{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

# vars - Explanatory Variables in Logistic...

This preview shows pages 1–2. Sign up to view the full content.

1 Explanatory Variables in Logistic Regression [explanatory_vars_in_logistic_regr.doc] The following is based on Hosmer & Lemeshow, Applied Logistic Regression Part I 1. Graphically & numerically describe the outcome var & potential explanatory vars. 2. List the potential explanatory variables in order of their anticipated, conceptual importance in relation to the outcome variable, briefly noting (a) the dimensions of such importance; (b) the anticipated type of relationship to the outcome variable; & (c) how each explanatory variable relates to each of the other explanatory variables. 2. In delineating the variables in these ways, consider the kinds of outcome var/explanatory var relationships discussed in Agresti & Finlay, chapter 10. Part II 1. Crosscheck the outcome var with potential explanatory vars: at this preliminary stage, select as potential explanatory vars those that have at least a modest association with the outcome var, entering the var names in a table. 2. Check collinearity among the quantitative vars: § graph comparative boxplots & a scatterplot matrix for the quantitative vars § estimate the model in OLS (including only quantitative explanatory vars on the right-hand side) § VIF 3. Explore univariable models with each potential explanatory var: record each coef, se & CI, & p-value. Provisionally select a var if its p-value<=0.25.

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### Page1 / 3

vars - Explanatory Variables in Logistic...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online