Presenting Sponsor:
Arkansas Blue Cross Blue Shield
Sponsors:
UALR William H. Bowen School of Law
University of Arkansas for Medical Sciences
$20 pre-registered/$30 at the door
Register online: http://ualr.edu/law/
October 4, 2016
12:00p.m. – 1:00p.m.
COPH 2280
Amanda L. Golbeck, Ph.D.
Professor, UAMS Department of Biostatistics
Abstract
The American academic women’s movement began in the late 1960’s. It was noted early on that there were women faculty with equivalent training, experience, responsibilities, and productivity to men who were being paid less. Statisticians and others began to document and estimate the extent of these differences. In 1970, a study reported results of simple additive linear models of salary; this study included sex among the explanatory variables and presented correlations within a statistical testing framework. In 1972, a second study used these same methods with data on full time faculty members that came from a large national faculty survey. In 1972 and 1973, several more studies used these same data but improved the statistical methods in a number of ways that will be discussed in this talk. These improved studies promoted use of the statistical methods for purposes of advocacy: Build a regression model for male salaries, use it to predict women’s salaries, and advocate for individual increases when actual salaries for women were lower than predicted. The American Association of University Professors became involved and catalyzed many local studies around the country that used regression models to advocate for salary increases. These studies uncovered a number of problems with data; there have been many misuses of linear models in affirmative action; and there have been criticisms of using individual rather than statistical remedies for discrimination indicated by linear models.
The Office of Student Affairs is pleased to announce the “What Is” series. This hour long, interactive series will allow departments to discuss with students the significance and opportunities available in a specialty area of public health through discussion, short film, and presentation.
We will kick-off the series with the segment:
“What is Environmental and Occupational Health?”
In collaboration with the Environmental and Occupational Health Department, join Dr. Rosalind Penney, faculty in the EOH department as she leads the discussion.
Wednesday, September 28, 2016
College of Public Health Building, room 3202
12:00 noon – 1:00pm
The first 25 attendees will be treated to lunch
May 26, 2016 at
3:00p.m. – 4:00p.m.
COPH 2280
Speaker information:
Hui Zhang, Ph.D.
Assistant Member, Department of Biostatistics – St. Jude Children’s Research Hospital
Memphis, TN
Abstract:
Count data plays an important role in biomedical and clinical research, especially nowadays with the rapid progress in next generation sequencing. However, using routine statistical model to analyze counts, such as Poisson model, often results in biased or even misleading conclusions. Primary challenges when applying Poisson model to count data include overdispersion and zero-inflation, which are commonly encountered in practice. In addition, the repeated measures and incomplete observations in modern clinical trials add to complexity. This talk will review these challenges in count data analysis and recent methodology progress made by the speaker.
Abstract:
Unmeasured confounding is a common concern when researchers attempt to estimate a treatment effect using observational data or randomized studies with non-perfect compliance. To address this concern, instrumental variable (IV) methods, such as two-stage predictor substitution (2SPS) and two-stage residual inclusion (2SRI), have been widely adopted. In many clinical studies of binary and survival outcomes, 2SRI has been accepted as the method of choice over 2SPS but a compelling theoretical rationale has not been postulated. We propose a novel two stage modeling framework to understanding the bias and consistency in estimating the conditional treatment effect for 2SPS and 2SRI when the outcome is binary, count or time to event. Under this framework, we demonstrate that the bias in 2SRI estimators can be reframed to mirror the problem of omitted variables in non-linear models and that there is a direct relationship with the collapsibility of effect measures. We demonstrate that only if the influence of the unmeasured covariates on the treatment is proportional to their effect on the outcome, then 2SRI estimates are generally unbiased for logit and Cox models. We also propose a novel dissimilarity metric to quantify the difference in these effects and demonstrate that with increasing dissimilarity between the effects of the unmeasured covariates on the treatment versus outcome, the bias of 2SRI increases in magnitude.
Tuesday, May 3rd, 2016
Noon – 1:00pm
The Department of Epidemiology Presents:
Ping-Ching Hsu, Ph.D.,
Post-Doctoral Researcher
The Ohio State University Comprehensive Cancer Center
“Untargeted Metabolomics Reveals Smokers’ Characteristic Profiles”
You are welcome to bring your lunch!
Thursday, March 10th, 2016
11:00 am – 12:00 pm
COPH Room 1202
“A Systematic Strategy to Prevent Future Outbreaks: Combatting Foodborne Pathogens’ Survival Strategies in Leafy Greens”
Faculty Candidate
ORISE Research Microbiologist
Food Safety Group
Division of Microbiology
National Center for Toxicology Research
U.S. Food and Drug Administration, Jefferson, AR
March 8th, 12 noon – 1 pm
College of Public Health, Room 3202
Joseph W. Thompson, M.D., MPH
Director, Arkansas Center for Health Improvement
Kenley, Money, MA, MFA
Director, Information System Architecture, Arkansas Center for Health Improvement
T. Mac Bird, Ph.D., MS
UAMS, COPH Assistant Professor, Department of Health Policy and Management
Special Presentation from COPH Department of Environmental and Occupational Health
“Omics” Applications for Food Safety and Public Health
Si Hong Park, Ph.D.
Faculty Candidate
Center for Food Safety
University of Arkansas, Fayetteville
Thursday, March 3rd
11:30 am – 12:30 pm
