PREPPING FOR GRAD SCHOOL
undefined
PREPPING FOR GRAD SCHOOL
Kelley M Kidwell, PhD
July 22, 2019
University of Michigan
BDSI
1
OUTLINE
About me
Degree options
Application requirements
Biostatistics at University of Michigan
Things to remember if you go to grad school
2
ABOUT ME
3
WHERE IT ALL BEGAN
4
INTRODUCTION TO MY LOVE OF MATH
Mrs. Roberson
Mrs. Gottschalk
5
MATH + SCIENCE = ENGINEERING?
No, MATH+SCIENCE = MATH
Logic, sets and What? Where did the numbers go?
Another Teacher- Professor Gorkin
6
HOMEWORK
If any teacher has had an
impact on your path, let them
know!
7
SUMMER OPPORTUNITIES
Actuary Internships
Math Camp for
Girls: Summer
Program for Women
in Mathematics, 2006
Mathematical Biology
Graduate School
8
GRADUATE SCHOOL DECISION
Applied in Fall of my senior year in college to
several graduate programs for a PhD
Research programs online
Email students currently in program
Visit open house or accepted students day
9
MY GRADUATE SCHOOL DECISION
I applied right out of undergrad
acceptances to masters programs, but only 2 directly into PhD
Visit programs
Current students
Research opportunities
Stipend
Geographic location
10
GRADUATE SCHOOL
University of Pittsburgh, PhD in Biostatistics
Enrolled: 2007
Graduated: 2012
No official masters
Decision: funding, feel of program, research opportunities, proximity
to family
Research Opportunities: teaching assistant, graduate student
researcher
11
JOB
Applied nationwide to academic and pharmaceutical jobs
Went to many interviews
Ultimately decided to come to University of Michigan in Fall of 2012
Excellent Biostat Department
Ann Arbor
Husband had a great offer in Psychology
12
DEGREE OPTIONS
13
PROGRAMS YOU MAY CONSIDER
Statistics-
theory, testing, estimation
Biostatistics-
develops and applies statistics to design and analysis
of studies in public health and biomedical research
Computer
Science-
artificial intelligence, chip design, databases and
data mining, computation theory, large scale and parallel systems,
algorithms, machine learning
Bioinformatics
(Computational Medicine)- computer science,
algorithms, databases and structures, data storage- added biology
and statistics knowledge
Data Science-
“dealing with data”, algorithms, machine learning,
large databases, visualizing data
14
GOOD DEGREES
Fortune Magazine and Payscale reported that
a doctorate in statistics leads to a career with lower stress
List of Best Graduate Degrees
PhD in Statistics is #1
Master’s in Biostatistics is #2
Master’s in Applied Math is #8
Master’s in Statistics is #9
15
DEGREES LEAD TO JOBS
According to Glassdoor (number of openings, salary and overall
satisfaction rating)
#1: Data Scientist
#3 Data Engineer
#5 Analytics Manager
#33 Professor
Forbes 2016: With the explosion of
big data
and the need to track it, employers keep on
hiring data scientists. But
qualified candidates are in short supply
. The field is so new, the
Bureau of Labor Statistics doesn’t even track it as a profession. Yet thousands of
companies, from startups that analyze credit card data in order to target marketing and
advertising campaigns, to giant corporations like Ford Motor and Price
WaterhouseCoopers, are bringing on scores of people who can take gigantic data sets
and wrestle them into usable information. As an April report from technology market
research firm Forrester put it, “
Businesses are drowning in data but starving for insights
.”
