Skip to main content
URMC / Psychiatry / Research / Quantitative Methods Core


Quantitative Methods Core (Qcore)

a person working with statistics

The Department of Psychiatry Quantitative Methods core (Qcore) provides department faculty with statistical support. The core is comprised of faculty members with advanced training in statistics who also have topical research areas of their own. This experience allows them to work in clear and practical ways with colleagues needing statistical support.

Statistical Support Services:

  • Answering questions about statistical methods, results, procedures, or problems
  • Analysis of data for faculty projects, including clinically-oriented program evaluations
  • Reviewing paper or grant sections for accuracy or clarity 
  • Power analyses and/or analytic sections for grant submissions
  • Pre-study consultation on data collection design and processes
  • Educational services, including meeting with faculty to explain statistical methods and procedure

Guidelines prior to submitting a project to Qcore

Administrative Data
The Qcore can help facilitate access to medical records data for analysis upon request. Note that the Qcore does not have direct access to this data, so the time frame for such projects depends on external factors, for example, the availability of ISD resources.

Data Cleaning Policy
Cleaning and warehousing data are not primary functions of the Qcore. The core will perform data management and cleaning required for analysis requests. However, the programming time involved will slow down analysis requests.

A Priori Hypotheses vs. Exploratory Analysis
Exploratory analysis is an important science component, even in well-developed areas. Therefore, the core encourages results by distinguishing between exploratory or hypothesis-generating analyses and testing a priori-hypotheses. The statistical approach and interpretation are different and should be distinct. The Qcore can assist write-ups of projects testing an initial a priori set of hypotheses, then pursuing post-hoc exploration.

Requesting Support

Faculty requests for statistical support can be submitted by clicking on the request button below. The Qcore will respond within 24 hours and, if needed, schedule a meeting. Analysis requests typically require a week, with time frames depending on the current queue. In rare cases of extremely dire circumstances, next-day emergency requests can be accommodated. 

Statistical Support Request

Provide important information about your request.


Qcore Team

Ben Chapman

Ben Chapman, PhD, MPH

The Quantitative Methods core is lead by Ben Chapman. Ben has a PhD in psychology with an MS in statistics and MPH focused on epidemiology. His statistical interests include measurement, predictive models, survival analysis, clinical trial methodology, methods for high dimensional data, and time series analysis. His topical work has been in social determinants of later life health outcomes, including cognitive impairment and mortality patterns.

Ian Cero

Ian Cero, PhD, MS

Ian Cero has PhD in Clinical Psychology and a master's degree in Probability and Statistics. His statistical background a range of methods, including social network analysis, agent-based models, multilevel models, missing data adjustments, and causal inference. His applied interests involve the development of social network enhancing interventions to prevent suicide among acute risk groups.

Patrick Walsh

Patrick Walsh, PhD MPH

Patrick Walsh has a PhD in Health Service Research and Policy and a Master's in Public Health. He has extensive experience utilizing quality improvement, clinical research study, and electronic medical record data to analyze healthcare utilization and health outcomes, as well as perform program evaluations. He has expertise in survey research, including survey development, data analysis, and qualitative assessments.

Daniel Maeng

Dan Maeng, PhD

Daniel Maeng, PhD is a health economist / health services researcher with methodological expertise in applied econometrics and causal inferences (e.g., instrumental variable, propensity score matching, difference-in-difference, healthcare cost data analysis, multilevel modeling, panel data analysis).  He has extensive research experiences analyzing large healthcare data, such as health insurance claims data and electronic medical records, as well as survey data.