Biostatistics and Methodology Core

Description

The goal of the Biostatistics and Methodology Core is to provide members of the UConn community with the expertise and experience necessary to conduct innovative and statistically rigorous research, and to enable them to compete very successfully for research grants in the health sciences. Members of the UConn community will be able to use the Core to connect with a range of statistics experts, and to establish long-term collaborations for innovative research into health and health behavior. To this end, the Core facilitates statistical support by experienced UConn faculty members, which is described in detail below. A list of the experts associated with the Core can be found in the experts tab above.

Leadership

The Biostatistics and Methodology Core is directed by Tania B. Huedo-Medina (PhD, Allied Health Sciences). Dr. Huedo-Medina has extensive experience collaborating with investigators from a wide range of health-related disciplines, and conducting cutting-edge statistical research. She is assisted in the administration of the Core by Eva Yujia Li (PhD Candidate, Measurement, Evaluation & Assessment; MS Candidate, Statistics).

If you have any questions or would like more information about the Core, please email biostats@chip.uconn.edu.

Office Hours

The Biostatistics and Methodology Core offers office hours during the Fall and Spring semesters. The Core Director and/or Graduate Assistant will be available during these hours to answer questions about applying for statistical support and to provide help finding statistical experts for research projects. The Core office is located in Room 22 of the J. Ray Ryan Building. The office hours for the Fall 2016 semester are Monday and Wednesday, from 1:00-5:00pm, and Thursday, from 3:00-5:00pm, unless otherwise posted at the Core office.

Services

The Biostatistics and Methodology Core provides three types of services: pre-award services, short-term statisitcal support, and long-term statistical support. When planning your request, please note that it may take at least two weeks for the Core to identify an appropriate statistical expert and arrange the initial consultation.

Pre-award services will be provided free of charge to any investigator who is both an InCHIP Affiliate and who will be submitting their external grant proposal through InCHIP. It is expected that the statistical expert that contributes to the grant proposal will be included in the proposed grant budget for their percent effort as a long-term collaborator for the project. The types of services included in pre-award services are listed in the Services tab above.

Short-term statistical support assists only with a specific part of a project, for a limited period of time. This short-term support will be managed by the Core Director, who will ensure that there are clear expectations about the kinds of support that will be provided. In general, it is expected that short-term support will only require 10 hours or less of support from a statistical expert. These short-term consultations will be managed by the Core Director, who will ensure that needs of the investigators can be met by the expert. Additionally, please note that, in general, it will be expected that the expert will be included as a co-author on any resulting publication.

Long-term statistical support provides expertise over the duration of a research project. For this kind of support, the Core will primarily act to connect an appropriate statistical expert with an investigator, and will not manage any of the actual services provided by the expert. It is expected that the expert will be added to the grant budget for their percent effort and/or be listed as a co-author on the resulting paper. Under this arrangement, the Core will not manage or guarantee any of the work done by the expert, but will instead help the investigator and expert establish their collaborative relationship. The enforcement of any collaboration agreement will be the sole responsibility of the investigator and expert.

A more complete list of the services offered by the Core can be found in the “Services” tab above. To request any type of service, please fill out the services request form:

Request Statistical Support

Research Assistant Searches

The Biostatistics and Methodology Core can help investigators find qualified graduate students with statistical expertise to serve as research assistants on health-related projects. To request help connecting with these graduate students, please fill out the research assistant search request form:

Request Research Assistant Search

Harel

Ofer Harel, PhD (Statistics, Pennsylvania State University)
Professor, Statistics
College of Liberal Arts and Sciences
ofer.harel@uconn.edu

Statistical/Methodological Expertise

  • Incomplete data
  • Diagnostic accuracy
  • Longitudinal analysis
  • Causal Inference
  • Verification Bias
  • Bayesian methods
  • Sampling techniques

Content Areas of Interest

  • HIV prevention
  • Cancer
  • Alcohol and drug abuse prevention
  • Diabetics
  • Aging
  • Dementia Care (Alzheimer)

Hwang

Jungbin Hwang, PhD (Economics, University of California, San Diego)
Assistant Professor, Economics
College of Liberal Arts and Sciences
jungbin.hwang@uconn.edu

Statistical/Methodological Expertise

  • Econometrics Theory
  • Financial Econometrics
  • Bayesian Econometrics
  • Econometrics of Big Data

Content Areas of Interest

  • Economic Demography and Health
  • Spatial analysis of Economic Health Data

Lachos Davila

Victor Hugo Lachos Davila, PhD (Statistics, São Paulo State University, Brazil)
Visiting Professor, Statistics
College of Liberal Arts and Sciences
hlachos@uconn.edu

