team-2

Collaboration 

Looking for collaboration with Faculty?

Connect With CIDA

 

 

Center for Innovative Design & Analysis

Collaborations are generally arranged through the Center for Innovative Design and Analysis (CIDA); although some partnerships are arranged with individual faculty based on expertise. The faculty focus on collaborative and team science partnerships. For short-term consulting needs please visit the CIDA – Consulting Center

 

 

Continuum of Interaction and Integration in Team Research 

Consulting

Research Collaboration

Team Science

An investigator works on a problem. Largely on his/her own and drops data off for analysis.

A group works on a scientific problem, each bringing some expertise to the problem.

 

Each member works on a separate part of the larger problem, integrating parts at the end.

 

The interaction of the lead investigators varies from limited to frequent, normally regarding data sharing and/or brainstorming.

A team works on a research problem with each member bringing specific expertise to the table.

 

There are regular meetings and discussions of the team’s overall goals, objectives of the individuals on the team, and future steps.

 

One person takes the lead while other members have key leadership roles in achieving the shared goals.

Outcome:

Report, perhaps co-authored publication.

Outcome:
Multiple co-authored publications with analysts as 2nd authors.

 

Co-investigator grants.

 

Biostatisticians develop subject area knowledge.

 

Outcome:

Analyst at multiple PI.

 

Analysts publishing first-author papers in subject area journals and in methodology journals.

 

Analysts attend subject-area conferences and have a network in that area.  

 

Areas of Expertise

  • Adaptive clinical trial designs
  • Administrative health record data, claims data
  • Artificial Intelligence, machine learning, deep learning
  • Bayesian inference, Bayesian methods, Bayesian hierarchical modeling, Bayesian modeling
  • Bioinformatics, genomics, epigenomics, proteomics, metabolomics, omics, multi-omics
  • Biomarker discovery, validation, and evaluation, proteomic biomarker development
  • Chronic obstructive pulmonary disease
  • Clustering methods, dimension reduction
  • Collaborative biostatistics, collaborative team science, best practices for statistical collaboration
  • Comparative effectiveness analysis using propensity score methods
  • Complex data management, heterogeneous signals analysis, mixed data types integration
  • Causal inference, observational studies
  • CT imaging biomarkers, medical image analysis, medical image computing (PET, CT, MRI, ultrasound, X-ray, microscopy, digital pathology), image biomarker discovery, segmentation, classification, registration, retrieval, synthesis
  • Data integration, multi-modal data integration
  • Data safety and monitoring
  • Data visualization, visual analysis, human-centered computing
  • Discrete data methods
  • Early life determinants of diabetes and obesity in children
  • EHR observational analyses
  • Endocrinology research, reproductive health
  • Environmental Health
  • Evaluation of serum biomarkers for health outcomes
  • Factor analysis, psychometric methods, structural equation modeling, hierarchical linear modeling
  • General clinical research
  • Health outcomes research
  • Hematology
  • High-dimensional inference, high-dimensional regression, statistical analysis of network data, network analysis, network models
  • Interpretability in machine learning
  • Joint models, multivariate longitudinal models, methodological development for joint models
  • Linkage analysis, statistical genetics
  • Longitudinal and correlated data, longitudinal data analysis, non-normal longitudinal data analysis, structured correlation analysis
  • Machine learning methods for biomedical applications, predictive modeling for time-to-event and binary outcomes
  • Meta-analysis, meta-analyses
  • Methods for incorporating information sharing
  • Microbiome, microbiome data analysis, microbiome-metabolome interactions
  • Mixture modeling
  • Missing data methods
  • Model development, model selection
  • Permutation methods
  • Prediction modeling, predictive modeling
  • SAS programming, statistical computation/software
  • Single-cell data analysis
  • Statistical methods for image computing, statistical methods for network data
  • Substance use disorders
  • Survival analysis
  • Wearable device data


CMS Login