Wednesday, January 8
Wed, Jan 8, 7:30 AM - 2:00 PM
Pacific Ballroom Prefunction
Conference Registration
ICHPS Hours
Wed, Jan 8, 8:30 AM - 10:15 AM
Pacific AB
CS19 - Statistical Methods to Inform Evaluations of Gun Policies: Challenges and Opportunities for Statisticians
Invited
Organizer(s): Elizabeth Stuart, Johns Hopkins Bloomberg School of Public Health
Chair(s): Elizabeth Stuart, Johns Hopkins Bloomberg School of Public Health
8:35 AM
Using synthetic control methods in gun policy research: concealed carry laws and suicide mortality
Alexander D. McCourt, Johns Hopkins Bloomberg School of Public Health
8:55 AM
Evaluating methods to estimate the effect of state laws on firearm deaths
Beth Ann Griffin, RAND Corporation
9:15 AM
Bracketing in the Comparative Interrupted Time-Series Design to Address Concerns about History Interacting with Group: Evaluating Missouri Handgun Purchaser Law
Luke John Keele, University of Pennsylvania
9:35 AM
9:55 AM
Wed, Jan 8, 8:30 AM - 10:15 AM
Pacific C
CS20 - Linked Data for Evidence-Based Policymaking
Invited
Organizer(s): Jennifer D Parker, NCHS
Chair(s): Jennifer Madans, National Center for Health Statistics
8:35 AM
Leveraging Linked Data for Evidence Based Policymaking
Lisa B. Mirel, CDC/NCHS/OAE/SPB
8:55 AM
Identification of Opioid Involved Health Outcomes Using Linked Hospital Care and Mortality Data
Presentation
Carol DeFrances, National Center for Health Statistics
9:15 AM
On the utility of prediction models in large government surveys: using linked administrative-survey data to inform analyses of more contemporaneous survey data
Presentation
Yulei He, National Center for Health Statistics
9:35 AM
Research Data Centers for Data Access
Jennifer D Parker, NCHS
9:55 AM
Wed, Jan 8, 8:30 AM - 10:15 AM
East Coast Ballroom
CS21 - Measuring and Improving Health Care Quality
Contributed
Chair(s): Ronald Gangnon, University of Wisconsin-Madison
WITHDRAWN - Does the medical consortium reform improve hospital ef?ciency? Evidence from secondary general hospitals in Shanxi, China, 2013-2017
Xiaojun Lin, West China School of Public Health, Sichuan University
8:35 AM
Using z-scores to measure within-hospital outcome improvement over time in a regional quality improvement collaborative
Anne H. Cain-Nielsen, Department of Surgery, University of Michigan
8:50 AM
Hospital report cards: matched design versus machine learning
Ali I. Hashmi, IBM Watson Health
9:05 AM
Estimating the causal effect of an observation versus inpatient stay on 30-day readmission: Comparison to risk-standardized estimates and implications for quality measurement
Ben Marafino, Stanford University
9:20 AM
Can Machine Learning Reduce the Burden of Health Care Quality Measurement?
Christina A Nguyen, Massachusetts Institute of Technology
9:35 AM
Design and analysis considerations for adjusted comparative quality surveys
Alan M. Zaslavsky, Harvard Medical School
9:50 AM
It’s getting hot in here: A novel application of heatmaps to health outcomes research
Jessica A. Lavery, Memorial Sloan Kettering Cancer Center
10:05 AM
Wed, Jan 8, 8:30 AM - 10:15 AM
West Coast Ballroom
CS22 - Comparative Effectiveness in the Real World
Contributed
Chair(s): Justin Williams, UCLA
8:30 AM
Comparative Studies of Bayesian Causal Inference with Gaussian Process Prior
Bin Huang, Cincinnati Children's Hospital Medical Center
8:45 AM
Towards causally interpretable meta-analysis: transporting inferences from multiple studies to a target population
Sarah E Robertson, Brown University
9:00 AM
Harmonizing Multi-Site Electronic Health Records Data for Critical Care Comparative Effectiveness Studies: How do we ensure that data quality is equivalent to traditional clinical trials?
