SLR Q4

Simple linear regression Q4

a <-read.csv("C:\\Users\\Harisha\\Desktop\\Datascience Assignments\\Simple linear regression\\Salary_Data.csv")

attach(a)
View(a)

# 1St Movement Business Decission(Mean,Meadian,Range)
summary(a)

##  YearsExperience      Salary      
##  Min.   : 1.100   Min.   : 37731  
##  1st Qu.: 3.200   1st Qu.: 56721  
##  Median : 4.700   Median : 65237  
##  Mean   : 5.313   Mean   : 76003  
##  3rd Qu.: 7.700   3rd Qu.:100545  
##  Max.   :10.500   Max.   :122391

# 2nd movement Business Decission(Variance,Standard Deviation)
var(YearsExperience)

## [1] 8.053609

var(Salary)

## [1] 751550960

sd(YearsExperience)

## [1] 2.837888

sd(Salary)

## [1] 27414.43

# 3rd & 4th Business Decission(Skewness and Kurtosis)
library(e1071)
skewness(Salary)

## [1] 0.3194946

kurtosis(Salary)

## [1] -1.395477

barplot(Salary)

hist(Salary)

boxplot(Salary, horizontal = T)

qqnorm(Salary)
qqline(Salary)

skewness(YearsExperience)

## [1] 0.3424477

kurtosis(YearsExperience)

## [1] -1.17293

barplot(YearsExperience)

hist(YearsExperience)

barplot(YearsExperience)

qqnorm(YearsExperience)
qqline(YearsExperience)

cor(Salary,YearsExperience)

## [1] 0.9782416

plot(a)

SLR4 <- lm(Salary~YearsExperience)
summary(SLR4)

## 
## Call:
## lm(formula = Salary ~ YearsExperience)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -7958.0 -4088.5  -459.9  3372.6 11448.0 
## 
## Coefficients:
##                 Estimate Std. Error t value Pr(>|t|)    
## (Intercept)      25792.2     2273.1   11.35 5.51e-12 ***
## YearsExperience   9450.0      378.8   24.95  < 2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 5788 on 28 degrees of freedom
## Multiple R-squared:  0.957,  Adjusted R-squared:  0.9554 
## F-statistic: 622.5 on 1 and 28 DF,  p-value: < 2.2e-16

# R squared value is >.8 hence its a strong model.