{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

R Code for discussion 6

# R Code for discussion 6 - #R code Discussion 6 Sta108 Fall...

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

1 #R code: Discussion 6. Sta108, Fall 2007, Utts ### Multiple Regression and Extra Sum of Squares #Example: Grocery Retailer: Problem 6.9 Data = read.table ( "CH06PR09.txt" ) names ( Data ) = c ( "Hours" , "Cases" , "Costs" , "Holiday" ) #scatterplot matrix for ALL variables in dataset pairs ( Data , pch = 19 ) #look for association between: #1. response variable and any of predictor variables #2. any two predictor variables #correlation matrix for ALL variables in dataset cor ( Data ) #gives correlation, r, measure of linear relationship b/w each pair of variables #fit multiple regression model Fit = lm ( Hours ~ Cases + Costs + Holiday , data = Data ) summary ( Fit ) #gives: parameter restimates, standard errors, t-statistic with p-value for testing #Ho: Beta.k = 0 #Ha: Beta.k not= 0, while all other parameters are kept in model #also, gives: sqrt(MSE), df, R-Sq, F-statistic with df and p-value for testing #Ho: Beta.k=0 for all k=1,2,..,p-1 #Ha: not all Beta.k are zero #(Test for regression relation) #variance-covariance matrix for vector of parameters, Beta vcov ( Fit )

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 ]}