16
MULTITUDE OF CAREER OPTIONS
Wealth of opportunities
Academia
Hospitals
Research centers
Government
Pharmaceutical companies
Tech companies
Other industry
17
JOBS: WORK IN BUSINESS
Organizations focus on finding 2 sport “data athletes” that bridge
areas: combinations of computer programming, statistics, psychology,
economics, finance, etc
http://www.mckinsey.com/business-functions/marketing-and-sales/our-insights/big-data-help-wanted-badly-how-to-win-the-war-for-talent
18
SCHOOLS WITH BIOSTATISTICS PHD
University of
Michigan
Harvard
University of
Washington
University of North
Carolina
Johns Hopkins
University
University of
Pennsylvania
University of
Pittsburgh
Columbia
Emory
UC Berkeley
University of
Minnesota
University of
Wisconsin
Medical College of
Wisconsin
Vanderbilt
Iowa University
Medical University of
South Carolina
Virginia
Commonwealth
University
Tulane
Boston University
University of Texas
Health Sciences Center
University of Buffalo
University of Cincinnati
19
SCHOOLS WITH OTHER PROGRAMS
Statistics
:
https://www.usnews.com/best-graduate-schools/top-
science-schools/statistics-rankings
Data Science
:
http://datascience.community/colleges
Computer Science
:
https://www.usnews.com/best-graduate-
schools/top-science-schools/computer-science-rankings
Bioinformatics
:
https://www.iscb.org/iscb-degree-certificate-
programs
20
BIOSTATISTICIANS
Develop and apply novel statistical designs and methods
for answering scientific questions
Participate in cutting-edge biomedical research
Apply mathematical skills and logical thinking to
important problems in many areas of research
Varied and stimulating career
Clear quantitative thinkers are in high demand
21
WHAT ARE WE DOING AT UM?
Design life-saving systems to prioritize who gets organ
transplants
Unravel genetic basis of human health and disease
Design and analyze data from clinical trials for new
drugs
Build models that predict cancer recurrence
Test effectiveness of behavioral interventions for smoking
cessation and obesity
22
ADMISSION REQUIREMENTS
23
GRADUATE DEGREES
MS
MPH
PhD
Funding: not all programs offer funding for students, especially
masters programs
24
ADMISSION TO PROGRAM
Math background and grades
GPA
GREs
Recommendation letters
Statement of purpose
Course Pre-reqs
Useful courses: advanced calculus, other math and
statistics, computer science
25
GRADUATE SCHOOL APPLICATIONS
Online
Start looking early and organize
Statement of purpose
Letters of recommendation
Fees
Due date
Apply to many programs/schools if possible
Application fee
Contact administration/professors/students at programs of interest
26
CLASSES AND GRADES
Good undergraduate GPA
More important for related courses to be high than overall high
If you have low grades in statistics, mathematics, or computer science
courses, you may want to explain circumstances in your cover letter
Take mathematics and statistics courses
Take a few related graduate courses if available
Courses related to your field and related programs are more
important than many extra-curriculars
27
GRE
General GRE required for most programs, occasionally subject
specific GRE also required
Use of these is complex and varies across programs
e.g.: UNC: average incoming students 72
nd
%ile verbal and 89
th
%ile quantitative
Aim as high as possible in all areas: Quantitative, Verbal and
Writing
Study/prepare
Take more than once if needed
Schedule with enough time to take again
28
LETTERS OF RECOMMENDATION
Usually 3 letters required
Choose wisely
More than you attended their class and did well
Visible and senior people in field
At least 2 in related field
Meet with a handful of professors and discuss the potential of
graduate school with them
Do you think I’m well suited for grad school?
Do you think I’ll be admitted and successful to these programs?
Provide these professors with your personal statement and transcript
29
STATEMENT OF PURPOSE
a concise, well-written statement about your academic and research
background, your career goals, and how this graduate program will
help you meet your career and educational objectives
Often students write about how they fell in love with math/stat
How are you unique?
Effective to write in a concrete way about what you want to be
doing in 10 years- are your goals aligned with the program?
Reflect on what is most pertinent to how you developed these goals- research
experience, coursework, internships
30
STATEMENT OF PURPOSE
Avoid generic sentences: I love statistics, I am
interested in research
Every sentence contain specifics about you
If multiple tracks in a program, delineate your
interests
Why this particular school/program?
