Biostatistics II (with Advanced R) for Public Health Practitioners and Researchers in Liberia

• Describing differences and similarities between mathematical and statistical modeling approaches

• Performing a simple linear regression using a built-in dataset in R

• Interpreting the coefficient from a simple linear regression model

• Describing the distribution of residuals from a regression model

• Recognizing whether linear regression is appropriate first approach for addressing a research question

• Visually and/or analytically evaluating the assumptions of linear regression

• Assessing criteria for potential confounding in a relationship between dependent and independent variables of interest

• Recognizing how secondary data analysis may limit full exploration of confounders and communicating such limitations

• Visually and/or analytically determining whether observations are exerting influence on the regression coefficients

• Describing why particular observations are more influential than others, in the context of a dataset

• Assessing linear regression assumptions for model with and without influential points

• Re-leveling categorical variables to specify a new reference level

• Scaling independent variables when they are on extremely different scales

• Visualizing count outcome variables

• Determining whether Poisson regression is an appropriate first step

• Implementing Poisson regression using the glm function

• Identifying and assessing Poisson regression assumptions

• Developing a table shell to reflect relevant simple and multiple regression results

• Identifying appropriate figures/graphs to support results of regression analysis

• Working on a team multiple regression analysis project

• Identifying variables to address a public health hypothesis