Assignment 9
mydata <- read.csv("C:\\Users\\RISHI RAHUL\\Desktop\\DS\\16 Basic Statistics\\Level-1\\Computer_Data.csv")
mydata <- mydata[-1]
attach(mydata)
# First Moment Business Decision (Mean, Median, Range)
summary(mydata)
## 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 cd multi premium ads
## Min. :14.00 no :3351 no :5386 no : 612 Min. : 39.0
## 1st Qu.:14.00 yes:2908 yes: 873 yes:5647 1st Qu.:162.5
## Median :14.00 Median :246.0
## Mean :14.61 Mean :221.3
## 3rd Qu.:15.00 3rd Qu.:275.0
## Max. :17.00 Max. :339.0
## trend
## Min. : 1.00
## 1st Qu.:10.00
## Median :16.00
## Mean :15.93
## 3rd Qu.:21.50
## Max. :35.00
# Second Moment Business Decision (Var, SD)
var(speed)
## [1] 447.6498
sd(price)
## [1] 580.804
# Skewness - Third Moment Business Decision
library(e1071)
skewness(screen)
## [1] 1.633225
# Kurtosis - Fourth Moment Business Decision
kurtosis(ram)
## [1] 1.458699
boxplot(price)
#Boxplot
boxplot(speed, horizontal = TRUE)
# Histogram
hist(ads)
# Plotting the TREND Column data
plot(trend)
# Scatter plot for the complete Dataset
plot(mydata)
# Correlation
cor(mydata[,1:5])
## price speed hd ram screen
## price 1.0000000 0.3009765 0.4302578 0.6227482 0.2960415
## speed 0.3009765 1.0000000 0.3723041 0.2347605 0.1890741
## hd 0.4302578 0.3723041 1.0000000 0.7777263 0.2328015
## ram 0.6227482 0.2347605 0.7777263 1.0000000 0.2089537
## screen 0.2960415 0.1890741 0.2328015 0.2089537 1.0000000
model <- lm(price~speed+hd+ram+screen)
summary(model)
##
## Call:
## lm(formula = price ~ speed + hd + ram + screen)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1048.21 -297.09 -48.29 214.30 2538.47
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 10.33311 88.22222 0.117 0.907
## speed 5.24930 0.27836 18.858 <2e-16 ***
## hd -0.57936 0.03507 -16.520 <2e-16 ***
## ram 76.74545 1.53586 49.969 <2e-16 ***
## screen 105.52592 6.18879 17.051 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 427.5 on 6254 degrees of freedom
## Multiple R-squared: 0.4586, Adjusted R-squared: 0.4583
## F-statistic: 1325 on 4 and 6254 DF, p-value: < 2.2e-16
confint(model,level = 0.95)
## 2.5 % 97.5 %
## (Intercept) -162.6127433 183.2789563
## speed 4.7036118 5.7949871
## hd -0.6481112 -0.5106089
## ram 73.7346413 79.7562585
## screen 93.3937677 117.6580711
#influence.measures(model)
#predict(model,interval = "predict")
library(mvinfluence)
## Warning: package 'mvinfluence' was built under R version 3.5.1
## Loading required package: car
## Warning: package 'car' was built under R version 3.5.1
## Loading required package: carData
## Loading required package: heplots
## Warning: package 'heplots' was built under R version 3.5.1
influenceIndexPlot(model)
plot(model)