Have many people read and give feedback
31
DURING AND AFTER APPLICATION
Research online
Email faculty and students currently in program
Visit open house or accepted students day
Ask about funding for this
32
BIOSTATISTICS PROGRAM
University of Michigan
33
DEGREES: MASTERS: 2 YEARS
MS: Masters in Science
2 years, 48 credits
22 credits (6 courses) core biostat courses
12 elective credits in biostat or stat
Open electives
Epidemiology requirement
1 credit Public Health course
MS Health Data Science Concentration:
additional core courses
MPH: Masters in Public Health
Similar to MS
Breadth and integration of knowledge- 3 PH related courses at least 2 credits each
(one in epi and other from other depts., not biostat, stat or math)
Internship- 8 weeks during summer after first year
34
MASTERS REQUIREMENTS
https://sph.umich.edu/biostat/programs/masters.html
Bachelor’s degree
General GRE exam within last 5 years
Competency in English if not native language (TOEFL or MELAB)
3 semesters calculus, matrix or linear algebra, intro statistics or
biostat course
Less prep may be conditionally admitted
35
MASTERS COURSEWORK
Probability theory, statistical inference
Applied sequence
linear regression
generalized linear models
longitudinal analysis
Capstone course: Analysis of biostatistical investigations
36
DEGREES: PHD: 5-6 YEARS
https://sph.umich.edu/biostat/programs/phd.html
With Masters
13-19 additional credit hours of core biostatistics courses (6 courses)
15 credit hours electives in biostat/stat
Epi requirement
1 credit Public Health requirement
7-10 credits: Open elective requirement
Without Masters
34 credit hours of core biostat course (12 courses)
Elective, Epi, PH, and open electives same as above
Qualifying Exams: ~after year 2
6 hour theory exam
6 hour applied exam
37
PHD REQUIREMENTS
https://sph.umich.edu/biostat/programs/phd.html
Previous masters degree or strong candidates with bachelor’s
degree
General GRE exam within last 5 years
Competency in English if not native language (TOEFL or MELAB)
3 semesters calculus, matrix or linear algebra, intro statistics or
biostat course
Less prep may be conditionally admitted
38
PHD COURSEWORK
Same as masters
Advanced inference
Stochastic Processes
Other courses
Survival analysis
Clinical trials
Time series
High throughput analysis
Bayesian inference
Nonparametric statistics
Categorical data
Population genetics
Spatial statistics
Missing Data
Special topics courses
39
PHD DISSERTATION
Work with one or more faculty mentors
Creative and significant original contribution to the field of
biostatistics
Development and evaluation of biostat methodology
3 loosely related papers to be of publishable quality or one in-
depth look at a topic
Dissertation committee of faculty
Propose dissertation with a presentation within 2 years of becoming
a PhD candidate
Defend dissertation with a presentation open to the public
40
THINGS TO REMEMBER IN
GRAD SCHOOL
41
CHOOSING AN ADVISOR
Challenging, intelligent, passionate, helpful
Worked in novel and interesting area
42
GRADUATE SCHOOL
Work ethic
Work hard, engage with faculty & other students
Take advantage of opportunities
Go to conferences
Have fun, seek balance
43
GRADUATE SCHOOL- OTHER INTERESTS
44
IN REVIEW
Start preparing now if you are interested in
graduate school- do your research
Remember you’ve chosen the path, so enjoy it
and find balance
Seek out mentors and let them influence you
Thank your mentors
Exciting, marketable field
45
THANK YOU
kidwell@umich.edu
46
MY RESEARCH
47
MOTIVATION
Setting
:
Treatment of Chronic Diseases
Problem
:
Discrepancy between how treatment is practiced and
how treatment is studied
48
HOW TREATMENT IS PRACTICED
49
HOW TREATMENT IS PRACTICED
50
HOW TREATMENT IS STUDIED
Aflibercept versus placebo in combination with docetaxel and prednisone for treatment of men with metastatic castration-resistant prostate cancer (VENICE): a phase
3, double-blind randomised trial. Lancet Oncology 2013
51
HOW TREATMENT IS STUDIED
52
ARE YOU STILL AWAKE?
