Home  |   Schedule    |   Classes   |   Problem Sets   |   Labs   |   e-Mail

 Biostatistics 140.654
 Methods in Biostatistics IV

  Department of Biostatistics, Johns Hopkins Bloomberg School of Public Health

 

• Weighted least squares
• Robust variance estimation
• Weighted least squares
• Robust variance estimation
• Model building
• Motivation: Why more than linear regression

• Overview
• Formulation/link functions
• Maximum likelihood estimation, inference
• Deviance

• The logistic function
• Parameter interpretation:
  • Simple
  • Multiple: Main, interactions
• Nonlinear / smooth curves
• Grouped, individual models

• ML fitting
  • Iteratively reweighted least squares
• Wald inference
• Inference using nested models, deviances
• Deviance test distribution

• Goodness of fit
• Leverage and influence
• Residual checking
• Case Study, part I

• Sensitivity/Specificity
• Receiver Operating Characteristic (ROC) curve
• Polytomous, ordinal logistic regression

• Method overview
• Bias/variance tradeoff: AIC, BIC
• Case Study

• Poisson regression
• Negative binomial regression

• Odds ratio equivalence
• Unmatched fitting, interpretation
• Example

• Setup: nuisance parameters
• Conditional logistic regression
• Fitting/Inference

• Incidence: beyond the logit link/collapsibility
• Censoring
• Rate/Cohort studies with Poisson regression

• Model
• Interpretation

• Estimation
• Hierarchical framework

• Paradigms defining causality
• Potential outcomes
• Propensity scoring

• FEH: Harrell, F.E. (2001), Regression Modeling Strategies, With Applications to Linear Models, Logistic Regression, and Survival Analysis, New York: Springer.

• SW: Weisberg S. (1985), Applied Linear Regression, 2nd. Ed., New York: John Wiley & Sons

 Home   |   Schedule   |   Classes   |   Problem Sets   |   Labs   |   e-Mail

 Last edited: 01 April, 2008

 ©2008, Department of Biostatistics,
            Johns Hopkins Bloomberg School of Public Health
            All Rights Reserved