Statistical/Methodological Expertise

  • Linear and Non Linear Mixed-Effects Models
  • Generalized Linear Mixed Models- Zero inflated models
  • Skew Elliptical Distribution and its Application
  • Time Series
  • Multivariate Analysis
  • Semiparametrics models
  • Censored Regression Models

Content Areas of Interest

  • Virus Data Modeling (e.g. HIV)

Laubenbacher

Reinhard Laubenbacher, PhD (Mathematics, Northwestern University)
Professor, Cell Biology, UConn Health
Professor, Computational Biology, Jackson Laboratory for Genomic Medicine
Director, Center for Quantitative Medicine
laubenbacher@uchc.edu

Statistical/Methodological Expertise

  • Modeling and simulation of biological networks
  • Applied discrete mathematics
  • Symbolic computation
  • Computational algebra
  • Algebraic geometry
  • Mathematical foundation of computer simulation

Content Areas of Interest

  • Computational biology
  • Systems biology
  • Cancer systems biology

Loken

Eric Loken, PhD (Developmental Psychology, Harvard University)
Associate Professor, Measurement, Evaluation, and Assessment
Neag School of Education
eric.loken@uconn.edu

Statistical/Methodological Expertise

  • Measurement
  • Mixture models
  • Item response theory
  • Mixed effects models
  • Factor models
  • Bayesian methods
  • Replicable science

Content Areas of Interest

  • Nutrition
  • Obesity
  • Instrument Development
  • Educational Assessment

Prakash

Nishith Prakash, PhD (Economics, University of Houston)
Assistant Professor, Economics
College of Liberal Arts and Sciences
nishith.prakash@uconn.edu

Statistical/Methodological Expertise

  • Causal Inference
  • Difference in Difference
  • Regression Discontinuity Design
  • Field Experiments

Content Areas of Interest

  • Health Policy in Developing Countries
  • Education Policies
  • Behavioral Economics

Rhoads

Christopher Rhoads, PhD (Statistics, Northwestern University)
Assistant Professor, Measurement, Evaluation, and Assessment
Neag School of Education
christopher.rhoads@uconn.edu

Statistical/Methodological Expertise

  • Experimental design in multi-level settings
  • Quasi-experimental designs (e.g. regression-discontinuity, instrumental variables, comparative interrupted time series and observational studies)
  • Matching methods for causal inference (e.g. propensity score matching)
  • Mediation models
  • Mixed-effects models
  • Power analysis in multi-level settings
  • Implementation fidelity

Content Areas of Interest

  • Mental and behavioral health (depression, bi-polar, anxiety, etc.)
  • Sensory integration disorder
  • Asthma and related illnesses
  • Education

The Biostatistics and Methodology Core can provides a range of services, including:

  • Pre-award Services: The Core can support the development of statistically rigorous external grant proposals. These pre-award services will be provided free of charge to InCHIP Affiliates who are submitting the grant proposal through InCHIP. Statistical experts will meet with the investigators to determine the goals of the proposal, and provide recommendations for the design of the study. This could include recommendations for survey design, the development of appropriate data collection and statistical analysis techniques, and power analyses to ensure adequate sample sizes. Additionally, the experts will contribute written sections directly to the grant proposal as a co-investigator. The statistical experts will also be included in the proposed grant budget for their percent effort as a long-term collaborator for the project.
  • Research Design and Data Collection Support: The Core will provide support for certain aspects of the execution of a funded research project. Statistical experts will initially meet with the investigators to determine the level of statistical consulting required, and will then develop a plan to best support the project. This plan could include assisting with study or survey design, the development of appropriate data collection and coding techniques, appropriate data analytic techniques, and ensuring that the study will produce useful and relevant data.
  • Data Analysis and Article Writing: The Core will conduct and provide support for modern data analytic techniques and the use of statistical software packages. Statistical experts will first meet with the investigators to discuss the goals for the analysis, and determine the types of support the Core can offer and the cost that may be involved. Following any statistical analysis, the experts will provide a written report of their analysis, including an explanation of the techniques that were used. Additionally, the experts may contribute statistical analysis sections directly to publications in peer-reviewed journals as a co-author.
  • Training and Mentoring: Experts associated with the Core can also provide training and mentoring in analytic techniques, study design, and the use of statistical software packages, as requested by the investigators. This training will provide the opportunity for the investigators to develop experience in techniques and methodologies not commonly taught in their disciplines, allowing them to create stronger research programs and more competitive funding applications.

Resources for Students

Below are some courses offered at UConn that might be useful for students interested in learning about methodologies and statistical techniques for health-related research. Please check with the department offering the course for up-to-date information about software, schedule, and prerequisites.