What are some of the discrepancies between how we practice and
how we treat chronic diseases?
What are some of the possible consequences of the discrepancy?
53
REPERCUSSIONS: TRIAL SUCCESS RATE
54
REPERCUSSIONS: MISSING THE BOAT
•
Compare treatments A vs. B for first-line treatment
–
Response Rates
•
A: 60%
•
B: 50%
–
Treatment A wins
•
Test efficacy of second-line treatment C for non-responders
–
Response Rates
•
A followed by C: 10%
•
B followed by C: 40%
–
Treatment B followed by C wins
•
Overall sequence
–
A,C: 64% (60%+40%*10%)
–
B,C: 70% (50%+50%*40%)
A
B
C
55
DYNAMIC TREATMENT REGIMEN
•
a.k.a. adaptive treatment strategy, adaptive intervention,
stepped care, treatment policies
•
Sequence of
individually tailored decision rules
that
specify whether, how and/or when to alter the intensity,
type, dose or delivery of treatment at critical decision
points in the course of care
•
Guide/Formula for treatment
•
Goal: operationalize sequential decision making with the aim of improving
clinical practice
56
DTR EXAMPLES
•
Leukemia:
•
First receive standard chemotherapy.
•
If the patient responds to chemotherapy and achieves remission, then receive
maintenance treatment cytarabine;
•
if remission is not achieved, there is no further treatment.
•
Prostate Cancer:
•
First receive combination chemotherapy paclitaxel + estramustine + etoposide (TEC).
•
If successful (a decrease of 40% or more in PSA from baseline at diagnosis, with no
evidence of disease progression at any site) at 8 weeks, then continue TEC;
•
otherwise switch to cyclophosphamide + vincristine + dexamethasone (CVD).
57
DTR BENEFITS
•
Patients
vary in their response
to treatment
•
Effectiveness of an intervention may
change over time
•
Presence of, or evolving,
comorbidities
•
Relapse
may be common
•
High cost of intensive interventions, possible burden and side effects
motivate interventions in which
intensity of treatment can be reduced
when possible
•
Adherence
issues
58
GETTING SMART
•
Sequential Multiple Assignment Randomized Trial (SMART)
•
A type of
multi-stage randomized design
•
Trial participants are randomized to a set of treatment options at
critical decision points over the course of treatment
•
All individuals
participate in all stages of the trial
•
Subsequent randomization is based on information leading up to that
point (tailor treatment)
•
Goal:
develop effective dynamic treatment regimens
59
SMART BENEFITS
•
Investigates Questions of
•
What treatment?
•
Which
order
?
•
When/for whom to change treatment or dose?
•
When/for whom to combine therapies?
•
How/when to measure
early response
to
tailor
subsequent
treatment?
•
Takes advantage of intra- and inter-patient
heterogeneity
60
SMART: DEPRESSION
61
DTRS WITHIN SMART
If adolescent responds
If adolescent does not respond
If adolescent responds
If adolescent does not respond
1
2
62
DTRS WITHIN SMART
If adolescent responds
If adolescent does not respond
If adolescent responds
If adolescent does not respond
3
4
63
SMART: DEPRESSION
64
SMART: DEPRESSION
65
SMART: CANCER
66
SMART: CANCER & DEPRESSION
67
BIOSTATISTICIANS AT THE TABLE
•
Design
•
Sample size/power
•
Analysis
•
Methods to estimate effects and test hypotheses
•
Dissemination
•
What do the results mean?
