Data Analyst I, Department of Medicine

Develop and implement innovative statistical and computational approaches for the analysis of large datasets. These datasets may utilize several types of available data sources, including public domain. Supports the generation of preliminary results for grant submissions, writes and edits grants and grant progress reports. Stay current on innovations in methods and tools for statistical analyses. Participate in the implementation of new tool development for deployment and supports current tools deployed. Participates in the design of a project. Leads a research effort in the direction set forth by the PI and the specific project. KNOWLEDGE/SKILLS/ABILITIESTechnical Learning Learns new data tools and platforms with minimal guidance.Quickly adapts to changes in data systems or reporting requirements.Applies new statistical methods or visualization techniques to improve analysis.?Detail Orientation Ensures data accuracy before publishing dataDocuments assumptions and methodologies clearly.Reviews peer work for quality assurance.?Time Management Prioritizes multiple data and statistical analysis requests effectively.Meets deadlines for recurring and ad hoc requests.Allocates time for both reactive and proactive analysis.?Statistical MethodsRegression and GLMs Fits linear/logistic/Poisson models; checks assumptions and interprets effects.Classification and Diagnostics Evaluates ROC- and PR-AUC, calibration, and threshold trade-offs.Resampling and Validation Uses bootstrap/permutation; applies k-fold/nested cross-validation.Survival Analysis Builds KM curves, log-rank tests; fits Cox PH and verifies assumptions.Enrichment Analysis Performs GSEA; uses hypergeometric/Fisher tests with FDR control.Clustering Applies k-means/hierarchical; evaluates with silhouette; uses PCA/UMAP for structure.Mixed/Hierarchical Models Models random effects for clustered/repeated measures; reports ICC.Nonparametric Methods Applies rank-based tests (Wilcoxon, KruskalWallis, Spearman/Kendall).Time Series and Forecasting Analyzes trend/seasonality; fits ARIMA/ETS and backtests accuracy.Power and Sample Size Computes requirements for t-tests/ANOVA/regression/survival.

Created: 2025-11-15