Presentation
Annie N Simpson, Medical University of South Carolina
9:15 AM
The future meets the past: Applying features of retrospective study design to improve prospective comparative effectiveness studies
Presentation
Jennifer H Lindquist, Department of Veterans Affairs
9:30 AM
Real-world effectiveness of approved anticancer agents among Medicare beneficiaries
Michael Curry, Memorial Sloan Kettering Cancer Center
9:45 AM
Health Information Technology and Innovation to Generate Insights
Jim Zhiming Li, Pfizer Inc
10:00 AM
Wed, Jan 8, 8:30 AM - 10:15 AM
Porthole
CS23 - Intensive Longitudinal Data
Contributed
Chair(s): Lisa M Lix, University of Manitoba
8:30 AM
Mixed Location Scale Hidden Markov Model with An Application to Ecological Momentary Assessment Data
Xiaolei Lin, Fudan University
8:45 AM
A Shared-Parameter Location-Scale Mixed Model for Non-ignorable Nonresponses in Self-Initiated Event-Contingent Assessments in Ecological Momentary Assessment Data
Presentation
Qianheng Ma, The University of Chicago
9:00 AM
Evaluating Reasonableness Tests for Longitudinal Measurement Invariance using CFA
Elizabeth Grandfield, University of Kansas Medical Center
9:15 AM
Two-stage and shared parameter mixed-effects location scale models for intensive longitudinal data
Presentation
Donald Hedeker, University of Chicago
9:30 AM
Multivariate joint modeling of mean and variation and time-lagged intensive longitudinal methods to assess associations between marijuana use and craving variation.
Maryam Skafyan, University of Northern Colorado
9:45 AM
Functional modeling approach for discrete scalar outcomes and account for the cross-dependence of multilevel repeated functional observations with Structured Penalties
Mostafa Zahed, University of Northern Colorado
10:00 AM
SAPTrees: Using Conditional Inference Trees to Characterize Heterogeneity in Human Activity Patterns
Presentation
Roland Brown, University of Minnesota
Wed, Jan 8, 10:30 AM - 12:15 PM
Pacific AB
CS24 - Causal Inference Methods for Health Policy Research
Invited
Organizer(s): Jason Roy, Rutgers School of Public Health
Chair(s): Arman Oganisian, University of Pennsylvania
10:35 AM
Differences-in-Differences with Multi-State Outcomes
John Graves, Vanderbilt University
11:05 AM
Causal estimation of scaled treatment effects with multiple outcomes in a community health worker study
Nandita Mitra, University of Pennsylvania
11:35 AM
The use of synthetic control and other covariate adjustment strategies for policy evaluation
Presentation
Elizabeth Stuart, Johns Hopkins Bloomberg School of Public Health
12:05 PM
Wed, Jan 8, 10:30 AM - 12:15 PM
Pacific C
CS25 - Methods for Quantifying Value of Information in Health Care Policy
Invited
Organizer(s): Aasthaa Bansal, The Comparative Health Outcomes, Policy, and Economics (CHOICE) Institute, University of Washington
Chair(s): Laura Anne Hatfield, Harvard Medical School
10:35 AM
An overall conceptualization of the VOI approach and statistical description of different VOI metrics
Anirban Basu, The Comparative Health Outcomes, Policy, and Economics (CHOICE) Institute, University of Washington
11:05 AM
Detailed statistical methods for computing the Expected Value of Sample Information metric
Hawre Jalal, University of Pittsburgh
11:35 AM
A VOI framework for personalizing the timing of biomarker collection
Aasthaa Bansal, The Comparative Health Outcomes, Policy, and Economics (CHOICE) Institute, University of Washington
12:05 PM
Wed, Jan 8, 10:30 AM - 12:15 PM
East Coast Ballroom
CS26 - Subgroups and Heterogeneity
Contributed
Chair(s): Frank Yoon, IBM Watson Health
WITHDRAWN - Who is most vulnerable? Estimating heterogeneous causal effects of air quality regulations with a novel principal stratification-based Bayesian machine learning approach
Falco J. Bargagli Stoffi, Imt School for Advanced Studies/KU Leuven
10:35 AM
Hierarchical Bayesian estimation of subgroup effects in large healthcare policy evaluations
Jonathan Gellar, Mathematica Policy Research, Inc.