•
How do we get researchers interested in this design
68
DESIGN: SAMPLE SIZE
69
ANALYSIS: COMPARE DTRS
Weighted Log-Rank Test to Compare Survival
of >2 DTRs
70
ANALYSIS: ESTIMATE DTR OUTCOMES
Median Residual Life Function: the median
of
the remaining lifetime at a specific time point
71
DESIGN AND ANALYSIS: RARE DISEASES
•
Received a PCORI (Patient Centered Outcomes Research Initiative)
Contract
•
August 2016-July 2019
•
Applying SMART design to study effective treatments for rare diseases
•
Methods do not exist to analyze data from this design with small samples
(<100 patients)
•
Advisory Board: physicians, patients, family members, and a statistician
72
DESIGN AND ANALYSIS: RARE DISEASES
73
In this narrative, Kelly M. Kidwell, PhD, shares her journey from undergraduate to graduate school, focusing on her decision-making process, experiences, and opportunities in the field of biostatistics at the University of Michigan and University of Pittsburgh. She discusses her path from mathematics and science love to pursuing a PhD, offering insight into application requirements, research opportunities, funding choices, and more along the way. Through anecdotes and reflections, she provides valuable guidance to those considering or navigating graduate school.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
E N D
Presentation Transcript
Kelley M Kidwell, PhD PREPPING FOR GRAD SCHOOL July 22, 2019 University of Michigan BDSI 1
OUTLINE About me Degree options Application requirements Biostatistics at University of Michigan Things to remember if you go to grad school 2
ABOUT ME 3
INTRODUCTION TO MY LOVE OF MATH Mrs. Roberson Mrs. Gottschalk 5
MATH + SCIENCE = ENGINEERING? No, MATH+SCIENCE = MATH Logic, sets and What? Where did the numbers go? Another Teacher- Professor Gorkin 6
HOMEWORK If any teacher has had an impact on your path, let them know! 7
SUMMER OPPORTUNITIES Actuary Internships Math Camp for Girls: Summer Program for Women in Mathematics, 2006 Mathematical Biology Graduate School 8
GRADUATE SCHOOL DECISION Applied in Fall of my senior year in college to several graduate programs for a PhD Research programs online Email students currently in program Visit open house or accepted students day 9
MY GRADUATE SCHOOL DECISION I applied right out of undergrad acceptances to masters programs, but only 2 directly into PhD Visit programs Current students Research opportunities Stipend Geographic location 10
GRADUATE SCHOOL University of Pittsburgh, PhD in Biostatistics Enrolled: 2007 Graduated: 2012 No official masters Decision: funding, feel of program, research opportunities, proximity to family Research Opportunities: teaching assistant, graduate student researcher 11
JOB Applied nationwide to academic and pharmaceutical jobs Went to many interviews Ultimately decided to come to University of Michigan in Fall of 2012 Excellent Biostat Department Ann Arbor Husband had a great offer in Psychology 12
PROGRAMS YOU MAY CONSIDER Statistics- theory, testing, estimation Biostatistics- develops and applies statistics to design and analysis of studies in public health and biomedical research ComputerScience- artificial intelligence, chip design, databases and data mining, computation theory, large scale and parallel systems, algorithms, machine learning Bioinformatics (Computational Medicine)- computer science, algorithms, databases and structures, data storage- added biology and statistics knowledge Data Science- dealing with data , algorithms, machine learning, large databases, visualizing data 14
GOOD DEGREES Fortune Magazine and Payscale reported that a doctorate in statistics leads to a career with lower stress List of Best Graduate Degrees PhD in Statistics is #1 Master s in Biostatistics is #2 Master s in Applied Math is #8 Master s in Statistics is #9 15
DEGREES LEAD TO JOBS According to Glassdoor (number of openings, salary and overall satisfaction rating) #1: Data Scientist #3 Data Engineer #5 Analytics Manager #33 Professor Forbes 2016: With the explosion of big data and the need to track it, employers keep on hiring data scientists. But qualified candidates are in short supply. The field is so new, the Bureau of Labor Statistics doesn t even track it as a profession. Yet thousands of companies, from startups that analyze credit card data in order to target marketing and advertising campaigns, to giant corporations like Ford Motor and Price WaterhouseCoopers, are bringing on scores of people who can take gigantic data sets and wrestle them into usable information. As an April report from technology market research firm Forrester put it, Businesses are drowning in data but starving for insights. 16
