MLRQ3 <- read.csv("D:\\DataScience\\Assignments\\MultiLinearRegression\\Computer_Data.csv")
attach(MLRQ3)
colnames(MLRQ3)
## [1] "X" "price" "speed" "hd" "ram" "screen" "cd"
## [8] "multi" "premium" "ads" "trend"
contrasts(MLRQ3$cd)
## yes
## no 0
## yes 1
MLRQ3$copyofcd <- NA
MLRQ3$copyofcd[MLRQ3$cd=="no"]=0
MLRQ3$copyofcd[MLRQ3$cd=="yes"]=1
contrasts(MLRQ3$multi)
## yes
## no 0
## yes 1
MLRQ3$copyofmulti <- NA
MLRQ3$copyofmulti[MLRQ3$multi=="no"]=0
MLRQ3$copyofmulti[MLRQ3$multi=="yes"]=1
contrasts(MLRQ3$premium)
## yes
## no 0
## yes 1
MLRQ3$copyofpremium <- NA
MLRQ3$copyofpremium[MLRQ3$premium=="no"]=0
MLRQ3$copyofpremium[MLRQ3$premium=="yes"]=1
dataQ3 <- MLRQ3[c("price","speed","hd","ram","screen","ads","trend","copyofcd","copyofmulti","copyofpremium")]
View(dataQ3)
summary(dataQ3)
## price speed hd ram
## Min. : 949 Min. : 25.00 Min. : 80.0 Min. : 2.000
## 1st Qu.:1794 1st Qu.: 33.00 1st Qu.: 214.0 1st Qu.: 4.000
## Median :2144 Median : 50.00 Median : 340.0 Median : 8.000
## Mean :2220 Mean : 52.01 Mean : 416.6 Mean : 8.287
## 3rd Qu.:2595 3rd Qu.: 66.00 3rd Qu.: 528.0 3rd Qu.: 8.000
## Max. :5399 Max. :100.00 Max. :2100.0 Max. :32.000
## screen ads trend copyofcd
## Min. :14.00 Min. : 39.0 Min. : 1.00 Min. :0.0000
## 1st Qu.:14.00 1st Qu.:162.5 1st Qu.:10.00 1st Qu.:0.0000
## Median :14.00 Median :246.0 Median :16.00 Median :0.0000
## Mean :14.61 Mean :221.3 Mean :15.93 Mean :0.4646
## 3rd Qu.:15.00 3rd Qu.:275.0 3rd Qu.:21.50 3rd Qu.:1.0000
## Max. :17.00 Max. :339.0 Max. :35.00 Max. :1.0000
## copyofmulti copyofpremium
## Min. :0.0000 Min. :0.0000
## 1st Qu.:0.0000 1st Qu.:1.0000
## Median :0.0000 Median :1.0000
## Mean :0.1395 Mean :0.9022
## 3rd Qu.:0.0000 3rd Qu.:1.0000
## Max. :1.0000 Max. :1.0000
plot(dataQ3)
cor(dataQ3)
## price speed hd ram screen
## price 1.00000000 0.30097646 0.43025779 0.62274824 0.296041474
## speed 0.30097646 1.00000000 0.37230410 0.23476050 0.189074122
## hd 0.43025779 0.37230410 1.00000000 0.77772630 0.232801530
## ram 0.62274824 0.23476050 0.77772630 1.00000000 0.208953740
## screen 0.29604147 0.18907412 0.23280153 0.20895374 1.000000000
## ads 0.05454047 -0.21523206 -0.32322200 -0.18166971 -0.093919429
## trend -0.19998694 0.40543833 0.57779013 0.27684384 0.188614445
## copyofcd 0.19734334 0.25825980 0.50357041 0.43850441 0.129487662
## copyofmulti -0.01665139 0.08417193 0.09280483 0.04549689 -0.001740414
## copyofpremium -0.08069636 0.11420791 0.19692359 0.19714459 0.018745223
## ads trend copyofcd copyofmulti
## price 0.05454047 -0.19998694 0.19734334 -0.016651388
## speed -0.21523206 0.40543833 0.25825980 0.084171934
## hd -0.32322200 0.57779013 0.50357041 0.092804830
## ram -0.18166971 0.27684384 0.43850441 0.045496894
## screen -0.09391943 0.18861444 0.12948766 -0.001740414
## ads 1.00000000 -0.31855251 -0.06109108 -0.030394260
## trend -0.31855251 1.00000000 0.44578018 0.210907431
## copyofcd -0.06109108 0.44578018 1.00000000 0.432179298
## copyofmulti -0.03039426 0.21090743 0.43217930 1.000000000
## copyofpremium -0.15202274 0.04210738 0.21607660 0.124774741
## copyofpremium
## price -0.08069636
## speed 0.11420791
## hd 0.19692359
## ram 0.19714459
## screen 0.01874522
## ads -0.15202274
## trend 0.04210738
## copyofcd 0.21607660
## copyofmulti 0.12477474
## copyofpremium 1.00000000
#cor2pcor(cor(dataQ3))
attach(dataQ3)
## The following objects are masked from MLRQ3:
##
## ads, hd, price, ram, screen, speed, trend
modelQ3 <- lm(price~speed+hd+ram+screen+ads+trend+copyofcd+copyofmulti+copyofpremium)
summary(modelQ3)
##
## Call:
## lm(formula = price ~ speed + hd + ram + screen + ads + trend +
## copyofcd + copyofmulti + copyofpremium)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1093.77 -174.24 -11.49 146.49 2001.05
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 307.98798 60.35341 5.103 3.44e-07 ***
## speed 9.32028 0.18506 50.364 < 2e-16 ***
## hd 0.78178 0.02761 28.311 < 2e-16 ***
## ram 48.25596 1.06608 45.265 < 2e-16 ***
## screen 123.08904 3.99950 30.776 < 2e-16 ***
## ads 0.65729 0.05132 12.809 < 2e-16 ***
## trend -51.84958 0.62871 -82.470 < 2e-16 ***
## copyofcd 60.91671 9.51559 6.402 1.65e-10 ***
## copyofmulti 104.32382 11.41268 9.141 < 2e-16 ***
## copyofpremium -509.22473 12.34225 -41.259 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 275.3 on 6249 degrees of freedom
## Multiple R-squared: 0.7756, Adjusted R-squared: 0.7752
## F-statistic: 2399 on 9 and 6249 DF, p-value: < 2.2e-16
plot(modelQ3)
#x<- stepAIC(modelQ3)