10:55 AM
A cautionary note about assessing heterogeneity over outcome scores in randomized trials
Hongseok Kim, Brown University
11:15 AM
Causal Clustering: A new approach to analysis of treatment effect heterogeneity
Presentation
Kwangho Kim, Carnegie Mellon University
11:35 AM
Proposing & Testing Sub-groups with Heterogeneous Treatment Effects: A Sequence of Two Studies
Rahul Ladhania, University of Pennsylvania
11:55 AM
Generalizability of subgroup effects
Marissa J Seamans, UCLA Fielding School of Public Health
Wed, Jan 8, 10:30 AM - 12:15 PM
West Coast Ballroom
CS27 - Quasi-Experimental Methods in Health Policy
Contributed
Chair(s): Evan Paul Carey, Assistant Professor, Health Data Science, St Louis University
WITHDRAWN - A Bayesian difference-in-differences framework for measuring the impact of primary care redesign on diabetes outcomes
James Paul Normington, University of Minnesota
10:35 AM
Do Birds of a Methodological Feather Flock Together?
Carrie E Fry, Harvard University
10:50 AM
Extending difference-in-difference methods to test the impact of state-level marijuana laws on substance use using published prevalence estimates.
Christine Mauro, Columbia University Mailman School of Public Health
11:05 AM
Effects of Medicaid expansion policy on the prevention of multiple forms of violence
Reshmi Nair, Johns Hopkins Bloomberg School of Public Health
11:20 AM
The use of segmented regression for evaluation of an interrupted time series study involving complex intervention: The CaPSAI Project Experience
Ndema Abu Habib, The World Health Organization
11:35 AM
Evaluating A Key Instrumental Variable Assumption Using Randomization Tests
Luke John Keele, University of Pennsylvania
11:50 AM
A generalized interrupted time series model for assessing complex health care interventions
Maricela Francis Cruz, University of California, Irvine
12:05 PM
Wed, Jan 8, 10:30 AM - 12:15 PM
Porthole
CS28 - Measuring Health Inequities to Inform Policy
Contributed
Chair(s): Caroline Thompson, San Diego State University
WITHDRAWN - Analysis of Competing Risks Survival and Comorbidity in Stomach Cancer Patients to Inform Cancer Survivorship Policy in Korea
Hyunsoon Cho, National Cancer Center, Korea
10:35 AM
How Do We Identify Homelessness in Large Health Care Data? Measuring Variation in Composition and Comorbidities by Definition
Wyatt P Bensken, Case Western Reserve University
10:55 AM
Geographical socioeconomic inequalities in cancer mortality using vital statistics in Japan: 1995-2014
Yuri Ito, Osaka Medical College
11:15 AM
Early Life Circumstances and Health Inequality among Older Adults in China and the U.S
Xi Chen, Yale School of Public Health
11:35 AM
Reproductive coercion sometimes works: Evaluating whether young Black women reporting reproductive coercion are more likely to become pregnant
Presentation
Janet E Rosenbaum, SUNY Downstate SPH
11:55 AM
Understanding Male Caregivers’ Emotional, Financial, and Physical Burden in the United States
Presentation
Priya Kohli, Connecticut College
Wed, Jan 8, 12:15 PM - 1:30 PM
Lunch (on own)
ICHPS Hours
Wed, Jan 8, 1:30 PM - 3:00 PM
Pacific AB
GS02 - Closing Plenary Session
Invited
Wed, Jan 8, 3:15 PM - 5:15 PM
Pacific C
Workshop 12 - Producing high-quality, reproducible reports using R and Markdown.
Workshop
Organizer(s): Robin A Donatello, California State University, Chico
Data analysts tend to write a lot of reports, describing their analyses and results, for their collaborators or to document their work for future reference. When we first start out, we often write an R script with all of the work, and would just send emails to collaborators, describing the results and attaching various graphs. In discussing the results, there often can be confusion about which graph was which.
Moving to writing formal reports, with Word or LaTeX, there is still much time spent on getting the figures to look right. Mostly, the concern is about page breaks and generating reproducible results. Imagine the work that has to be done to find the right analysis code to fix a problem in a report generated 4 years ago on an old data set, that you hope you can still find.