MULTITUDE OF CAREER OPTIONS Wealth of opportunities Academia Hospitals Research centers Government Pharmaceutical companies Tech companies Other industry 17
JOBS: WORK IN BUSINESS Organizations focus on finding 2 sport data athletes that bridge areas: combinations of computer programming, statistics, psychology, economics, finance, etc 18 http://www.mckinsey.com/business-functions/marketing-and-sales/our-insights/big-data-help-wanted-badly-how-to-win-the-war-for-talent
SCHOOLS WITH BIOSTATISTICS PHD University of Michigan Columbia Medical University of South Carolina Emory Harvard Virginia Commonwealth University UC Berkeley University of Washington University of Minnesota Tulane University of North Carolina University of Wisconsin Boston University Johns Hopkins University University of Texas Health Sciences Center Medical College of Wisconsin University of Pennsylvania University of Buffalo Vanderbilt University of Cincinnati Iowa University University of Pittsburgh 19
SCHOOLS WITH OTHER PROGRAMS Statistics: https://www.usnews.com/best-graduate-schools/top- science-schools/statistics-rankings Data Science: http://datascience.community/colleges Computer Science: https://www.usnews.com/best-graduate- schools/top-science-schools/computer-science-rankings Bioinformatics: https://www.iscb.org/iscb-degree-certificate- programs 20
BIOSTATISTICIANS Develop and apply novel statistical designs and methods for answering scientific questions Participate in cutting-edge biomedical research Apply mathematical skills and logical thinking to important problems in many areas of research Varied and stimulating career Clear quantitative thinkers are in high demand 21
WHAT ARE WE DOING AT UM? Design life-saving systems to prioritize who gets organ transplants Unravel genetic basis of human health and disease Design and analyze data from clinical trials for new drugs Build models that predict cancer recurrence Test effectiveness of behavioral interventions for smoking cessation and obesity 22
GRADUATE DEGREES MS MPH PhD Funding: not all programs offer funding for students, especially masters programs 24
ADMISSION TO PROGRAM Math background and grades GPA GREs Recommendation letters Statement of purpose Course Pre-reqs Useful courses: advanced calculus, other math and statistics, computer science 25
GRADUATE SCHOOL APPLICATIONS Online Start looking early and organize Statement of purpose Letters of recommendation Fees Due date Apply to many programs/schools if possible Application fee Contact administration/professors/students at programs of interest 26
CLASSES AND GRADES Good undergraduate GPA More important for related courses to be high than overall high If you have low grades in statistics, mathematics, or computer science courses, you may want to explain circumstances in your cover letter Take mathematics and statistics courses Take a few related graduate courses if available Courses related to your field and related programs are more important than many extra-curriculars 27
GRE General GRE required for most programs, occasionally subject specific GRE also required Use of these is complex and varies across programs e.g.: UNC: average incoming students 72nd %ile verbal and 89th %ile quantitative Aim as high as possible in all areas: Quantitative, Verbal and Writing Study/prepare Take more than once if needed Schedule with enough time to take again 28
LETTERS OF RECOMMENDATION Usually 3 letters required Choose wisely More than you attended their class and did well Visible and senior people in field At least 2 in related field Meet with a handful of professors and discuss the potential of graduate school with them Do you think I m well suited for grad school? Do you think I ll be admitted and successful to these programs? Provide these professors with your personal statement and transcript 29
