ISYE 6501 HW 08 Data Warehousing and Foundations of Business Intelligence (California State University, Fullerton).pdf

lOMoARcPSD|67928686




ISYE 6501 HW 08 Data Warehousing and Foundations of

Business Intelligence (California State University, Fullerton)


Tran Tran

ISYE 6501

5 March 2025

Homework 8

Question 11.1

#a. stepwise

> # call out data from data table

> rm(list = ls())

> set.seed(42)

> data = read.table("/Users/joeytran/Downloads/hw5/uscrime.txt", header = TRUE)

>

> #now we need to create our initial model 1 for stepwise regression

> model = lm(Crime~., data = data)

>

> step (

+ model, scope = list(lower_sc = formula(lm(Crime~., data = data)),

+ upper_sc = formula(lm(Crime~., data = data))),

+ direction = "both"

+)

Start: AIC=514.65

Crime ~ M + So + Ed + Po1 + Po2 + LF + M.F + Pop + NW + U1 +

U2 + Wealth + Ineq + Prob + Time

Call:

, lOMoARcPSD|67928686




lm(formula = Crime ~ M + So + Ed + Po1 + Po2 + LF + M.F + Pop +

NW + U1 + U2 + Wealth + Ineq + Prob + Time, data = data)

Coefficients:

(Intercept) M So Ed Po1 Po2 LF

-5.984e+03 8.783e+01 -3.803e+00 1.883e+02 1.928e+02 -1.094e+02 -6.638e+02

M.F Pop NW U1 U2 Wealth Ineq

1.741e+01 -7.330e-01 4.204e+00 -5.827e+03 1.678e+02 9.617e-02 7.067e+01

Prob Time

-4.855e+03 -3.479e+00

>

> #As shown on the result for stepwise regression above, it have removed 7 factors that

> #do not have significance

>

> #using the remainder of the factors, we're going to put together a new model that

> #works for the given data

> model1 = lm(Crime~M+Ed+Po1+M.F+U1+U2+Ineq+Prob, data = data)

> summary(model1)

Call:

lm(formula = Crime ~ M + Ed + Po1 + M.F + U1 + U2 + Ineq + Prob,

data = data)

Residuals:

Min 1Q Median 3Q Max -444.70

-111.07 3.03 122.15 483.30

Coefficients:

Estimate Std. Error t value Pr(>|t|)

(Intercept) -6426.10 1194.61 -5.379 4.04e-06 ***

M 93.32 33.50 2.786 0.00828 **