Ideally, such analysis reports are reproducible documents: If an error is discovered, or if some additional subjects are added to the data, you can just re-compile the report and get the new or corrected results (versus having to reconstruct figures, paste them into a Word document, and further hand-edit various detailed results).
This workshop will walk you through a key package in R called knitr, that is the leading solution to these types of reports. It allows you to create a document that is a mixture of text and chunks of code. When the document is processed by knitr, chunks of code will be executed, and graphs or other results inserted into a professional looking final document. Reports can be created in many formats such as Word, PDF or as HTML webpages, and are highly customizable.
Prior knowledge of R is helpful, but not necessary.
Download Handouts
Wed, Jan 8, 3:15 PM - 5:15 PM
West Coast Ballroom
Workshop 13 - Promote Yourself: Make Your Own Professional Website Without Knowing HTML.
Workshop
Organizer(s): Robin A Donatello, California State University, Chico
Linkedin is great, your department or office website may have a bio on a page for you, but you need your own space to share your work. To demonstrate your talent, share recent projects or research, create and curate scientific content. Share your course lecture notes, blog about your recent research, or present analysis results in all their grisly detail as a supplement to a presentation or manuscript. This hands-on workshop will walk you through the process of creating two types of websites with no knowledge of HTML or CSS needed. The first type is a simple site that links a series of web pages you create using the Markdown language together into a website framework. This is ideal for a small project, such as presenting class materials, or an interactive dashboard. The second type of website is ideal for users who wish to write a blog or present a more “modern” feel to their website. This website uses the website generator Hugo, but again no knowledge of Hugo will be necessary. We will use the R studio environment to build these websites using Markdown, and demonstrations of how live code and output can be shown in these webpages, but no direct knowledge of R is required. Both methods require knowledge of version control and use of github.
Download Handouts
Wed, Jan 8, 3:15 PM - 5:45 PM
East Coast Ballroom
Workshop 14 - "So What?: Communicating the Value of your Research"
Workshop
Instructor(s): Meg Nakahara, COMPASS
This COMPASS science communication training will help participants share what they do, what they know—and most importantly, why it matters—in clear, lively terms. Grounded in the latest research on science communication, this training is designed to help participants find the relevance of their science for the audiences they most want to reach—journalists, policymakers, the public, and even other scientists.
Download Handouts
Pacific Ballroom Prefunction
ICHPS Hours
Pacific AB
Invited
Alexander D. McCourt, Johns Hopkins Bloomberg School of Public Health
Beth Ann Griffin, RAND Corporation
Luke John Keele, University of Pennsylvania
Pacific C
Invited
Lisa B. Mirel, CDC/NCHS/OAE/SPB
Presentation Carol DeFrances, National Center for Health Statistics
Presentation Yulei He, National Center for Health Statistics
Jennifer D Parker, NCHS
East Coast Ballroom
Contributed
Xiaojun Lin, West China School of Public Health, Sichuan University
Anne H. Cain-Nielsen, Department of Surgery, University of Michigan
Ali I. Hashmi, IBM Watson Health
Ben Marafino, Stanford University
Christina A Nguyen, Massachusetts Institute of Technology
Alan M. Zaslavsky, Harvard Medical School
Jessica A. Lavery, Memorial Sloan Kettering Cancer Center
West Coast Ballroom
Contributed
Bin Huang, Cincinnati Children's Hospital Medical Center
Sarah E Robertson, Brown University
Presentation Annie N Simpson, Medical University of South Carolina
Presentation Jennifer H Lindquist, Department of Veterans Affairs
Michael Curry, Memorial Sloan Kettering Cancer Center
Jim Zhiming Li, Pfizer Inc
Porthole
Contributed
Xiaolei Lin, Fudan University
Presentation Qianheng Ma, The University of Chicago
Elizabeth Grandfield, University of Kansas Medical Center
Presentation Donald Hedeker, University of Chicago
Maryam Skafyan, University of Northern Colorado
Mostafa Zahed, University of Northern Colorado
Presentation Roland Brown, University of Minnesota
Pacific AB
Invited
John Graves, Vanderbilt University
Nandita Mitra, University of Pennsylvania
Presentation Elizabeth Stuart, Johns Hopkins Bloomberg School of Public Health
Pacific C
Invited
Anirban Basu, The Comparative Health Outcomes, Policy, and Economics (CHOICE) Institute, University of Washington
Hawre Jalal, University of Pittsburgh
Aasthaa Bansal, The Comparative Health Outcomes, Policy, and Economics (CHOICE) Institute, University of Washington
East Coast Ballroom
Contributed
Falco J. Bargagli Stoffi, Imt School for Advanced Studies/KU Leuven
Jonathan Gellar, Mathematica Policy Research, Inc.