STATEMENT OF PURPOSE a concise, well-written statement about your academic and research background, your career goals, and how this graduate program will help you meet your career and educational objectives Often students write about how they fell in love with math/stat How are you unique? Effective to write in a concrete way about what you want to be doing in 10 years- are your goals aligned with the program? Reflect on what is most pertinent to how you developed these goals- research experience, coursework, internships 30
STATEMENT OF PURPOSE Avoid generic sentences: I love statistics, I am interested in research Every sentence contain specifics about you If multiple tracks in a program, delineate your interests Why this particular school/program? Have many people read and give feedback 31
DURING AND AFTER APPLICATION Research online Email faculty and students currently in program Visit open house or accepted students day Ask about funding for this 32
BIOSTATISTICS PROGRAM University of Michigan 33
DEGREES: MASTERS: 2 YEARS MS: Masters in Science 2 years, 48 credits 22 credits (6 courses) core biostat courses 12 elective credits in biostat or stat Open electives Epidemiology requirement 1 credit Public Health course MS Health Data Science Concentration: additional core courses MPH: Masters in Public Health Similar to MS Breadth and integration of knowledge- 3 PH related courses at least 2 credits each (one in epi and other from other depts., not biostat, stat or math) Internship- 8 weeks during summer after first year 34
MASTERS REQUIREMENTS https://sph.umich.edu/biostat/programs/masters.html Bachelor s degree General GRE exam within last 5 years Competency in English if not native language (TOEFL or MELAB) 3 semesters calculus, matrix or linear algebra, intro statistics or biostat course Less prep may be conditionally admitted 35
MASTERS COURSEWORK Probability theory, statistical inference Applied sequence linear regression generalized linear models longitudinal analysis Capstone course: Analysis of biostatistical investigations 36
DEGREES: PHD: 5-6 YEARS https://sph.umich.edu/biostat/programs/phd.html With Masters 13-19 additional credit hours of core biostatistics courses (6 courses) 15 credit hours electives in biostat/stat Epi requirement 1 credit Public Health requirement 7-10 credits: Open elective requirement Without Masters 34 credit hours of core biostat course (12 courses) Elective, Epi, PH, and open electives same as above Qualifying Exams: ~after year 2 6 hour theory exam 6 hour applied exam 37
PHD REQUIREMENTS https://sph.umich.edu/biostat/programs/phd.html Previous masters degree or strong candidates with bachelor s degree General GRE exam within last 5 years Competency in English if not native language (TOEFL or MELAB) 3 semesters calculus, matrix or linear algebra, intro statistics or biostat course Less prep may be conditionally admitted 38
PHD COURSEWORK Same as masters Advanced inference Stochastic Processes Other courses Survival analysis Clinical trials Time series High throughput analysis Bayesian inference Nonparametric statistics Categorical data Population genetics Spatial statistics Missing Data Special topics courses 39
PHD DISSERTATION Work with one or more faculty mentors Creative and significant original contribution to the field of biostatistics Development and evaluation of biostat methodology 3 loosely related papers to be of publishable quality or one in- depth look at a topic Dissertation committee of faculty Propose dissertation with a presentation within 2 years of becoming a PhD candidate Defend dissertation with a presentation open to the public 40
THINGS TO REMEMBER IN GRAD SCHOOL 41
CHOOSING AN ADVISOR Challenging, intelligent, passionate, helpful Worked in novel and interesting area 42
GRADUATE SCHOOL Work ethic Work hard, engage with faculty & other students Take advantage of opportunities Go to conferences Have fun, seek balance 43
IN REVIEW Start preparing now if you are interested in graduate school- do your research Remember you ve chosen the path, so enjoy it and find balance Seek out mentors and let them influence you Thank your mentors Exciting, marketable field 45
THANK YOU kidwell@umich.edu 46
MY RESEARCH 47
MOTIVATION Setting: Treatment of Chronic Diseases Problem: Discrepancy between how treatment is practiced and how treatment is studied 48
