ch 5 exercise

## ch 5 exercise
> mydata=ch5_exercise <- read.csv("C:/Users/benny/Downloads/ch5_exercise.csv")
> View(mydata)

#for EACH VARIABLE (5), do the following:
    ## VAR A
> shapiro.test(mydata$variable_a) #shaprio-wilk normality test (normal if p >/= 0.05)
    ### p-val = 0.02838 < 0.05 therfore NOT normal distribution
> hist(mydata$variable_a,main = "Histogram of Var. A",xlab = "Variable A",)
> boxplot(mydata$variable_a,main="Boxplot of Var. A")
> qqnorm(mydata$variable_a,main = "Q-Q Plot of Var. A")
> qqline(mydata$variable_a) #generates a Q-Q plot
    ##step E: FALSE, data distribution is NOT normal

    ##VAR B
> shapiro.test(mydata$variable_b) #p-val = 0.19 > 0.05 therefore normal dist :)
> hist(mydata$variable_b,main = "Histogram of Var. B",xlab = "Variable B",)
> boxplot(mydata$variable_b,main="Boxplot of Var. B")
> qqnorm(mydata$variable_b,main = "Q-Q Plot of Var. B")
> qqline(mydata$variable_b)
    ##step E: TRUE, data distribution IS normal

    ##VAR C
> shapiro.test(mydata$variable_c) #pval = 0.18
> hist(mydata$variable_c,main = "Histogram of Var. C",xlab = "Variable C",)
> boxplot(mydata$variable_c,main="Boxplot of Var. C")
> qqnorm(mydata$variable_c,main = "Q-Q Plot of Var. C")
> qqline(mydata$variable_c)
    ##step E: TRUE, dist is normal

    ##VAR D
> shapiro.test(mydata$variable_d) #p-val = 0.002 <0.05
> hist(mydata$variable_d,main = "Histogram of Var. D",xlab = "Variable D",)
> boxplot(mydata$variable_d,main="Boxplot of Var. B")
> qqnorm(mydata$variable_d,main = "Q-Q Plot of Var. B")
> qqline(mydata$variable_d)
    ##step E: FALSE, dist is NOT normal

    ##VAR E
> shapiro.test(mydata$variable_e) #p-val = 0.2317
> hist(mydata$variable_e,main = "Histogram of Var. E",xlab = "Variable E",)
> boxplot(mydata$variable_e,main="Boxplot of Var. E")
> qqnorm(mydata$variable_e,main = "Q-Q Plot of Var. E")
> qqline(mydata$variable_e)
    ##step E: TRUE