Hongseok Kim, Brown University
Presentation Kwangho Kim, Carnegie Mellon University
Rahul Ladhania, University of Pennsylvania
Marissa J Seamans, UCLA Fielding School of Public Health
West Coast Ballroom
Contributed
James Paul Normington, University of Minnesota
Carrie E Fry, Harvard University
Christine Mauro, Columbia University Mailman School of Public Health
Reshmi Nair, Johns Hopkins Bloomberg School of Public Health
Ndema Abu Habib, The World Health Organization
Luke John Keele, University of Pennsylvania
Maricela Francis Cruz, University of California, Irvine
Porthole
Contributed
Hyunsoon Cho, National Cancer Center, Korea
Wyatt P Bensken, Case Western Reserve University
Yuri Ito, Osaka Medical College
Xi Chen, Yale School of Public Health
Presentation Janet E Rosenbaum, SUNY Downstate SPH
Presentation Priya Kohli, Connecticut College
ICHPS Hours
Pacific AB
Invited
Pacific C
Workshop
Data analysts tend to write a lot of reports, describing their analyses and results, for their collaborators or to document their work for future reference. When we first start out, we often write an R script with all of the work, and would just send emails to collaborators, describing the results and attaching various graphs. In discussing the results, there often can be confusion about which graph was which.
Moving to writing formal reports, with Word or LaTeX, there is still much time spent on getting the figures to look right. Mostly, the concern is about page breaks and generating reproducible results. Imagine the work that has to be done to find the right analysis code to fix a problem in a report generated 4 years ago on an old data set, that you hope you can still find.
Ideally, such analysis reports are reproducible documents: If an error is discovered, or if some additional subjects are added to the data, you can just re-compile the report and get the new or corrected results (versus having to reconstruct figures, paste them into a Word document, and further hand-edit various detailed results).
This workshop will walk you through a key package in R called knitr, that is the leading solution to these types of reports. It allows you to create a document that is a mixture of text and chunks of code. When the document is processed by knitr, chunks of code will be executed, and graphs or other results inserted into a professional looking final document. Reports can be created in many formats such as Word, PDF or as HTML webpages, and are highly customizable.
Prior knowledge of R is helpful, but not necessary.
Download Handouts
West Coast Ballroom
Workshop
Linkedin is great, your department or office website may have a bio on a page for you, but you need your own space to share your work. To demonstrate your talent, share recent projects or research, create and curate scientific content. Share your course lecture notes, blog about your recent research, or present analysis results in all their grisly detail as a supplement to a presentation or manuscript. This hands-on workshop will walk you through the process of creating two types of websites with no knowledge of HTML or CSS needed. The first type is a simple site that links a series of web pages you create using the Markdown language together into a website framework. This is ideal for a small project, such as presenting class materials, or an interactive dashboard. The second type of website is ideal for users who wish to write a blog or present a more “modern” feel to their website. This website uses the website generator Hugo, but again no knowledge of Hugo will be necessary. We will use the R studio environment to build these websites using Markdown, and demonstrations of how live code and output can be shown in these webpages, but no direct knowledge of R is required. Both methods require knowledge of version control and use of github.
Download Handouts
East Coast Ballroom
Workshop
This COMPASS science communication training will help participants share what they do, what they know—and most importantly, why it matters—in clear, lively terms. Grounded in the latest research on science communication, this training is designed to help participants find the relevance of their science for the audiences they most want to reach—journalists, policymakers, the public, and even other scientists.
Download Handouts