentals Computational fundamentals Data technologies Mathematical foundations Communication Interdisciplinary knowledge
Alignment of Desirable Attributes with Skills Identified in New Guidelines Statistical skills Programming skills Data management skills Communication skills Initiative Attention to detail Ability to work in a team environment Statistical fundamentals Computational fundamentals Data technologies Mathematical foundations Communication Interdisciplinary knowledge
Alignment of Desirable Attributes with Skills Identified in New Guidelines Statistical skills Programming skills Data management skills Communication skills Initiative Attention to detail Ability to work in a team environment Statistical fundamentals Computational fundamentals Data technologies Mathematical foundations Communication Interdisciplinary knowledge
Alignment of Desirable Attributes with Skills Identified in New Guidelines Statistical skills Programming skills Data management skills Communication skills Initiative Attention to detail Ability to work in a team environment Statistical fundamentals Computational fundamentals Data technologies Mathematical foundations Communication Interdisciplinary knowledge
Alignment of Desirable Attributes with Skills Identified in New Guidelines Statistical skills Programming skills Data management skills Communication skills Initiative Attention to detail Ability to work in a team environment Statistical fundamentals Computational fundamentals Data technologies Mathematical foundations Communication Interdisciplinary knowledge
Alignment of Desirable Attributes with Skills Identified in New Guidelines Statistical skills Programming skills Data management skills Communication skills Initiative Attention to detail Ability to work in a team environment Statistical fundamentals Computational fundamentals Data technologies Mathematical foundations Communication Interdisciplinary knowledge
Alignment of Desirable Attributes with Skills Identified in New Guidelines Statistical skills Programming skills Data management skills Communication skills Initiative Attention to detail Ability to work in a team environment Statistical fundamentals Computational fundamentals Data technologies Mathematical foundations Communication Interdisciplinary knowledge
Alignment of Desirable Attributes with Skills Identified in New Guidelines Inquisitiveness Adaptability Understanding of biology, medicine Understanding of the “big picture” Ability to anticipate next steps Practical experience Statistical fundamentals Computational fundamentals Data technologies Mathematical foundations Communication Interdisciplinary knowledge
Alignment of Desirable Attributes with Skills Identified in New Guidelines Inquisitiveness Adaptability Understanding of biology, medicine Understanding of the “big picture” Ability to anticipate next steps Practical experience Statistical fundamentals Computational fundamentals Data technologies Mathematical foundations Communication Interdisciplinary knowledge
Alignment of Desirable Attributes with Skills Identified in New Guidelines Inquisitiveness Adaptability Understanding of biology, medicine Understanding of the “big picture” Ability to anticipate next steps Practical experience Statistical fundamentals Computational fundamentals Data technologies Mathematical foundations Communication Interdisciplinary knowledge
Alignment of Desirable Attributes with Skills Identified in New Guidelines Inquisitiveness Adaptability Understanding of biology, medicine Understanding of the “big picture” Ability to anticipate next steps Practical experience Statistical fundamentals Computational fundamentals Data technologies Mathematical foundations Communication Interdisciplinary knowledge
Alignment of Desirable Attributes with Skills Identified in New Guidelines Inquisitiveness Adaptability Understanding of biology, medicine Understanding of the “big picture” Ability to anticipate next steps Practical experience Statistical fundamentals Computational fundamentals Data technologies Mathematical foundations Communication Interdisciplinary knowledge
Alignment of Desirable Attributes with Skills Identified in New Guidelines Inquisitiveness Adaptability Understanding of biology, medicine Understanding of the “big picture” Ability to anticipate next steps Practical experience Statistical fundamentals Computational fundamentals Data technologies Mathematical foundations Communication Interdisciplinary knowledge
Conclusions Increasing need for well-rounded applied statisticians in variety of different disciplines – Statistical, programming skills – Data management skills – Communication, problem-solving skills – Ability to work in team environment with different types of personalities. New ASA guidelines align well with these needs Will yield new graduates with desirable attributes for employers
Conclusions Encourage universities with Bachelor’s Degree statistical programs to provide opportunities for… – Real applications of statistics Statistical consulting Team projects Capstone projects – Working with real data Missing, messy – Developing problem-solving skills Statistical consulting Capstone projects – Developing communication skills
Questions?