graphicalModels_4perPage

# graphicalModels_4perPage - Outline Graphical Models Data...

This preview shows pages 1–3. Sign up to view the full content.

Graphical Models Data Mining Prof. Dawn Woodard School of ORIE Cornell University 1 Outline 1 Graphical Models 2 Naive Bayes Assumption: Pr ( { X 1 , X 2 ,..., X K }| Y )= K Y k = 1 Pr ( X k | Y ) Naive Bayes assumes that, conditional on the outcome variable, the predictors are independent. 4 Credit Variables Recall the variables for the credit data: Credit V1 V14 V2 V3 5

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

View Full Document
A Full Model A full model for Pr ( Y , { X k } ) must take into account all the two-way, three-way, etc. interactions between the variables: Credit V1 V14 V2 V3 6 Naive Bayes Naive Bayes only models the interaction between the outcome and each of the predictors: Credit V1 V14 V2 V3 7 Naive Bayes This type of graph is called a conditional independence graph , graphical model , Bayesian network ,or belief network , and shows the model’s independence assumptions: Credit V1 V14 V2 V3 8 Credit Data Do you think the naive Bayes assumption holds (approximately) for the credit data? Recall that the predictors are variables like: Amount in checking account Duration of credit in months Credit history Duration of present employment Marital status 9
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### Page1 / 5

graphicalModels_4perPage - Outline Graphical Models Data...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online