Department of Statistics

Measurement, Evaluation, and Assessment Program, Department of Educational Psychology

Department of Psychological Sciences

Below are some websites and online courses that might be helpful for students and researchers looking for an introduction to statistical theory and analysis. Please check with the websites offering the courses for up-to-date information about fees, topics covered, and other information.

EdX: Statistics and Data Science Courses

  • Courses are Free
  • Certificate is Available for a Fee
  • Some courses are self-paced, while others have specific start and end dates

Courses in R

Introduction to R for Data Science
Learn the R statistical programming language, the lingua franca of data science in this hands-on course.

Explore Statistics with R
Learn basic statistics in a practical, experimental way, through statistical programming with R, using examples from the health sciences.

Programming with R for Data Science
Learn the fundamentals of programming with R, from reading and writing data to customizing visualizations and performing predictive analysis.

Statistics and R
An introduction to basic statistical concepts and R programming skills necessary for analyzing data in the life sciences.

Statistical Theory

Probability: Basic Concepts & Discrete Random Variables
Learn fundamental concepts of mathematical probability to prepare for a career in the growing field of information and data science.

Probability: Distribution Models & Continuous Random Variables
Learn about probability distribution models, including normal distribution, and continuous random variables to prepare for a career in information and data science.

Foundations of Data Analysis – Part 2: Inferential Statistics
Use R to learn the fundamental statistical topic of basic inferential statistics.

Applied Statistics & Biostatistics

Introduction to Statistics: Descriptive Statistics
An introduction to descriptive statistics, emphasizing critical thinking and clear communication.

High-Dimensional Data Analysis
A focus on several techniques that are widely used in the analysis of high-dimensional data. Factor analysis, clustering, heat maps, etc.

Introduction to Applied Biostatistics: Statistics for Medical Research
Learn data analysis for medical research with practical hands-on examples using R Commander.

Coursera: Data Science Courses

  • Enrollment requires a fee
  • Certificate is available after course completion
  • Some courses are self-paced, while others have specific start and end dates

Course Sequenences in Statistical Specializations

Statistics with R
Learn to analyze and visualize data in R and create reproducible data analysis reports, demonstrate a conceptual understanding of the unified nature of statistical inference, perform frequentist and Bayesian statistical inference and modeling to understand natural phenomena and make data-based decisions, communicate statistical results correctly, effectively, and in context without relying on statistical jargon, critique data-based claims and evaluated data-based decisions, and wrangle and visualize data with R packages for data analysis. The student will produce a portfolio of data analysis projects from the Specialization that demonstrates mastery of statistical data analysis from exploratory analysis to inference to modeling, suitable for applying for statistical analysis or data scientist positions.

Methods and Statistics in Social Sciences
Covers research methods, design and statistical analysis for social science research questions. In the final Capstone Project, the student will apply the skills learned by developing their own research question, gathering data, and analyzing and reporting on the results using statistical methods.

Data Science
Covers the concepts and tools needed throughout the entire data science pipeline, from asking the right kinds of questions to making inferences and publishing results. In the final Capstone Project, the student will apply the skills learned by building a data product using real-world data. At completion, students will have a portfolio demonstrating their mastery of the material.

Machine Learning
Provides a case-based introduction to the exciting, high-demand field of machine learning. Learn to analyze large and complex datasets, build applications that can make predictions from data, and create systems that adapt and improve over time. In the final Capstone Project, the student will apply their skills to solve an original, real-world problem through implementation of machine learning algorithms.

Probabilistic Graphical Models
Probabilistic graphical models (PGMs) are a rich framework for encoding probability distributions over complex domains: joint (multivariate) distributions over large numbers of random variables that interact with each other. These representations sit at the intersection of statistics and computer science, relying on concepts from probability theory, graph algorithms, machine learning, and more. They are the basis for the state-of-the-art methods in a wide variety of applications, such as medical diagnosis, image understanding, speech recognition, natural language processing, and many, many more. They are also a foundational tool in formulating many machine learning problems.

Khan Academy: Statistics & Probability Topics

  • Courses are Free
  • All Courses are Self-paced

Ben Lambert: Tutoring Videos

  • Video courses include the following topics:
    • A full undergraduate course in econometrics
    • A graduate course in econometrics
    • A course in Asymptotic Behavior of Estimators
    • A short course on Factor Analysis and SEM
  • YouTube Channel: https://www.youtube.com/user/SpartacanUsuals/playlists

The Biostatistics and Methodology Core maintains a list of students who are interested in parterning with faculty as a research assistant on health-related projects. If you are a graduate student with statistical expertise, and would like to be considered as a potential research assistant for investigators who contact the Core, please fill out the application form:

Submit Information for Research Assistant List