Statistical Consulting Service
Contact Information
Directions
Software
The Department of Biostatistics and Computational Biology of the School of Medicine and Dentistry offers a statistical consulting service to support faculty and non-faculty researchers of the Medical Center, as well as investigators outside the Medical Center who require help with projects and grant preparation, depending on the staffing level and the mutual interest between statisticians and investigators. Services range from purely advisory assistance to complete statistical analysis as well as support for data management. Charges for statistical consulting, programming and data management support, and computer usage are billed to investigators using established hourly rates.
We offer support for all types of projects and have expertise in a wide range of topics including: |
|
|
Structural Equation Models (SEM) Models for Mixture Study Populations |
Equivalence and Non-inferiority Testing |
_________________________________________________________________
Contact Information
The Consulting Service is headed by Xin Tu, PhD, coordinated by Susan Messing, MS, and assisted by the Faculty, Post-doctoral and senior PhD students, and programmers and database developers. Faculty members are available to serve as investigators for grant submissions.
To schedule a statistical consultation, please contact Susan Messing at Susan_Messing@urmc.rochester.edu.
Directions
The Department of Biostatistics and Computational Biology is located on the fourth floor of the Saunders Research Building, at 265 Crittenden Boulevard, next to the University of Rochester School of Nursing.
Printable map with directions to the Saunders Research Building
Software
We use a variety of software packages including the popular SAS, R, STATA, SPSS, and a wider range of specialized packages such as MPlus, LISREL, Winbugs, MULTILOG, PASS, and NQUERY. We have also developed and distributed a large collection of SAS macros and R functions to facilitate research in the biomedical and psychosocial sciences. Details about the available free software are available at CTSpedia.org and at the Department of Biostatistics and Computational Biology's Software Web page.
Expertise
Models for Instrumentation
- Principal Component Analysis and Factor Analysis (Exploratory or Confirmatory) for scale construction
- ROC Analysis for diagnostic and screening tests
- Models for internal item and scale-level consistency (e.g., Cronbach coefficient alpha and intra-class correlation)
- Agreement, reliability and reproducibility analyses (e.g., Cohen’s kappa, Concordance Correlation Coefficient, and Intraclass correlation)
Structural Equation Models (SEM)
- Mediation Analysis
- General structural relationships, or path analysis, involving multiple endogenous and exogenous variables
Models for Mixture Study Populations
- Zero-modified models for count data such as zero-inflated Poisson (ZIP), zero-inflated negative binomial (ZINB) and Hurdle Model
- Latent growth mixture models (LGMM)
- Cluster analysis
- Finite mixture models
- Latent class analysis and latent class scaling analysis
Longitudinal Data Analysis Models
- Generalized Linear Mixed-effects Models (GLMM) for multi-level nested and clustered study designs
- Weighted Generalized Estimating Equations (WGEE) for robust inference with skewed data
- Rank-based tests (e.g., longitudinal Mann-Whitney-Wilcoxon rank sum test) for robust inference with outliers
Models for Causal Inference
- Methods for addressing selection bias in non- and semi-randomized studies such as Propensity Score, Instrumental Variable (IV) method and Marginal Structural Models (MSM).
- Methods for addressing confounders in post-randomization for randomized controlled trials (RCT) (e.g., Principal Stratification methods and Structural Nested Models)
- Doubly Robust estimation of treatment effects
- Cost and Cost-effectiveness analysis using Propensity Score
Survival Analysis
- Parametric and Semi-parametric models
- Continuous and discrete survival data
- Repeated Events (Multiple Event Time Data)
- Cure models
Equivalency and Noninferiority Testing
- Parametric and non-parametric tests for equivalence
- Methods for continuous and non-continuous outcomes
- Confidence-interval inclusion rules for equivalence
- Equivalence tests for paired observations
Clinical Trials Methodology
- Clinical trial design (e.g., protocol development and/or review)
- Effect size calculations for longitudinal data
- Power analysis for longitudinal study designs
- Power analysis for Structural Equation Models
- Power analysis for stepped wedge design
- Randomization schema (simple, block, urn and adaptive procedures)
- Data Monitoring Committee (DMC) support
Social Network Analysis
- Social network metric construction
- Inference for social network connectivity
- Regression models with network connections as responses
- Agent based models
- Social network diffusion models
Models for High-Dimensional and High-Volume Data
- Analysis of Flow Cytometry data
- Analysis of Cell Kinetics data
- Interrupted times series modeling (ARIMA)
- Imaging analysis
- Analysis of online social media data (e.g., data from Twitter)
- Analysis of actigraphy and electrocardiography
Bioinformatics Services
- Array data processing and clinical/lab data integration
- High-throughput “-omics” data analysis: microarray, RNA-Seq, proteomics, microbiomics data
- Gene regulatory, natural population structure and other biological network analysis
- Statistical genetics, including pedigree inference, and the analysis of polymorphic data (microsatellites, SNPs)
- Amnis-ImageStream Gen X data analysis
Computational Biology and Mathematical Biology
- Computational modeling of biological systems
- Systems biology analysis and modeling
- Molecular dynamics modeling and simulations
- Analysis of technological monitoring data, including human trajectory reconstruction, actigraphy, and electrocardiography
