Scientific & Technical Core

The Scientific and Technical Core (STC) supports junior and established PDHP affiliates and others as they design, create, and use new data to advance population science by enhancing methods used for each of these three activities, and providing technical support and guidance for computing.

The STC helps researchers advance methods for collecting and analyzing data for population studies. We provide researchers with access to the methodological resources and training necessary for improving and fielding innovative and large-scale surveys; analyzing big data and complex sample survey data; linking administrative and organic data; designing and implementing experimental and quasi-experimental studies; applying new data science techniques; and working with restricted data. To do so, we offer seminars, workshops, and in-depth statistical consultation; provide analytic and data management support on funded projects; mentor researchers; facilitate collaborative research; and guide access to diverse U-M resources.

The STC supports high-performance computing, data access and storage, and data science techniques. We provide access to scalable, flexible, and customizable high performance computing through virtual computing and file storage infrastructure provided by PSC, ISR, and UM; ensure that computing and data storage cover the entire range of data security and protection needs of PSC researchers, including confidential and restricted data; and provide technical support for data science methods that offer emerging data visualization and analysis techniques.

In addition to the free services offered above, fractional allocations of PDHP staff time are also available for hire by funded projects for regular long-term assistance with any technical or methodological needs your project may have. These fractions are available on a first come first serve basis, and projects lacking full indirect cost coverage will be subject to an additional surcharge to cover overhead costs. For further details and current availability, please contact Paul Schulz.

STC Personnel:

Brady West
Brady West
(PDHP Scientific & Technical Core Director) is a PSC faculty affiliate and a Research Associate Professor in the Survey Research Center (SRC) of the Institute for Social Research (ISR) at the University of Michigan-Ann Arbor. He has considerable experience leading large and complex methodological and data collection projects. He is the PI of the PDB/NICHD R01-funded American Family Health Study, which is a new national web/mail data collection project that aims to demonstrate the cost efficiencies in national data collections that can be gained by using sequential mixed mode approaches. He is also the co-PI of a PDB/NICHD R25 grant that provides international training on the implementation of responsive and adaptive survey design techniques. West currently serves on the Senior Staff Advisory Committee of SRC and directs SRC’s Survey Methodology Program (SMP), which conducts investigator-initiated methodological research and supports other SRC data collection projects. West’s substantive research interests center on family demography and fertility, substance use and abuse, and health disparities among population subgroups defined by sexual identity and race/ethnicity. His methodological research interests include total survey error, interviewer effects, selection bias in surveys, responsive and adaptive design, and the analysis of complex sample survey data.

Paul Schulz
(managing director of Scientific & Technical Core Operations and consulting statistician) manages the daily operations of the Scientific and Technical Core, including directing the workshop series and consulting operation. Schulz has over 20 years of experience at ISR (both on the project side providing consultation and analysis work with NSFG, SCA, MTF, and many other prominent surveys and the operations side with SRO).  He has managed the PDHP team of statisticians and data scientists since 2018.  He specializes in statistical methods and computing, including hypothesis testing, data analysis and modeling, sampling (including weight creation and adjustment, and power calculations), as well as the use of secure computing enclaves (SRCVDI, Likert cluster, and Flux/Great Lakes). Paul writes code in Stata and SAS for general-purpose desktop computing, and R and Python for selected applications, such as data visualization and web scraping/automation, among other uses.
Liz Hanley
Liz Hanley
(consulting statistician and data scientist) is a consulting statistician and data scientist at the Population Studies Center within the University of Michigan Institute for Social Research. Liz’s expertise is in natural language processing, data mining, and data visualization. Depending on the project, Liz writes code in Python, R, and SQL, as well as the front-end HTML/CSS/JavaScript stack for custom web applications and data visualization. Liz has instructional experience running workshops on a variety of data science topics including sentiment analysis, topic analysis, and use of the U-M high-performance Cavium computing cluster. In the past she has also served as a guest instructor for Cornell University’s Data Analytics in R certificate program, which covers statistical modeling and machine learning concepts in the R programming environment.
Huchen LiuHuchen Liu (consulting statistician and data scientist) combines expertise in computational methods and statistical modelling with a background in political science to form a unique skillset that he applies to social science research. He has expertise in analysis of complex survey data (using R, Python, Stata, and SPSS) as well as web-scraping and web automation techniques to efficiently acquire and process web-native data. These skills, combined with his experience leading his own publications, uniquely position Huchen to support all aspects of the research process. Huchen received his PhD in political science from UC San Diego and joined the STC from Princeton, where he was a postdoctoral research associate in the Department of Politics.